WO2005036314A2 - Method and system of diagnosing a processing system using adaptive multivariate analysis - Google Patents
Method and system of diagnosing a processing system using adaptive multivariate analysis Download PDFInfo
- Publication number
- WO2005036314A2 WO2005036314A2 PCT/US2004/025599 US2004025599W WO2005036314A2 WO 2005036314 A2 WO2005036314 A2 WO 2005036314A2 US 2004025599 W US2004025599 W US 2004025599W WO 2005036314 A2 WO2005036314 A2 WO 2005036314A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- coefficients
- substrate
- adaptive
- value
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/67005—Apparatus not specifically provided for elsewhere
- H01L21/67242—Apparatus for monitoring, sorting or marking
- H01L21/67253—Process monitoring, e.g. flow or thickness monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Definitions
- the present invention relates to a method of diagnosing a processing system using principal components analysis (PCA), and more particularly to the utilization of an updated PCA.
- PCA principal components analysis
- PCA principal component analysis
- One object of the present invention is to solve or mitigate any or all of the above described problems, or other problems in the prior art.
- Another object of the present invention is to provide a robust PCA model that enables monitoring for a single processing system over a long horizon.
- Yet another object of the present invention is to provide a robust PCA model that is capable of useful application to more than one processing system.
- These and other objects of the present invention may be met by a method of diagnosing a processing system using adaptive multivariate analysis in accordance with the present invention.
- a method of monitoring a processing system for processing a substrate during the course of semiconductor manufacturing includes: acquiring data from the processing system for a plurality of observations, the data comprising a plurality of data parameters; constructing a principal components analysis (PCA) model from the data, including centering coefficients; acquiring additional data from the processing system, the additional data having an additional observation of the plurality of data parameters; adjusting the centering coefficients to produce updated adaptive centering coefficients for each of the data parameters in the PCA model; applying the updated adaptive centering coefficients to each of data parameters in the PCA model; determining at least one statistical quantity from the additional data using the PCA model; setting a control limit for the at least one statistical quantity; and comparing the at least one statistical quantity to the control limit.
- PCA principal components analysis
- the method can further include: determining scaling coefficients from the PCA model; adjusting the scaling coefficients to produce updated adaptive scaling coefficients for each of the data parameters in the PCA model; and applying the updated adaptive scaling coefficients to each of the data parameters in the PCA model.
- a principal components analysis (PCA) model for monitoring a processing system for processing a substrate during the course of semiconductor manufacturing
- PCA principal components analysis
- an improvement is described including: an adaptive centering coefficient for each data parameter during a current observation of the given data parameter, the adaptive centering coefficient combining an old value of the adaptive centering coefficient and the current value of the data parameter for the current observation, wherein the old value includes the mean value of the data parameter during a plurality of observations preceding the current observation.
- the improvement can further include: an adaptive scaling coefficient for each data parameter during a current observation of the given data parameter, the adaptive scaling coefficient comprising application of a recursive standard deviation filter, the formula combining an old value of the adaptive scaling coefficient, the current value of each data parameter for the current observation, and an old value of the adaptive centering coefficient, wherein the old value of the adaptive scaling coefficient comprises the standard deviation of the data parameter during a plurality of observations preceding the current observation and the old value of the adaptive centering coefficient comprises the mean value of the data parameter during a plurality of observations preceding the current observation.
- a processing system for processing a substrate during the course of semiconductor manufacturing including: a process tool; and a process performance monitoring system coupled to the process tool having a plurality of sensors coupled to the process tool, and a controller coupled to the plurality of sensors and the process tool, wherein the controller includes means for acquiring data from the plurality of sensors for a plurality of observations, the data including a plurality of data parameters; means for constructing a principal components analysis (PCA) model from the data, including centering coefficients; means for acquiring additional data from the plurality of sensors; means for adjusting the centering coefficients to produce updated adaptive centering coefficients for each of the data parameters; means for applying the updated adaptive centering coefficients to each of the data parameters in the PCA model; means for determining at least one statistical quantity from the additional data using the PCA model; means for setting a control limit for the at least one statistical quantity; and means for comparing the at least one statistical quantity to the control limit.
- PCA principal components analysis
- processing system can further include: means for determining scaling coefficients from the PCA model; means for adjusting the scaling coefficients to produce updated adaptive scaling coefficients for each of the data parameters in the PCA model; and means for applying the updated adaptive scaling coefficients to each of the data parameters in the PCA model.
- a process performance monitoring system to monitor a processing system for processing a substrate during the course of semiconductor manufacturing including: a plurality of sensors coupled to the processing system; and a controller coupled to the plurality of sensors and the processing system, wherein the controller includes means for acquiring data from the plurality of sensors for a plurality of observations, the data having a plurality of data variables; means for acquiring data from the plurality of sensors for a plurality of observations, the data comprising a plurality of data parameters; means for constructing a principal components analysis (PCA) model from the data, including centering coefficients; means for acquiring additional data from the plurality of sensors; means for adjusting the centering coefficients to produce updated adaptive centering coefficients for each of the data parameters; means for applying the updated adaptive centering coefficients to each of the data parameters in the PCA model; means for determining at least one statistical quantity from the additional data using the PCA model; means for setting a control limit for the at least one statistical quantity; and means for comparing the at least
- PCA principal components analysis
- processing system can further include: means for dete ⁇ nining scaling coefficients from the PCA model; means for adjusting the scaling coefficients to produce updated adaptive scaling coefficients for each of the data parameters in the PCA model; and means for applying the updated adaptive scaling coefficients to each of the data parameters in the PCA model.
- a method of monitoring a first processing system for processing a substrate during the course of semiconductor manufacturing includes: acquiring data from a second processing system for a plurality of observations, the data having a plurality of data parameters; constructing a principal components analysis (PCA) model from the data for the second processing system, including centering coefficients; acquiring additional data from the first processing system, the additional data includes an additional observation of the plurality of data parameters; adjusting the centering coefficients to produce updated adaptive centering coefficients for each of the data parameters in the PCA model; applying the updated adaptive centering coefficients to each of the data parameters in the PCA model; determining at least one statistical quantity from the additional data using the PCA model; setting a control limit for the at least one statistical quantity; and comparing the at least one statistical quantity to the control limit.
- PCA principal components analysis
- the method can further include: determining scaling coefficients from the PCA model; adjusting the scaling coefficients to produce updated adaptive scaling coefficients for each of the data parameters in the PCA model; and applying the updated adaptive scaling coefficients to each of the data parameters in the PCA model.
- the method includes: monitoring a plurality of data parameters from the processing system for each substrate run within the plurality of substrate runs; identifying a fault substrate run, within the plurality of substrate runs using multivariate analysis, in which the process fault occurred; selecting a first substrate run preceding the fault substrate run; calculating a first plurality of mean values for each of the plurality of data parameters during the first substrate run; selecting a second substrate run following the fault substrate run; calculating a second plurality of mean values for each of the plurality of data parameters during the second substrate run; determining the absolute value of a plurality of differences between the second plurality of mean values and the first plurality of mean values for each of the plurality of data parameters; calculating a plurality of standard deviations for each of the plurality of data parameters during at least one of the first substrate run and the second substrate run; normalizing the plurality of differences by the plurality of standard deviations for each of the plurality of data parameters; determining the largest value of the normalized differences; and identifying the data parameter amongst the plurality of data parameters
- a method for classifying a process fault occurring during a plurality of substrate runs in a processing system includes: monitoring a plurality of data parameters from the processing system for each substrate run within the plurality of substrate runs; identifying a fault substrate run, within the plurality of substrate runs using multivariate analysis, in which the process fault occurred; selecting a first substrate run preceding the fault substrate run; calculating a first plurality of standard deviations for each of the plurality of data parameters during the first substrate run; selecting a second substrate run following the fault substrate run; calculating a second plurality of standard deviations for each of the plurality of data parameters during the second substrate run; determining the absolute value of a plurality of differences between the second plurality of standard deviations and the first plurality of standard deviations for each of the plurality of data parameters; calculating a plurality of mean values for each of the plurality of data parameters during one of the first substrate run and the second substrate run; normalizing the plurality of differences by the plurality of mean values for
- FIG. 1 shows a material processing system according to a preferred embodiment of the present invention
- FIG. 2 shows a material processing system according to one embodiment of the present invention
- FIG. 3 shows a material processing system according to another embodiment of the present invention.
- FIG. 4 shows a material processing system according to a further embodiment of the present invention.
- FIG. 5 shows a material processing system according to an additional embodiment of the present invention
- FIG. 6A presents an exemplary calculated Q-statistic using static centering and scaling coefficients
- FIG. 6B presents an exemplary calculated Q-statistic using adaptive centering and scaling coefficients following the first 500 substrates;
- FIG. 7 presents an exemplary Q contribution plot;
- FIG. 8 presents an exemplary summary statistic for two data parameters;
- FIG. 9A presents an exemplary model mean movement metric plot for two substrate ranges;
- FIG. 9B presents an exemplary summary statistic for the highest values in the movement metric plot of FIG. 9 A;
- FIG. 10 presents an exemplary calculated Q-statistic using static centering and scaling coefficients applied to a second processing system
- FIG. 11 presents an exemplary calculated Q-statistic using adaptive centering and scaling coefficients applied to a second processing system
- FIG. 12 illustrates a computer system for implementing various embodiments of the present invention.
- FIG. 13 presents a method of monitoring a processing system according to an embodiment of the present invention.
- a material processing system 1 is depicted in FIG. 1 that includes a process tool 10 and a process performance monitoring system 100.
- the process performance monitoring system 100 includes a plurality of sensors 50 and a controller 55.
- the material processing system 1 can include a plurality of process tools 10.
- the sensors 50 are coupled to the process tool 10 to measure tool data and the controller 55 is coupled to the sensors 50 in order to receive tool data.
- the controller 55 is further coupled to process tool 10.
- the controller 55 is configured to monitor the performance of processing system 1 using the (tool) data parameters.
- the process performance can, for example, include the detection of process faults.
- the material processing system 1 utilizes a plasma for material processing.
- the material processing system 1 includes an etch chamber.
- the material processing system 1 includes a photoresist coating chamber such as, for example, a photoresist spin coating system; a photoresist patterning chamber such as, for example, an ultraviolet (UV) lithography system; a dielectric coating chamber such as, for example, a spin- on-glass (SOG) or spin-on-dielectric (SOD) system; a deposition chamber such as, for example, a chemical vapor deposition (CVD) system or a physical vapor deposition (PVD) system; a rapid thermal processing (RTP) chamber such as, for example, a RTP system for thermal annealing; or a batch-processing vertical furnace.
- a photoresist coating chamber such as, for example, a photoresist spin coating system
- a photoresist patterning chamber such as, for example, an ultraviolet (UV) lithography system
- the material processing system 1 includes process tool 10, substrate holder 20, upon which a substrate 25 to be processed is affixed, gas injection system 40, and vacuum pumping system 58.
- Substrate 25 can be, for example, a semiconductor substrate, a wafer, or a liquid crystal display (LCD).
- Process tool 10 can be, for example, configured to facilitate the generation of plasma in processing region 45 adjacent a surface of substrate 25, where plasma is formed via collisions between heated electrons and an ionizable gas. An ionizable gas or mixture of gases is introduced via gas injection system 40, and the process pressure is adjusted.
- plasma is utilized to create materials specific to a predetermined materials process, and to aid either the deposition of material to substrate 25 or the removal of material from the exposed surfaces of substrate 25.
- controller 55 can be used to control vacuum pumping system 58 and gas injection system 40.
- Substrate 25 can be, for example, transferred into and out of process tool 10 through a slot valve (not shown) and chamber feed-through (not shown) via robotic substrate transfer system where it is received by substrate lift pins (not shown) housed within substrate holder 20 and mechanically translated by devices housed therein. Once substrate 25 is received from substrate transfer system, it is lowered to an upper surface of substrate holder 20.
- substrate 25 can be affixed to the substrate holder 20 via an electrostatic clamping system 28.
- substrate holder 20 can further include a cooling system including a re-circulating coolant flow that receives heat from substrate holder 20 and transfers heat to a heat exchanger system (not shown), or when heating, transfers heat from the heat exchanger system.
- gas can be delivered to the back-side of the substrate via a backside gas system 26 to improve the gas-gap thermal conductance between substrate 25 and substrate holder 20.
- a backside gas system can be utilized when temperature control of the substrate is required at elevated or reduced temperatures.
- temperature control of the substrate can be useful at temperatures in excess of the steady-state temperature achieved due to a balance of the heat flux delivered to the substrate 25 from the plasma and the heat flux removed from substrate 25 by conduction to the substrate holder 20.
- heating elements such as resistive heating elements, or thermo-electric heaters/coolers can be included.
- substrate holder 20 includes an electrode through which RF power is coupled to plasma in processing region 45.
- substrate holder 20 can be electrically biased at an RF voltage via the transmission of RF power from RF generator 30 through impedance match network 32 to substrate holder 20.
- the RF bias can serve to heat electrons to form and maintain plasma.
- the system can operate as a reactive ion etch (RIE) reactor, where the chamber and upper gas injection electrode serve as ground surfaces.
- RIE reactive ion etch
- a typical frequency for the RF bias can range from 1 MHz to 100 MHz and is preferably 13.56 MHz.
- RF power can be applied to the substrate holder electrode at multiple frequencies.
- impedance match network 32 serves to maximize the transfer of RF power to plasma in processing chamber 10 by minimizing the reflected power.
- Various match network topologies e.g., L-type, ⁇ -type, T-type, etc.
- automatic control methods can be utilized.
- process gas can be, for example, introduced to processing region 45 through gas injection system 40.
- Process gas can, for example, include a mixture of gases such as argon, CF 4 and O 2 , or argon, C F 8 and O for oxide etch applications, or other chemistries such as, for example, O 2 /CO/Ar/C 4 F 8 , O 2 /CO/Ar/C 5 F 8 , O 2 /CO/Ar/C 4 F 6 , O 2 /Ar/C 4 F 6 , N 2 /H 2 .
- gases such as argon, CF 4 and O 2 , or argon, C F 8 and O for oxide etch applications, or other chemistries such as, for example, O 2 /CO/Ar/C 4 F 8 , O 2 /CO/Ar/C 5 F 8 , O 2 /CO/Ar/C 4 F 6 , O 2 /Ar/C 4 F 6 , N 2 /H 2 .
- Gas injection system 40 includes a showerhead, where process gas is supplied from a gas delivery system (not shown) to the processing region 45 through a gas injection plenum (not shown), a series of baffle plates (not shown) and a multi-orifice showerhead gas injection plate (not shown).
- Vacuum pump system 58 can, for example, include a turbo-molecular vacuum pump (TMP) capable of a pumping speed up to 5000 liters per second (and greater) and a gate valve for throttling the chamber pressure.
- TMP turbo-molecular vacuum pump
- a 1000 to 3000 liter per second TMP is generally employed.
- TMPs are useful for low pressure processing, typically less than 50 mTorr. At higher pressures, the TMP pumping speed falls off dramatically.
- a mechanical booster pump and dry roughing pump can be used.
- a device for monitoring chamber pressure (not shown) is coupled to the process chamber 16.
- process performance monitoring system 100 includes plurality of sensors 50 coupled to process tool 10 to measure tool data and controller 55 coupled to the sensors 50 to receive tool data.
- the sensors 50 can include both sensors that are intrinsic to the process tool 10 and sensors extrinsic to the process tool 10.
- Sensors intrinsic to process tool 10 can include those sensors pertaining to the functionality of process tool 10 such as the measurement of the Helium backside gas pressure, Helium backside flow, electrostatic chuck (ESC) voltage, ESC current, substrate holder 20 temperature (or lower electrode (LEL) temperature), coolant temperature, upper electrode (UEL) temperature, forward RF power, reflected RF power, RF self-induced DC bias, RF peak-to-peak voltage, chamber wall temperature, process gas flow rates, process gas partial pressures, chamber pressure, capacitor settings (i.e., C] and C 2 positions), a focus ring thickness, RF hours, focus ring RF hours, and any statistic thereof.
- sensors pertaining to the functionality of process tool 10 such as the measurement of the Helium backside gas pressure, Helium backside flow, electrostatic chuck (ESC) voltage, ESC current, substrate holder 20 temperature (or lower electrode (LEL) temperature), coolant temperature, upper electrode (UEL) temperature, forward RF power, reflected RF power, RF self-induced DC bias,
- sensors extrinsic to process tool 10 can include those not directly related to the functionality of process tool 10 such as a light detection device 34 for monitoring the light emitted from the plasma in processing region 45 as shown in FIG. 2, or an electrical measurement device 36 for monitoring the electrical system of process tool 10 as shown in FIG. 2.
- the light detection device 34 can include a detector such as a (silicon) photodiode or a photomultiplier tube (PMT) for measuring the total light intensity emitted from the plasma.
- the light detection device 34 can further include an optical filter such as a narrow-band interference filter.
- the light detection device 34 includes a line CCD (charge coupled device) or CID (charge injection device) array and a light dispersing device such as a grating or a prism.
- light detection device 34 can include a monochromator (e.g., grating/detector system) for measuring light at a given wavelength, or a spectrometer (e.g., with a rotating grating) for measuring the light spectrum such as, for example, the device described in U.S. Patent No. 5,888,337.
- the light detection device 34 can include a high resolution OES sensor from Peak Sensor Systems.
- OES sensor has a broad spectrum that spans the ultraviolet (UV), visible (VIS) and near infrared (NIR) light spectrums.
- UV ultraviolet
- VIS visible
- NIR near infrared
- the resolution is approximately 1.4 Angstroms, that is, the sensor is capable of collecting 5550 wavelengths from 240 to 1000 nm.
- the sensor is equipped with high sensitivity miniature fiber optic UV-VIS- NIR spectrometers which are, in turn, integrated with 2048 pixel linear CCD arrays.
- the spectrometers in one embodiment of the present invention receive light transmitted through single and bundled optical fibers, where the light output from the optical fibers is dispersed across the line CCD array using a fixed grating. Similar to the configuration described above, light emitting through an optical vacuum window is focused onto the input end of the optical fibers via a convex spherical lens.
- the electrical measurement device 36 can include, for example, a current and/or voltage probe, a power meter, or spectrum analyzer.
- a current and/or voltage probe for example, plasma processing systems often employ RF power to form plasma, in which case, an RF transmission line, such as a coaxial cable or structure, is employed to couple RF energy to the plasma through an electrical coupling element (i.e., inductive coil, electrode, etc.).
- Electrical measurements using, for example, a current-voltage probe can be exercised anywhere within the electrical (RF) circuit, such as within an RF transmission line.
- the measurement of an electrical signal such as a time trace of voltage or current, permits the transformation of the signal into frequency space using discrete Fourier series representation (assuming a periodic signal).
- a voltage-current probe can be, for example, a device as described in detail in pending U.S. Application Serial No. 60/259,862 filed on January 8, 2001, and U.S. Patent No. 5,467,013, each of which is incorporated herein by reference in its entirety.
- electrical measurement device 36 can include a broadband RF antenna useful for measuring a radiated RF field external to material processing system 1.
- a commercially available broadband RF antenna is a broadband antenna such as Antenna Research Model RAM-220 (0.1MHz to 300MHz).
- the plurality of sensors 50 can include any number of sensors, intrinsic and extrinsic, which can be coupled to process tool 10 to provide tool data to the controller 55.
- Controller 55 includes a microprocessor, memory, and a digital I/O port (potentially including D/A and/or A/D converters) capable of generating control voltages sufficient to communicate and activate inputs to material processing system 1 as well as monitor outputs from material processing system 1. As shown in FIG. 2, controller 55 can be coupled to and exchange information with RF generator 30, impedance match network 32, gas injection system 40, vacuum pump system 58, backside gas delivery system 26, electrostatic clamping system 28, light detection device 34, and electrical measurement device 36. A program stored in the memory is utilized to interact with the aforementioned components of a material processing system 1 according to a stored process recipe.
- controller 55 is a DELL PRECISION WORKSTATION 530TM, available from Dell Corporation, Austin, Texas.
- Controller 55 can be locally located relative to the material processing system 1, or it can be remotely located relative to the material processing system 1.
- controller 55 can exchange data with material processing system 1 using at least one of a direct connection, an intranet, and the internet.
- Controller 55 can be coupled to an intranet at, for example, a customer site (i.e., a device maker, etc.), or it can be coupled to an intranet at, for example, a vendor site (i.e., an equipment manufacturer).
- controller 55 can be coupled to the internet.
- another computer i.e., controller, server, etc.
- material processing system 1 can include a magnetic field system 60.
- the magnetic field system 60 can include a stationary, or either a mechanically or electrically rotating DC magnetic field in order to potentially increase plasma density and/or improve material processing uniformity.
- controller 55 can be coupled to magnetic field system 60 in order to regulate the field strength or speed of rotation.
- the material processing system can include an upper electrode 70.
- RF power can be coupled from RF generator 72 through impedance match network 74 to upper electrode 70.
- a frequency for the application of RF power to the upper electrode preferably ranges from 10 MHz to 200 MHz and is preferably 60 MHz.
- a frequency for the application of power to the lower electrode can range from 0.1 MHz to 30 MHz and is preferably 2 MHz.
- controller 55 can be coupled to RF generator 72 and impedance match network 74 in order to control the application of RF power to upper electrode 70.
- the material processing system of FIG. 1 can include an inductive coil 80.
- RF power can be coupled from RF generator 82 through impedance match network 84 to inductive coil 80, and RF power can be inductively coupled from inductive coil 80 through dielectric window (not shown) to plasma processing region 45.
- a frequency for the application of RF power to the inductive coil 80 preferably ranges from 10 MHz to 100 MHz and is preferably 13.56 MHz.
- a frequency for the application of power to the chuck electrode preferably ranges from 0.1 MHz to 30 MHz and is preferably 13.56 MHz.
- a slotted Faraday shield (not shown) can be employed to reduce capacitive coupling between the inductive coil 80 and plasma.
- controller 55 can be coupled to RF generator 82 and impedance match network 84 in order to control the application of power to inductive coil 80.
- inductive coil 80 can be a "spiral" coil or "pancake” coil in communication with the plasma processing region 45 from above as in a transformer coupled plasma (TCP) reactor.
- TCP transformer coupled plasma
- the plasma can be formed using electron cyclotron resonance (ECR).
- ECR electron cyclotron resonance
- the plasma is formed from the launching of a Helicon wave.
- the plasma is formed from a propagating surface wave.
- the process performance monitoring system 100 includes plurality of sensors 50 and controller 55, where the sensors 50 are coupled to process tool 10 and the controller 55 is coupled to the sensors 50 to receive tool data.
- the controller 55 is further capable of executing at least one algorithm to optimize the tool data received from the sensors 50, determine a relationship (model) between the tool data, and use the relationship (model) for fault detection.
- MVA multivariate analysis
- one such MVA technique includes Principal Components Analysis (PCA).
- PCA Principal Components Analysis
- a model can be assembled to extract from a large set of data a signal exhibiting the greatest variance in the multi-dimensional parameter space.
- each set of data parameters for a given substrate run, or instant in time can be stored as a row in a matrix X and, hence, once the matrix X is assembled, each row represents a different substrate run, or instant in time (or observation), and each column represents a different data parameter (or data variable) corresponding to the plurality of sensors 50. Therefore, matrix X is a rectangular matrix of dimensions q by r, where q represents the row dimension and r represents the column dimension.
- the data is generally mean-centered and/or normalized. The process of mean-centering the data stored in a matrix column involves computing a mean value of the column elements and subtracting the mean value from each element.
- the data residing in a column of the matrix can be normalized by determining the standard deviation of the data in the column.
- a PCA model can be constructed in a manner similar to that described in United States Provisional Application Serial no. 60/470,901, entitled “A process system health index and method of using the same", filed on May 16, 2002. The entire content of this application is hereby incorporated herein by reference. [0055] Using the PCA technique, the correlation structure within matrix X is determined by approximating matrix X with a matrix product (TP T ) of lower dimensions plus an error matrix E , viz.
- the loadings matrix P can be shown to comprise the eigenvectors of the covariance matrix of X , where the covariance matrix S can be shown to be
- the covariance matrix S is a real, symmetric matrix; and, therefore, the covariance matrix can be described as
- T T T A . (5)
- each eigenvalue represents the variance of the data in the direction of the corresponding eigenvector within n- dimensional space.
- the largest eigenvalue corresponds to the greatest variance in the data within the multi-dimensional space whereas the smallest eigenvalue represents the smallest variance in the data.
- all eigenvectors are orthogonal, and therefore, the second largest eigenvalue corresponds to the second greatest variance in the data in the direction of the corresponding eigenvector, which is, of course, normal to the direction of the first eigenvector.
- the first several (three to four, or more) largest eigenvalues are chosen to approximate the data and, as a result of the approximation, an error E is introduced to the representation in equation (la).
- an error E is introduced to the representation in equation (la).
- a set of the largest eigenvalues can be chosen and the error matrix E of equation (la) can be determined.
- An example of commercially available software which supports PCA modeling is MATLABTM (commercially available from The Mathworks, Inc., Natick, MA), and PLS Toolbox (commercially available from Eigenvector Research, Inc., Manson, WA).
- loadings matrix can be constructed using a "training" set of data (i.e. assemble X for a number of observations and determine a PCA model using
- a PCA model loadings matrix P , etc.
- a "training" set of data i.e. assemble X for a number of observations and determine a PCA model using MATLABTM.
- a statistical quantity such as the Q-statistic, or the Hotelling T 2 , is monitored for a process, and, when this quantity exceeds a pre-determined control limit, a fault for the process is detected.
- FIG. 6A shows an example of conventional use of a PCA model to monitor the Q-statistic (Q-factor) of a process in order to determine faults in the process.
- the model is applied to process data acquired from Unity II DRM (Dipole Ring Magnet) CCP (Capacitively Coupled Plasma) processing systems (commercially available from Tokyo Electron Limited; see FIG. 3) that perform a patterned oxide etch with a C F 8 /CO/Ar + O based chemistry.
- This processing system operates in a batch mode with a fixed process recipe for each lot. Typically, a single recipe is utilized from lot to lot for a particular process step in the manufacture of a device.
- the same processing system is frequently utilized for many different device layers and steps, but for each process step, the recipe remains the same.
- the data parameters collected include the chamber pressure, applied power, various temperatures, and many other variables relating to the pressure, power, and temperature control as shown in Table 1.
- the process recipe used in this example has three main steps: a photoresist cleaning step, a main etch step, and a photoresist stripping step.
- the scope of this example applied to the main etch step but it is not limited to this particular step or any particular step and is, therefore, applicable to other steps as well.
- an observation mean and observation standard deviation of a time trace for each data parameter (or tool variable) was calculated from roughly 160 samples for each substrate. The beginning portion of the time trace for each data parameter, where the RF power increases, was trimmed in these statistical calculations in an attempt to remove the variation due to the power when it is turned on.
- a PCA model was performed for the first 500 substrates using the same recipe in a single processing system.
- the standard PCA methods implemented in MATLABTM were used, with mean centering and unit variance scaling.
- the standard Q residuals (SPE) and Q contributions were calculated using the Eigenvector Research PLS Toolbox offered by Eigenvector Research as an add-on to MATLABTM.
- the PCA model was constructed from the first 500 substrates in a first processing system and was applied to all 3200 substrates from this processing system.
- the resulting Q statistic exceeds the 95% confidence limit in the model within less than 250 substrates after the PCA model was built (i.e. by substrate number 750), and never returns to below that level.
- substrate number 750 substrate number 750
- distinct outliers and distinct step-like changes are apparent.
- FIG. 6A demonstrates that while a conventional PCA model constructed as described above can be used to monitor the Q-statistic, there exist periods of time where the statistical parameter deviates above the control limit never to return below.
- any of the above described statistics can be monitored using a given model for a specific process in a specific processing system, but will eventually deviate above the control limit never to return below. Thereafter, the model is no longer applicable to the given process and given processing system.
- the present inventors have recognized that these methods are not practical for commercial application to semiconductor manufacturing process control.
- the PCA model can be actually rebuilt with each process run in order to update the model on the fly during the process. While this adaptive modeling technique may generally stabilize the statistical monitoring within a given control limit, it requires computational resources not practical for commercial processes.
- control limit can be reset for each process run based on a predicted degradation of the PCA model. While this method will avoid the indication of an out-of-process condition due to degradation of the PCA model, changing the control limit with each process run requires a complex scheme that is also impractical for commercial processes.
- the present inventors have recognized that conventional methods for adapting a PCA model to enable statistical monitoring over long process runs is impractical for commercial processes. More specifically, the present inventors have discovered that the standard approach to centering and scaling the data in a PCA matrix has not enabled the development of a robust model capable of use for long periods of time (i.e., substantive number of substrate runs).
- an adaptive multivariate analysis is described for preparing a robust PCA model.
- the centering and scaling coefficients are updated using an adaptation scheme.
- the mean values (utilized for centering) for each summary statistic are updated from one observation to the next using a filter, such as an exponentially weighted moving average (EWMA) filter shown as follows:
- XM, J ,H represents the calculated model mean value ("M") of the j ⁇ data parameter at the current run (or observation "n")
- Xjj classroom represents the current value of the j* data parameter for the current run
- model standard deviations (utilized for scaling) for each summary statistic are updated using the following recursive standard deviation filter
- ⁇ x represents the calculated model standard deviation of the j data parameter for the current run (or observation "n")
- ⁇ J ⁇ W _ j represents the calculated model standard deviation of the j n data parameter for the previous run (or observation "n-1")
- n represents the run (or observation) number
- k represents a filter constant.
- the filter constant k can, for example, be selected as a constant less than or equal to N, where N represents the number of substrate runs, or observations, utilized to construct the PCA model.
- FIG. 6B shows the same example of using a PCA model to monitor the Q- statistic that was presented in FIG. 6A, except that the centering and scaling coefficients are updated using an adaptation scheme in accordance with the present invention.
- the Q-statistic chart is substantially more stable across all of the remaining substrates, and the data predominantly resides within the same limit.
- the inventive adaptation scheme provides similar improvement to other statistical monitoring schemes (e.g., the Hotelling T 2 parameter).
- adaptation of the PCA model in accordance with the present invention allows for a more robust PCA model that can be used for long process runs.
- the first excursion of substantive magnitude is the run with the largest Q value in the adaptive case, which occurs for substrate 1492.
- Cl-POSITION-LO mean, RF-VPP-LO mean, and ESC-CURRENT are the extreme values.
- the arbitrarily scaled summary statistics for the latter two data parameters are plotted in FIG. 8. These three data parameters account for the large spikes in the data at four points, which could indicate an issue with the impedance match network system. This type of outlier is clear in both Q charts, but only the adaptive case allows for a fixed limit (e.g., 95% confidence limit) for all time.
- the relative change in the centering and scaling coefficients can be calculated to alert the operator or engineer that step summary statistics have shifted between two runs, or observations. For each centering coefficient, this is done by subtracting the estimate at an initial run from the estimate at a final run, then scaling each difference by the standard deviation used for scaling that step statistic for the initial run, viz. -A M ,b ⁇ X Mj,a
- M- is the model mean movement metric
- XM JJ * represents the model mean value for the j th data parameter for the a th substrate
- XM, J J> represents the model mean value for the j* data parameter for the b th substrate
- ⁇ j a represents the model standard deviation for the j th data parameter for the a th substrate.
- the calculation is the difference in standard deviations scaled with the mean used for centering that step statistic, viz.
- ⁇ jJb represents the model standard deviation for the j th data parameter for the b th substrate. »
- FIG. 9A presents the model mean movement metric and the model standard deviation metric for all of the data parameters.
- the arbitrarily scaled summary data for the two data parameters is displayed in FIG. 9B.
- the two major changes in the Q statistic seem to be dominated by these two data parameters.
- the shift in these data parameters may have been caused by a tool cleaning, e.g., replacing key parts and changing the electrical or heat transfer characteristics of the processing system.
- the temperature is regulated in the processing system, this is done only at the upper electrode and walls.
- the lower temperature is not controlled and could be affected by different materials or part configurations in the processing system.
- the contribution plots for the static case and the adaptive case for substrate 1880 both are dominated by the Cl-POSITION-LO.
- FIGs. 10 and 11 illustrate a second example of the present invention wherein, after looking at the major changes over time for one processing system, the same model from the first 500 substrates was then applied to a set of 800 substrates from a second processing system. As seen in FIG. 10, the plot of the Q statistic for the static model is many orders of magnitude greater than the confidence limit for the model.
- FIG. 11 shows the same model with the adaptive centering and scaling coefficients of the present invention applied.
- the data returns below the confidence limit after only 25 substrates (the typical load for a single cassette).
- Increasing ⁇ may provide an even faster recovery, but may result in overshoot problems.
- the same gross outliers are still evident, but other variations such as the region between substrate 445 and 455 are highlighted as well.
- the metric points to the APC mean and the COOL-GAS-FLOW1 standard deviation.
- the substrate summary data for these variables exhibit a crisp jump at this time. Further analysis would be necessary to speculate on a type of problem that would be characterized by a shift in the throttle valve angle used to control pressure and the variability in the helium flow used to control temperature on the lower electrode.
- the present inventors have recognized that a static PCA model is inadequate for monitoring and detecting local faults on an industrial material processing system.
- the confidence limit on the model is quickly exceeded after the model is constructed; furthermore, the confidence limit is inappropriate when the model is applied to another processing system.
- the mean and standard deviation values, used for univariate scaling, can be slowly adapted with new data.
- the adaptive centering and scaling method is sufficient to keep the distance to the model in the residual space (Q) stable, and the original model confidence limit is appropriate for detecting excursions.
- the Q contributions calculated from the adaptive method help discriminate the root cause data parameters of the local deviation instead of being coupled to the contributions of those data parameters that have global changes. Supplemental to the contribution plot, the movement metric identified input data parameters that had sharp step changes during periods of consecutive confidence limit violations.
- FIG. 13 presents a flow chart describing a method of monitoring a processing system for processing a substrate during the course of semiconductor manufacturing.
- the method 500 begins at 510 with acquiring data from the processing system for a plurality of observations.
- the processing system can, for example, be an etch system, or it may be another processing system as described in FIG. 1.
- the data from the processing system can be acquired using a plurality of sensors coupled to the processing system and a controller.
- the data can, for example, comprise any measurable data parameter, and any statistic thereof (e.g., mean, standard deviation, skewness, kurtosis, etc.).
- Additional data can, for example, include optical emission spectra, RF harmonics of voltage and/or current measurements or radiated RF emission, etc.
- Each observation can pertain to a substrate run, instant in time, time average, etc.
- a PCA model is constructed from the acquired data parameters by determining one or more principal components to represent the data at 530 and applying static centering and scaling coefficients, as described above, to the data parameters of the acquired data at 540.
- a commercially available software such as MATLABTM and PLS Toolbox can be utilized to construct the PCA model.
- additional data is acquired from a processing system, and, at 555, adaptive centering and scaling coefficients are utilized when applying the PCA model to the acquired data parameters.
- at least one statistical quantity is determined from the additional data and the PCA model.
- the additional data can be forward projected onto the one or more principal components to determine a set of scores, and the set of scores can be backward projected onto the principal components to determine one or more residual errors.
- at least one statistical quantity can be determined, such as the Q-statistic, or the Hotelling T 2 parameter, for each additional observation.
- a control limit can be set, and, at 580, at least one statistical quantity can be compared with the control limit.
- the control limit can be set using either subjective methods or empirical methods. For example, when using the Q-statistic, the control limit can be set at the 95% confidence limit (see, for instance, FIGs. 6A, 6B, and 11). Additionally, for example, when using the Hotelling T 2 parameter, the control limit can be set at the 95% confidence limit. Alternatively, for example, the control limit can be established by assuming a theoretical distribution for the statistical quantity, such as a ⁇ 2 -distribution; however, the observed distribution should be verified with the theory. If the at least one statistical quantity exceeds the control limit, then a fault for the processing system is detected at 590, and an operator can be notified at 600.
- FIG. 12 illustrates a computer system 1201 for implementing various embodiments of the present invention.
- the computer system 1201 may be used as the controller 55 to perform any or all of the functions of the controller described above.
- the computer system 1201 includes a bus 1202 or other communication mechanism for communicating information, and a processor 1203 coupled with the bus 1202 for processing the information.
- the computer system 1201 also includes a main memory 1204, such as a random access memory (RAM) or other dynamic storage device (e.g., dynamic RAM (DRAM), static RAM (SRAM), and synchronous DRAM (SDRAM)), coupled to the bus 1202 for storing information and instructions to be executed by processor 1203.
- RAM random access memory
- DRAM dynamic RAM
- SRAM static RAM
- SDRAM synchronous DRAM
- the main memory 1204 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processor 1203.
- the computer system 1201 further includes a read only memory (ROM) 1205 or other static storage device (e.g., programmable ROM (PROM), erasable PROM (EPROM), and electrically erasable PROM (EEPROM)) coupled to the bus 1202 for storing static information and instructions for the processor 1203.
- ROM read only memory
- PROM programmable ROM
- EPROM erasable PROM
- EEPROM electrically erasable PROM
- the computer system 1201 also includes a disk controller 1206 coupled to the bus 1202 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 1207, and a removable media drive 1208 (e.g., floppy disk drive, read-only compact disc drive, read/write compact disc drive, compact disc jukebox, tape drive, and removable magneto-optical drive).
- the storage devices may be added to the computer system 1201 using an appropriate device interface (e.g., small computer system interface (SCSI), integrated device electronics (IDE), enhanced-IDE (E-IDE), direct memory access (DMA), or ultra-DMA).
- SCSI small computer system interface
- IDE integrated device electronics
- E-IDE enhanced-IDE
- DMA direct memory access
- ultra-DMA ultra-DMA
- the computer system 1201 may also include special purpose logic devices (e.g., application specific integrated circuits (ASICs)) or configurable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)).
- ASICs application specific integrated circuits
- SPLDs simple programmable logic devices
- CPLDs complex programmable logic devices
- FPGAs field programmable gate arrays
- the computer system 1201 may also include a display controller 1209 coupled to the bus 1202 to control a display 1210, such as a cathode ray tube (CRT), for displaying information to a computer user.
- the computer system includes input devices, such as a keyboard 1211 and a pointing device 1212, for interacting with a computer user and providing information to the processor 1203.
- the pointing device 1212 may be a mouse, a trackball, or a pointing stick for communicating direction information and command selections to the processor 1203 and for controlling cursor movement on the display 1210.
- a printer may provide printed listings of data stored and/or generated by the computer system 1201.
- the computer system 1201 performs a portion or all of the processing steps of the invention (such as for example those described in relation to Figure 13). in response to the processor 1203 executing one or more sequences of one or more instructions contained in a memory, such as the main memory 1204. Such instructions may be read into the main memory 1204 from another computer readable medium, such as a hard disk 1207 or a removable media drive 1208.
- processors in a multi-processing arrangement may also be employed to execute the sequences of instructions contained in main memory 1204.
- hard- wired circuitry may be used in place of or in combination with software instructions.
- embodiments are not limited to any specific combination of hardware circuitry and software.
- the computer system 1201 includes at least one computer readable medium or memory for holding instructions programmed according to the teachings of the invention and for containing data structures, tables, records, or other data described herein.
- Examples of computer readable media are compact discs, hard disks, floppy disks, tape, magneto-optical disks, PROMs (EPROM, EEPROM, flash EPROM), DRAM, SRAM, SDRAM, or any other magnetic medium, compact discs (e.g., CD-ROM), or any other optical medium, punch cards, paper tape, or other physical medium with patterns of holes, a carrier wave (described below), or any other medium from which a computer can read.
- the present invention includes software for controlling the computer system 1201, for driving a device or devices for implementing the invention, and for enabling the computer system 1201 to interact with a human user (e.g., print production personnel).
- software may include, but is not limited to, device drivers, operating systems, development tools, and applications software.
- Such computer readable media further includes the computer program product of the present invention for performing all or a portion (if processing is distributed) of the processing performed in implementing the invention.
- the computer code devices of the present invention may be any interpretable or executable code mechanism, including but not limited to scripts, interpretable programs, dynamic link libraries (DLLs), Java classes, and complete executable programs. Moreover, parts of the processing of the present invention may be distributed for better performance, reliability, and/or cost.
- Non- volatile media includes, for example, optical, magnetic disks, and magneto-optical disks, such as the hard disk 1207 or the removable media drive 1208.
- Volatile media includes dynamic memory, such as the main memory 1204.
- Transmission media includes coaxial cables, copper wire and fiber optics, including the wires that make up the bus 1202. Transmission media also may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.
- Various forms of computer readable media may be involved in carrying out one or more sequences of one or more instructions to processor 1203 for execution.
- the instructions may initially be carried on a magnetic disk of a remote computer.
- the remote computer can load the instructions for implementing all or a portion of the present invention remotely into a dynamic memory and send the instructions over a telephone line using a modem.
- a modem local to the computer system 1201 may receive the data on the telephone line and use an infrared transmitter to convert the data to an infrared signal.
- An infrared detector coupled to the bus 1202 can receive the data carried in the infrared signal and place the data on the bus 1202.
- the bus 1202 carries the data to the main memory 1204, from which the processor 1203 retrieves and executes the instructions.
- the instructions received by the main memory 1204 may optionally be stored on storage device 1207 or 1208 either before or after execution by processor 1203.
- the computer system 1201 also includes a communication interface 1213 coupled to the bus 1202.
- the communication interface 1213 provides a two-way data communication coupling to a network link 1214 that is connected to, for example, a local area network (LAN) 1215, or to another communications network 1216 such as the Internet.
- the communication interface 1213 may be a network interface card to attach to any packet switched LAN.
- the communication interface 1213 may be an asymmetrical digital subscriber line (ADSL) card, an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of communications line.
- Wireless links may also be implemented.
- the communication interface 1213 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
- the network link 1214 typically provides data communication through one or more networks to other data devices.
- the network link 1214 may provide a connection to another computer through a local network 1215 (e.g., a LAN) or through equipment operated by a service provider, which provides communication services through a communications network 1216.
- the local network 1214 and the communications network 1216 use, for example, electrical, electromagnetic, or optical signals that carry digital data streams, and the associated physical layer (e.g., CAT 5 cable, coaxial cable, optical fiber, etc).
- the signals through the various networks and the signals on the network link 1214 and through the communication interface 1213, which carry the digital data to and from the computer system 1201 maybe implemented in baseband signals, or carrier wave based signals.
- the baseband signals convey the digital data as unmodulated electrical pulses that are descriptive of a stream of digital data bits, where the term "bits" is to be construed broadly to mean symbol, where each symbol conveys at least one or more information bits.
- the digital data may also be used to modulate a carrier wave, such as with amplitude, phase and/or frequency shift keyed signals that are propagated over a conductive media, or transmitted as electromagnetic waves through a propagation medium.
- the digital data may be sent as unmodulated baseband data through a "wired" communication channel and/or sent within a predetermined frequency band, different than baseband, by modulating a carrier wave.
- the computer system 1201 can transmit and receive data, including program code, through the network(s) 1215 and 1216, the network link 1214, and the communication interface 1213.
- the network link 1214 may provide a connection through a LAN 1215 to a mobile device 1217 such as a personal digital assistant (PDA) laptop computer, or cellular telephone.
- PDA personal digital assistant
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP04809545A EP1665076A4 (en) | 2003-09-12 | 2004-08-27 | Method and system of diagnosing a processing system using adaptive multivariate analysis |
KR1020067005122A KR101047971B1 (en) | 2003-09-12 | 2004-08-27 | Diagnostic Method and Apparatus for Processing Systems Using Adaptive Multivariate Analysis |
JP2006526083A JP4699367B2 (en) | 2003-09-12 | 2004-08-27 | Method and apparatus for diagnosing processing equipment using adaptive multivariable analysis |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/660,697 | 2003-09-12 | ||
US10/660,697 US7328126B2 (en) | 2003-09-12 | 2003-09-12 | Method and system of diagnosing a processing system using adaptive multivariate analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2005036314A2 true WO2005036314A2 (en) | 2005-04-21 |
WO2005036314A3 WO2005036314A3 (en) | 2005-11-10 |
Family
ID=34273706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2004/025599 WO2005036314A2 (en) | 2003-09-12 | 2004-08-27 | Method and system of diagnosing a processing system using adaptive multivariate analysis |
Country Status (7)
Country | Link |
---|---|
US (1) | US7328126B2 (en) |
EP (1) | EP1665076A4 (en) |
JP (1) | JP4699367B2 (en) |
KR (1) | KR101047971B1 (en) |
CN (1) | CN100476798C (en) |
TW (1) | TWI261738B (en) |
WO (1) | WO2005036314A2 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007019431A (en) * | 2005-07-11 | 2007-01-25 | Tokyo Electron Ltd | Apparatus, system, and program for substrate treatment monitor and recording medium |
JP2009528674A (en) * | 2006-02-07 | 2009-08-06 | 東京エレクトロン株式会社 | Method for converting measurement data from semiconductor processing systems using multivariate analysis |
Families Citing this family (99)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020191102A1 (en) * | 2001-05-31 | 2002-12-19 | Casio Computer Co., Ltd. | Light emitting device, camera with light emitting device, and image pickup method |
JP2004240628A (en) * | 2003-02-05 | 2004-08-26 | Yokogawa Electric Corp | Estimation method and estimation device for production process |
US8676538B2 (en) * | 2004-11-02 | 2014-03-18 | Advanced Micro Devices, Inc. | Adjusting weighting of a parameter relating to fault detection based on a detected fault |
US7404123B1 (en) * | 2005-03-28 | 2008-07-22 | Lam Research Corporation | Automated test and characterization data analysis methods and arrangement |
WO2007008538A2 (en) * | 2005-07-07 | 2007-01-18 | Mks Instruments, Inc. | Self-correcting multivariate analysis for use in monitoring dynamic parameters in process environments |
US7523021B2 (en) * | 2006-03-08 | 2009-04-21 | Tokyo Electron Limited | Weighting function to enhance measured diffraction signals in optical metrology |
US9158941B2 (en) * | 2006-03-16 | 2015-10-13 | Arm Limited | Managing access to content in a data processing apparatus |
US7587296B2 (en) * | 2006-05-07 | 2009-09-08 | Applied Materials, Inc. | Adaptive multivariate fault detection |
US7596718B2 (en) * | 2006-05-07 | 2009-09-29 | Applied Materials, Inc. | Ranged fault signatures for fault diagnosis |
US8145358B2 (en) | 2006-07-25 | 2012-03-27 | Fisher-Rosemount Systems, Inc. | Method and system for detecting abnormal operation of a level regulatory control loop |
US7912676B2 (en) * | 2006-07-25 | 2011-03-22 | Fisher-Rosemount Systems, Inc. | Method and system for detecting abnormal operation in a process plant |
US8606544B2 (en) * | 2006-07-25 | 2013-12-10 | Fisher-Rosemount Systems, Inc. | Methods and systems for detecting deviation of a process variable from expected values |
US7657399B2 (en) * | 2006-07-25 | 2010-02-02 | Fisher-Rosemount Systems, Inc. | Methods and systems for detecting deviation of a process variable from expected values |
EP2057517B1 (en) * | 2006-09-28 | 2013-06-12 | Fisher-Rosemount Systems, Inc. | Abnormal situation prevention in a heat exchanger |
US20080120060A1 (en) * | 2006-09-29 | 2008-05-22 | Fisher-Rosemount Systems, Inc. | Detection of catalyst losses in a fluid catalytic cracker for use in abnormal situation prevention |
US7917240B2 (en) * | 2006-09-29 | 2011-03-29 | Fisher-Rosemount Systems, Inc. | Univariate method for monitoring and analysis of multivariate data |
WO2008042757A2 (en) * | 2006-09-29 | 2008-04-10 | Fisher-Rosemount Systems, Inc. | Univariate method for monitoring and analysis of multivariate data |
PL2097794T5 (en) * | 2006-11-03 | 2018-01-31 | Air Prod & Chem | System and method for process monitoring |
US20080140345A1 (en) * | 2006-12-07 | 2008-06-12 | International Business Machines Corporation | Statistical summarization of event data |
US8103481B2 (en) * | 2006-12-12 | 2012-01-24 | International Business Machines Corporation | Processing irregularly occuring data events in real time |
US20080167842A1 (en) * | 2007-01-04 | 2008-07-10 | Honeywell International Inc. | Method and system for detecting, analyzing and subsequently recognizing abnormal events |
US8032340B2 (en) * | 2007-01-04 | 2011-10-04 | Fisher-Rosemount Systems, Inc. | Method and system for modeling a process variable in a process plant |
US8032341B2 (en) | 2007-01-04 | 2011-10-04 | Fisher-Rosemount Systems, Inc. | Modeling a process using a composite model comprising a plurality of regression models |
US7827006B2 (en) * | 2007-01-31 | 2010-11-02 | Fisher-Rosemount Systems, Inc. | Heat exchanger fouling detection |
US7630859B2 (en) * | 2007-05-01 | 2009-12-08 | Verity Instruments, Inc. | Method and apparatus for reducing the effects of window clouding on a viewport window in a reactive environment |
US8271103B2 (en) * | 2007-05-02 | 2012-09-18 | Mks Instruments, Inc. | Automated model building and model updating |
US8010321B2 (en) * | 2007-05-04 | 2011-08-30 | Applied Materials, Inc. | Metrics independent and recipe independent fault classes |
US7765020B2 (en) * | 2007-05-04 | 2010-07-27 | Applied Materials, Inc. | Graphical user interface for presenting multivariate fault contributions |
KR100885187B1 (en) * | 2007-05-10 | 2009-02-23 | 삼성전자주식회사 | Method And System For Monitoring State Of Plasma Chamber |
KR100928205B1 (en) * | 2007-06-05 | 2009-11-25 | 삼성전자주식회사 | Semiconductor manufacturing facility management system and its statistical process control method |
US8301676B2 (en) * | 2007-08-23 | 2012-10-30 | Fisher-Rosemount Systems, Inc. | Field device with capability of calculating digital filter coefficients |
US7702401B2 (en) | 2007-09-05 | 2010-04-20 | Fisher-Rosemount Systems, Inc. | System for preserving and displaying process control data associated with an abnormal situation |
US8055479B2 (en) | 2007-10-10 | 2011-11-08 | Fisher-Rosemount Systems, Inc. | Simplified algorithm for abnormal situation prevention in load following applications including plugged line diagnostics in a dynamic process |
US8271122B2 (en) | 2008-03-07 | 2012-09-18 | Mks Instruments, Inc. | Process control using process data and yield data |
US7622308B2 (en) * | 2008-03-07 | 2009-11-24 | Mks Instruments, Inc. | Process control using process data and yield data |
DE102008021558A1 (en) * | 2008-04-30 | 2009-11-12 | Advanced Micro Devices, Inc., Sunnyvale | Process and system for semiconductor process control and monitoring using PCA models of reduced size |
US20090282296A1 (en) * | 2008-05-08 | 2009-11-12 | Applied Materials, Inc. | Multivariate fault detection improvement for electronic device manufacturing |
US8335582B2 (en) * | 2008-05-19 | 2012-12-18 | Applied Materials, Inc. | Software application to analyze event log and chart tool fail rate as function of chamber and recipe |
KR101504594B1 (en) * | 2008-08-28 | 2015-03-23 | 삼성전자주식회사 | Method of simulating a leakage current in a semiconductor device |
US8494798B2 (en) * | 2008-09-02 | 2013-07-23 | Mks Instruments, Inc. | Automated model building and batch model building for a manufacturing process, process monitoring, and fault detection |
US8527080B2 (en) * | 2008-10-02 | 2013-09-03 | Applied Materials, Inc. | Method and system for managing process jobs in a semiconductor fabrication facility |
US8643539B2 (en) * | 2008-11-19 | 2014-02-04 | Nokomis, Inc. | Advance manufacturing monitoring and diagnostic tool |
US9069345B2 (en) * | 2009-01-23 | 2015-06-30 | Mks Instruments, Inc. | Controlling a manufacturing process with a multivariate model |
DE102009006887B3 (en) * | 2009-01-30 | 2010-07-15 | Advanced Micro Devices, Inc., Sunnyvale | Method and system for semiconductor process control and monitoring using a data quality measure |
US8989887B2 (en) | 2009-02-11 | 2015-03-24 | Applied Materials, Inc. | Use of prediction data in monitoring actual production targets |
US8983631B2 (en) * | 2009-06-30 | 2015-03-17 | Lam Research Corporation | Arrangement for identifying uncontrolled events at the process module level and methods thereof |
US8855804B2 (en) | 2010-11-16 | 2014-10-07 | Mks Instruments, Inc. | Controlling a discrete-type manufacturing process with a multivariate model |
SG190883A1 (en) * | 2010-11-26 | 2013-07-31 | Heung Seob Koo | Representative-value calculating device and method |
US9295148B2 (en) * | 2012-12-14 | 2016-03-22 | Lam Research Corporation | Computation of statistics for statistical data decimation |
US9541471B2 (en) | 2012-04-06 | 2017-01-10 | Mks Instruments, Inc. | Multivariate prediction of a batch manufacturing process |
US9429939B2 (en) | 2012-04-06 | 2016-08-30 | Mks Instruments, Inc. | Multivariate monitoring of a batch manufacturing process |
JP5739841B2 (en) * | 2012-06-13 | 2015-06-24 | 株式会社東芝 | Electronic device production management apparatus, production management system, and production management program |
US8917261B2 (en) * | 2012-06-26 | 2014-12-23 | Atmel Corporation | Pixel occlusion mitigation |
TWI463426B (en) * | 2012-09-25 | 2014-12-01 | China Steel Corp | Integrated Process Monitoring Method and Its System |
CN104736744B (en) | 2012-10-17 | 2017-06-06 | 东京毅力科创株式会社 | Use the plasma etching end point determination of multi-variables analysis |
FR3003034B1 (en) | 2013-03-05 | 2017-09-08 | Polyor Sarl | PROTOCOL FOR THE PRECONIZATION AND DETERMINATION OF PHOSPHO-POTASSIUM AND MAGNESIC FERTILIZATION (PKMG) OF AGRONOMIC CULTURES |
US9400944B2 (en) * | 2013-03-11 | 2016-07-26 | Sas Institute Inc. | Space dilating two-way variable selection |
JP6173851B2 (en) * | 2013-09-20 | 2017-08-02 | 株式会社日立ハイテクノロジーズ | Analysis method and plasma etching apparatus |
CN103472732A (en) * | 2013-09-27 | 2013-12-25 | 上海交通大学 | Improved multivariate controller performance monitoring method based on Mahalanobis distance |
US10431428B2 (en) | 2014-01-10 | 2019-10-01 | Reno Technologies, Inc. | System for providing variable capacitance |
KR101522385B1 (en) * | 2014-05-02 | 2015-05-26 | 연세대학교 산학협력단 | Method and apparatus for detecting fault in the semiconductor menufacturing process and recording medium thereof |
FR3029622B1 (en) * | 2014-12-05 | 2019-06-14 | Safran Aircraft Engines | PROCESS FOR FOLLOWING THE MANUFACTURE OF PARTS BASED ON THE ANALYSIS OF CENTERING COEFFICIENTS |
FR3029620B1 (en) * | 2014-12-05 | 2019-06-14 | Safran Aircraft Engines | PROCESS FOR MONITORING THE PRODUCTION OF PARTS BASED ON THE SIMULTANEOUS ANALYSIS OF STATISTICAL INDICATORS |
CN104714537B (en) * | 2015-01-10 | 2017-08-04 | 浙江大学 | A kind of failure prediction method based on the relative mutation analysis of joint and autoregression model |
CN104777831B (en) * | 2015-04-09 | 2017-11-17 | 武汉船用机械有限责任公司 | A kind of method for diagnosing faults of fluid pressure type immersed pump system |
US10622197B2 (en) * | 2015-07-21 | 2020-04-14 | Tokyo Electron Limited | Plasma processing apparatus and plasma processing method |
US10395895B2 (en) * | 2015-08-27 | 2019-08-27 | Mks Instruments, Inc. | Feedback control by RF waveform tailoring for ion energy distribution |
US10656102B2 (en) | 2015-10-22 | 2020-05-19 | Battelle Memorial Institute | Evaluating system performance with sparse principal component analysis and a test statistic |
US10692705B2 (en) | 2015-11-16 | 2020-06-23 | Tokyo Electron Limited | Advanced optical sensor and method for detecting an optical event in a light emission signal in a plasma chamber |
TWI690009B (en) * | 2015-11-20 | 2020-04-01 | 財團法人工業技術研究院 | Breakdown measuring method and breakdown measuring device of equipment |
US20170245361A1 (en) * | 2016-01-06 | 2017-08-24 | Nokomis, Inc. | Electronic device and methods to customize electronic device electromagnetic emissions |
US10521774B2 (en) * | 2016-03-22 | 2019-12-31 | Asm Ip Holding B.V. | Preventive maintenance system and preventive maintenance method |
KR102304823B1 (en) | 2016-03-31 | 2021-09-23 | 도쿄엘렉트론가부시키가이샤 | Controlling Dry Etching Process Characteristics Using Waferless Dry Cleaning Light Emission Spectroscopy |
US10453653B2 (en) | 2016-09-02 | 2019-10-22 | Tokyo Electron Limited | Endpoint detection algorithm for atomic layer etching (ALE) |
US10804821B2 (en) * | 2016-11-04 | 2020-10-13 | Advanced Ion Beam Technology, Inc. | Apparatus and method for monitoring the relative relationship between the wafer and the chuck |
KR102520779B1 (en) | 2016-11-18 | 2023-04-11 | 도쿄엘렉트론가부시키가이샤 | Compositional Emission Spectroscopy for Particle-Induced Arc Detection in Manufacturing Processes |
CN106647274B (en) * | 2016-12-28 | 2018-05-18 | 中南大学 | Operating condition stable state method of discrimination in a kind of continuous flow procedure |
US10606253B2 (en) * | 2017-02-08 | 2020-03-31 | United Microelectronics Corp. | Method of monitoring processing system for processing substrate |
US10448864B1 (en) | 2017-02-24 | 2019-10-22 | Nokomis, Inc. | Apparatus and method to identify and measure gas concentrations |
CN110431655A (en) | 2017-03-17 | 2019-11-08 | 东京毅力科创株式会社 | The modified control in improved surface is measured for etching |
FR3066289B1 (en) * | 2017-05-09 | 2021-03-19 | Quantics Tech | PROCESS, IMPLEMENTATION BY COMPUTER, OF SEARCHING FOR ASSOCIATION RULES IN A DATABASE |
JP6524274B2 (en) * | 2017-05-26 | 2019-06-05 | ローム株式会社 | Traffic light monitor |
US11521833B2 (en) | 2017-07-10 | 2022-12-06 | Reno Technologies, Inc. | Combined RF generator and RF solid-state matching network |
US11476091B2 (en) | 2017-07-10 | 2022-10-18 | Reno Technologies, Inc. | Impedance matching network for diagnosing plasma chamber |
US11489847B1 (en) | 2018-02-14 | 2022-11-01 | Nokomis, Inc. | System and method for physically detecting, identifying, and diagnosing medical electronic devices connectable to a network |
JP7139734B2 (en) * | 2018-07-09 | 2022-09-21 | 日新電機株式会社 | Anomaly detection method and anomaly detection system |
JP6990634B2 (en) * | 2018-08-21 | 2022-02-03 | 株式会社日立ハイテク | State prediction device and semiconductor manufacturing device |
JP7068583B2 (en) * | 2018-09-20 | 2022-05-17 | 日本電信電話株式会社 | Learning device, estimation device, learning method, estimation method and program |
US10976718B2 (en) * | 2019-03-06 | 2021-04-13 | Honeywell Limited | System and method for monitoring changes in process dynamic behavior by mapping parameters to a lower dimensional space |
CN109933049B (en) * | 2019-03-29 | 2020-10-13 | 国网山东省电力公司费县供电公司 | Power dispatching log fault classification method and system |
CN110109435B (en) * | 2019-05-22 | 2020-07-24 | 杭州电子科技大学 | Online monitoring method for improving two-step subspace division |
JP2022533246A (en) | 2019-05-23 | 2022-07-21 | 東京エレクトロン株式会社 | Optical diagnosis of semiconductor processes using hyperspectral imaging |
US10910201B1 (en) | 2019-08-22 | 2021-02-02 | Tokyo Electron Limited | Synthetic wavelengths for endpoint detection in plasma etching |
JP2021052093A (en) * | 2019-09-25 | 2021-04-01 | 東京エレクトロン株式会社 | Board processing control method, board processing device, and storage medium |
US11293981B2 (en) | 2020-01-15 | 2022-04-05 | Toyota Motor Engineering & Manufacturing North America, Inc. | Systems and methods for false-positive reduction in power electronic device evaluation |
CN110987436B (en) * | 2020-03-05 | 2020-06-09 | 天津开发区精诺瀚海数据科技有限公司 | Bearing fault diagnosis method based on excitation mechanism |
TWI742693B (en) * | 2020-05-26 | 2021-10-11 | 國立中正大學 | Sensor placement optimization device and method thereof |
US11893004B2 (en) | 2020-08-26 | 2024-02-06 | Ford Global Technologies, Llc | Anomaly detection in multidimensional sensor data |
CN112463264B (en) * | 2020-12-11 | 2022-12-09 | 西安交通大学 | Interactive function implementation method for reactor breach accident analysis program |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5442562A (en) | 1993-12-10 | 1995-08-15 | Eastman Kodak Company | Method of controlling a manufacturing process using multivariate analysis |
SE9304246L (en) * | 1993-12-22 | 1995-06-23 | Asea Brown Boveri | Procedure for monitoring multivariate processes |
US5796606A (en) * | 1996-02-07 | 1998-08-18 | Noranda Inc. | Process information and maintenance system for distributed control systems |
US6153115A (en) * | 1997-10-23 | 2000-11-28 | Massachusetts Institute Of Technology | Monitor of plasma processes with multivariate statistical analysis of plasma emission spectra |
JP2000114338A (en) * | 1998-09-30 | 2000-04-21 | Mitsubishi Electric Corp | Method and device for evaluating characteristics fluctuation of semiconductor device, and recording medium where characteristics fluctuation evaluating program is stored |
JP2000252179A (en) * | 1999-03-04 | 2000-09-14 | Hitachi Ltd | Semiconductor manufacturing process stabilization support system |
US6442445B1 (en) * | 1999-03-19 | 2002-08-27 | International Business Machines Corporation, | User configurable multivariate time series reduction tool control method |
US6368975B1 (en) * | 1999-07-07 | 2002-04-09 | Applied Materials, Inc. | Method and apparatus for monitoring a process by employing principal component analysis |
US6564114B1 (en) * | 1999-09-08 | 2003-05-13 | Advanced Micro Devices, Inc. | Determining endpoint in etching processes using real-time principal components analysis of optical emission spectra |
US6470230B1 (en) * | 2000-01-04 | 2002-10-22 | Advanced Micro Devices, Inc. | Supervisory method for determining optimal process targets based on product performance in microelectronic fabrication |
WO2001069329A2 (en) * | 2000-03-10 | 2001-09-20 | Cyrano Sciences, Inc. | Control for an industrial process using one or more multidimensional variables |
GB0007063D0 (en) * | 2000-03-23 | 2000-05-10 | Simsci Limited | Mulitvariate statistical process monitors |
US6622059B1 (en) * | 2000-04-13 | 2003-09-16 | Advanced Micro Devices, Inc. | Automated process monitoring and analysis system for semiconductor processing |
WO2002003256A1 (en) * | 2000-07-05 | 2002-01-10 | Camo, Inc. | Method and system for the dynamic analysis of data |
CN1186700C (en) | 2000-09-15 | 2005-01-26 | 先进微装置公司 | Adaptive sampling method for improved control in semiconductor manufacturing |
US6549864B1 (en) | 2001-08-13 | 2003-04-15 | General Electric Company | Multivariate statistical process analysis systems and methods for the production of melt polycarbonate |
CN100419983C (en) * | 2003-05-16 | 2008-09-17 | 东京毅力科创株式会社 | Process system health index and method of using the same |
US6952657B2 (en) * | 2003-09-10 | 2005-10-04 | Peak Sensor Systems Llc | Industrial process fault detection using principal component analysis |
-
2003
- 2003-09-12 US US10/660,697 patent/US7328126B2/en not_active Expired - Lifetime
-
2004
- 2004-08-27 KR KR1020067005122A patent/KR101047971B1/en active IP Right Grant
- 2004-08-27 JP JP2006526083A patent/JP4699367B2/en not_active Expired - Fee Related
- 2004-08-27 EP EP04809545A patent/EP1665076A4/en not_active Withdrawn
- 2004-08-27 WO PCT/US2004/025599 patent/WO2005036314A2/en active Application Filing
- 2004-08-27 CN CNB2004800264199A patent/CN100476798C/en active Active
- 2004-09-09 TW TW093127260A patent/TWI261738B/en active
Non-Patent Citations (1)
Title |
---|
None |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007019431A (en) * | 2005-07-11 | 2007-01-25 | Tokyo Electron Ltd | Apparatus, system, and program for substrate treatment monitor and recording medium |
JP2009528674A (en) * | 2006-02-07 | 2009-08-06 | 東京エレクトロン株式会社 | Method for converting measurement data from semiconductor processing systems using multivariate analysis |
US8346506B2 (en) | 2006-02-07 | 2013-01-01 | Tokyo Electron Limited | Transforming metrology data from a semiconductor treatment system using multivariate analysis |
KR101304835B1 (en) * | 2006-02-07 | 2013-09-05 | 도쿄엘렉트론가부시키가이샤 | Transforming metrology data from a semiconductor treatment system using multivariate analysis |
Also Published As
Publication number | Publication date |
---|---|
EP1665076A2 (en) | 2006-06-07 |
EP1665076A4 (en) | 2007-06-20 |
US7328126B2 (en) | 2008-02-05 |
WO2005036314A3 (en) | 2005-11-10 |
CN1849599A (en) | 2006-10-18 |
KR101047971B1 (en) | 2011-07-13 |
TW200515112A (en) | 2005-05-01 |
CN100476798C (en) | 2009-04-08 |
JP2007505494A (en) | 2007-03-08 |
JP4699367B2 (en) | 2011-06-08 |
KR20060123098A (en) | 2006-12-01 |
US20050060103A1 (en) | 2005-03-17 |
TWI261738B (en) | 2006-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7328126B2 (en) | Method and system of diagnosing a processing system using adaptive multivariate analysis | |
US7713760B2 (en) | Process system health index and method of using the same | |
US7127358B2 (en) | Method and system for run-to-run control | |
US7167766B2 (en) | Controlling a material processing tool and performance data | |
US7844559B2 (en) | Method and system for predicting process performance using material processing tool and sensor data | |
JP4659359B2 (en) | Material processing method and system for material processing | |
CN104040679A (en) | Adaptive recipe selector | |
US6825920B2 (en) | Method and system of determining chamber seasoning condition by optical emission | |
JP4660091B2 (en) | Material processing system and method for characterizing material processing system | |
US10910201B1 (en) | Synthetic wavelengths for endpoint detection in plasma etching |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200480026419.9 Country of ref document: CN |
|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2004809545 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2006526083 Country of ref document: JP Ref document number: 1020067005122 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 2004809545 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 1020067005122 Country of ref document: KR |