WO2015047121A1 - Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery - Google Patents

Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery Download PDF

Info

Publication number
WO2015047121A1
WO2015047121A1 PCT/RU2013/000834 RU2013000834W WO2015047121A1 WO 2015047121 A1 WO2015047121 A1 WO 2015047121A1 RU 2013000834 W RU2013000834 W RU 2013000834W WO 2015047121 A1 WO2015047121 A1 WO 2015047121A1
Authority
WO
WIPO (PCT)
Prior art keywords
drive
motor current
motor
mcsa
predicting
Prior art date
Application number
PCT/RU2013/000834
Other languages
French (fr)
Inventor
Alexey Sergeyevich MININ
Ilya Igorevich MOKHOV
Alexey Petrovich KOZIONOV
Original Assignee
Siemens Aktiengesellschaft
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Priority to PCT/RU2013/000834 priority Critical patent/WO2015047121A1/en
Publication of WO2015047121A1 publication Critical patent/WO2015047121A1/en

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34—Testing dynamo-electric machines
    • G01R31/343—Testing dynamo-electric machines in operation

Definitions

  • the invention relates to operation monitoring and failure predicting in systems including a drive-operated motor, based on Motor Current Signature Analysis (MCSA) performed on a drive level.
  • MCSA Motor Current Signature Analysis
  • Induction motor drives are the most widely used electrical drive systems and typically consume 40 to 50 percent of an. industrialized nation's total generating capacity. To ensure safe and efficient operation and maintain operational readiness in emergency situations, these motor drives must be maintained so that they operate properly under all anticipated conditions.
  • MCSA is a condition monitoring technique that is now widely used to diagnose different motor related faults. It is necessary to detect a number of failures of the motor connected to particular drive and, potentially, to get more information about state of the motor and motor operated load (e.g. pump) on a drive level.
  • MSCA Machine Learning
  • the complete MCSA strategy can be represented by Fig. 3.
  • ammeter chart Properly monitored, the ammeter chart can provide valuable information for the detection and correction of minor operational problems before they become costly major problems. When the ammeter is properly utilized and understood, it can be very valuable in showing when a change in the equipment operation or well characteristics occur. An expert performs an analysis of ammeter charts.
  • HW Human Machine Interface
  • US 4965513 discloses a motor current noise signature analysis method and apparatus for remotely monitoring the operating characteristics of an electric motor- operated device such as a motor-operated valve.
  • Frequency domain signal analysis techniques are applied to a conditioned motor current signal to distinctly identify various operating parameters of the motor driven device from the motor current signature.
  • the signature may be recorded and compared with subsequent signatures to detect operating abnormalities and degradation of the device.
  • Thresholds are applied for measured signals directly or for extracted features: frequency, time-frequency or others, but such methods do not utilize dependencies between measured parameters.
  • an object of the present invention is to provide a method and system for operation monitoring and failure predicting, capable to get more information about state of a motor and motor operated load and to increase accuracy of operation monitoring and failure predicting of a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level.
  • MCSA Motor Current Signature Analysis
  • This object is achieved in a method for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, the method comprising:
  • the collected motor current data being obtained from a motor current signal being available through an HM- interface supported by a particular drive
  • processing comprises simulating the system by a complex valued recurrent neural network.
  • a system for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, the system configured to perform said method.
  • MCSA Motor Current Signature Analysis
  • Fig. 1 represents most typical motor related faults.
  • Fig. 2 represents types of faults of motors and their occurrences.
  • Fig. 3 represents a complete MCSA strategy.
  • Fig. 4 represents a current spectrum analysis, wherein sidebands relate to the Main Component of the spectrum.
  • Fig. 5 shows levels of integration from state of the art system with additional HW to fully integrated solution according to one embodiment of the invention.
  • Fig. 6 is a model-based approach for fault detection according to one embodiment of the invention.
  • Fig. 7 shows results of the transformer modeling for the subset of data containing leaps, according to one embodiment of the invention.
  • Fig. 8 shows results of the transformer modeling for the subset of data containing leaps (absolute values for voltage and current), according to another embodiment of the invention.
  • Fig. 9 shows results of the transformer modeling for the subset of data containing leaps (real and imaginary values for voltage and current), according to another embodiment of the invention.
  • Main idea of the invention is to claim the MCSA integrated on the drive level.
  • the data which is usually collected by state-of-the-art MCSA devices is already available at the drive level.
  • Levels of integration are shown on Fig. 5 from state of the art system with additional HW to fully integrated solution where all the analysis of the motor current signal is performed on drive firmware level.
  • Results of the MCSA can be accessed through a drive HM-interface or/and digital communication interfaces supported by a particular drive (for example, Profibus).
  • An algorithm of the method for operation monitoring and failure predicting in system including drive-operated motor, based on Motor Current Signature Analysis (MCSA) performed on a drive level can be described in the following way.
  • MCSA Motor Current Signature Analysis
  • Each block of motor can be presented as a dynamic system.
  • a model of a dynamic system simulates dependence between input of the system and output.
  • a model output is compared with a real output by calculation of difference (model error). Then this difference is classified by a machine learning classifier (see Fig. 6).
  • Fig. 7 shows results of the transformer modeling for the subset of data containing leaps.
  • the image is zoomed, since otherwise one can not see the short circuit moment.
  • Fig. 8 shows results of the transformer modeling for the subset of data containing leaps.
  • the region is zoomed in order to see the short circuit moment better. Absolute values for voltage and current are shown.
  • Fig. 9 shows results of the transformer modeling for the subset of data containing leaps. One can see the real part of the network outputs and the actual values of , U2 on the Validation set. The region is zoomed in order to see the short circuit moment better. Real and Imaginary values for voltage and current are shown.
  • the claimed invention provides unique algorithmic base for MCSA developed for embedded applications, possibility to put the suggested methods into the control system of a motor, possibility to implement remote condition monitoring based on standard motor functionality, implementation of the additional feature of the drive using the MCSA approach.

Abstract

The present invention relates to operation monitoring and failure predicting in motor-operated systems. Provided is a method for operation monitoring and failure predicting in a system including a drive-operated motor, based on Motor Current Signature Analysis (MCSA) performed on a drive level, comprising: collecting motor current data by a condition monitor, the collected motor current data being obtained from a motor current signal being available through an HM-interface supported by a particular drive, processing the collected data by the MCSA on a drive firmware level, making a decision regarding the operation condition and predicting a failure based on results of the processing. The processing comprises simulating the system by a complex valued recurrent neural network.

Description

METHOD AND APPARATUS FOR EMBEDDED CURRENT SIGNATURE ANALYSIS AND REMOTE CONDITION MONITORING FOR
INDUSTRIAL MACHINERY
FIELD OF THE INVENTION
The invention relates to operation monitoring and failure predicting in systems including a drive-operated motor, based on Motor Current Signature Analysis (MCSA) performed on a drive level.
BACKGROUND ART
Induction motor drives are the most widely used electrical drive systems and typically consume 40 to 50 percent of an. industrialized nation's total generating capacity. To ensure safe and efficient operation and maintain operational readiness in emergency situations, these motor drives must be maintained so that they operate properly under all anticipated conditions. MCSA is a condition monitoring technique that is now widely used to diagnose different motor related faults. It is necessary to detect a number of failures of the motor connected to particular drive and, potentially, to get more information about state of the motor and motor operated load (e.g. pump) on a drive level.
There are faults of two types: mechanical damage and electrical damage. Most typical faults (see Fig. 1) related to motors are connected with broken bars, rotor core, end ring, rotor shaft, rotor bars and ventilating ducts. According to the Baker company (IEEE study), problems related to rotor and stator of the motor are 34% of all faults, the rest are for bearing and other faults (see Fig. 2).
For some customers it is very important to detect failure at the earliest possible time, since it is directly connected with financial outcome, resources loss, etc. MSCA allows customers to save the money, therefore, it has to be considered through the prism of Machine Learning methods due to the fact that nearly all analysis is currently done via the visual inspection of the current and torque spectra.
The complete MCSA strategy can be represented by Fig. 3.
In order to predict failures and to do the preventive maintenance one should be able to perform the current spectrum analysis similar to the one presented at Fig. 4.
Classical MCSA methods are based on comparison of measured parameters: voltage, current, power, frequency with thresholds. Recommendations on parameters are set by IEEE standards.
There are two approaches of MCSA: the first - visual analysis of measured parameters, the second - automated analysis of measured parameter.
One of the most valuable tools of visual analysis available to the field service technician for troubleshooting is the recording ammeter. Properly monitored, the ammeter chart can provide valuable information for the detection and correction of minor operational problems before they become costly major problems. When the ammeter is properly utilized and understood, it can be very valuable in showing when a change in the equipment operation or well characteristics occur. An expert performs an analysis of ammeter charts.
MCSA is applied usually by installing additional hardware (HW) for motor current data acquisition and processing. For example, there is Artesis Motor Condition Monitor solution (see http://www.artesis.com). Artesis monitors plant and equipment, it identifies incipient faults on both the electric motor and the driven equipment and alerts staff as soon as something starts to go amiss. Such HW is connected to motor supply cables for current measurements, results of the MCSA are output to Human Machine Interface (HM-interface) in form of operator panel.
US 4965513 discloses a motor current noise signature analysis method and apparatus for remotely monitoring the operating characteristics of an electric motor- operated device such as a motor-operated valve. Frequency domain signal analysis techniques are applied to a conditioned motor current signal to distinctly identify various operating parameters of the motor driven device from the motor current signature. The signature may be recorded and compared with subsequent signatures to detect operating abnormalities and degradation of the device.
In case of automated analysis most often threshold based methods are used.
Thresholds are applied for measured signals directly or for extracted features: frequency, time-frequency or others, but such methods do not utilize dependencies between measured parameters.
Publication entitled "Motor Current Signature Analysis to Detect Faults in Induction Motor Drives - Fundamentals, Data Interpretation, and Industrial Case Histories", Thomson W.T. and Gilmore R.J., Texas (USA), 2003, discloses fundamentals on MCSA plus data interpretation and the presentation of industrial case histories.
Therefore, an object of the present invention is to provide a method and system for operation monitoring and failure predicting, capable to get more information about state of a motor and motor operated load and to increase accuracy of operation monitoring and failure predicting of a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level.
SUMMARY OF THE INVENTION
This object is achieved in a method for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, the method comprising:
collecting motor current data by a condition monitor, the collected motor current data being obtained from a motor current signal being available through an HM- interface supported by a particular drive,
processing the collected data by the MCSA on a drive firmware level, making a decision regarding an operation condition and predicting a failure based on results of the processing,
wherein the processing comprises simulating the system by a complex valued recurrent neural network.
In another aspect, provided is a system for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, the system configured to perform said method.
BRIEF DESCRIPTION OF THE DRAWINGS
Exemplary embodiments of the invention are explained in more detail by means of the drawings in which:
Fig. 1 represents most typical motor related faults.
Fig. 2 represents types of faults of motors and their occurrences.
Fig. 3 represents a complete MCSA strategy.
Fig. 4 represents a current spectrum analysis, wherein sidebands relate to the Main Component of the spectrum.
Fig. 5 shows levels of integration from state of the art system with additional HW to fully integrated solution according to one embodiment of the invention. Fig. 6 is a model-based approach for fault detection according to one embodiment of the invention.
Fig. 7 shows results of the transformer modeling for the subset of data containing leaps, according to one embodiment of the invention.
Fig. 8 shows results of the transformer modeling for the subset of data containing leaps (absolute values for voltage and current), according to another embodiment of the invention.
Fig. 9 shows results of the transformer modeling for the subset of data containing leaps (real and imaginary values for voltage and current), according to another embodiment of the invention.
DESCRIPTION OF EMBODIMENTS
Main idea of the invention is to claim the MCSA integrated on the drive level. The data which is usually collected by state-of-the-art MCSA devices is already available at the drive level. Levels of integration are shown on Fig. 5 from state of the art system with additional HW to fully integrated solution where all the analysis of the motor current signal is performed on drive firmware level. Results of the MCSA can be accessed through a drive HM-interface or/and digital communication interfaces supported by a particular drive (for example, Profibus).
An algorithm of the method for operation monitoring and failure predicting in system including drive-operated motor, based on Motor Current Signature Analysis (MCSA) performed on a drive level, can be described in the following way. Each block of motor can be presented as a dynamic system. There are different approaches for modeling of dynamic systems: linear transfer function, neural networks, lookup tables. A model of a dynamic system simulates dependence between input of the system and output. In a general model-based fault detection method, a model output is compared with a real output by calculation of difference (model error). Then this difference is classified by a machine learning classifier (see Fig. 6).
In this invention disclosure described is an application of a complex valued recurrent neural network for modeling motor blocks.
Further simulation results are considered. The results of modeling are shown in Fig. 7, where time characterizes time steps at which measurements are made. The statistics for the training set is not presented since it is nearly ideal as it should be at the training set. Here one can see that expectation values almost coincide with the observation ones and only differ slightly at the bump area; statistical coefficients are also close to their corresponding best values. Fig. 8 and Fig. 9 show Validation set results for the whole time period and for the specified area with a leap of current and voltage
Fig. 7 shows results of the transformer modeling for the subset of data containing leaps. One can see the real part of the network outputs and the actual values of I2, U2 on the training set. The image is zoomed, since otherwise one can not see the short circuit moment. One can see that network reacted perfectly, but this is training set.
Fig. 8 shows results of the transformer modeling for the subset of data containing leaps. One can see the real part of the network outputs and the actual values of , U2 on the Validation set. The region is zoomed in order to see the short circuit moment better. Absolute values for voltage and current are shown.
Fig. 9 shows results of the transformer modeling for the subset of data containing leaps. One can see the real part of the network outputs and the actual values of , U2 on the Validation set. The region is zoomed in order to see the short circuit moment better. Real and Imaginary values for voltage and current are shown.
One can see the moment where a short circuit happened (region between the 100 and 104 patterns at the Fig.8 and Fig. 9). One can see that network was able to predict such change of the sin like function of the current and voltage. Such results are only possible with the complex valued neural network due to the following reasons: the system under the modeling is recurrent, since it has memory e.g. the current state of the transformer depends on the previous states of the transformer. Another reason is that one cannot model the transformer with the real valued network in the same way we did, since one will have to separate the real and imaginary parts of the current and voltage and feed this information as a separate inputs. In this case he takes a hypothesis, that imaginary part and real part of the complex inputs are independent and do not interact while neural network processing which is not the case to our point of view. The complex valued signals interact inside the neural network which makes the modeling more physical since now we model waves interaction inside the complex weights of the neural network. Such approach can be considered as "back to analogous" modeling. Using the complex valued networks we can model such things like interference of the waves etc. The presented results can be easily extended for other electrical elements modeling like Phasors, Generators, Drives etc.
Thus, the claimed invention provides unique algorithmic base for MCSA developed for embedded applications, possibility to put the suggested methods into the control system of a motor, possibility to implement remote condition monitoring based on standard motor functionality, implementation of the additional feature of the drive using the MCSA approach.

Claims

1. Method for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, comprising:
collecting motor current data by a condition monitor, the collected motor current data being obtained from a motor current signal being available through an HM- interface supported by a particular drive,
processing the collected data by the MCSA on a drive firmware level, making a decision regarding the operation condition and predicting a failure based on results of the processing,
wherein the processing comprises simulating the system by a complex valued recurrent neural network.
2. The method according to claim 1, wherein the system is presented as a dynamic system.
3. The method according to claim 1, wherein the simulating the system consists in simulating dependence between system input and system output.
4. The method according to claim 1, comprising comparing model output with real output by calculating difference as a model error.
5. The method according to claim 1, wherein input and output values are motor current data.
6. The method according to claim 1 , wherein motor current data are at least one of a voltage, current, power or frequency.
7. System for operation monitoring and failure predicting in a system including a drive-operated motor, based on the Motor Current Signature Analysis (MCSA) performed on a drive level, the system being configured to perform the method according to claim 1.
PCT/RU2013/000834 2013-09-25 2013-09-25 Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery WO2015047121A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/RU2013/000834 WO2015047121A1 (en) 2013-09-25 2013-09-25 Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/RU2013/000834 WO2015047121A1 (en) 2013-09-25 2013-09-25 Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery

Publications (1)

Publication Number Publication Date
WO2015047121A1 true WO2015047121A1 (en) 2015-04-02

Family

ID=50473747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2013/000834 WO2015047121A1 (en) 2013-09-25 2013-09-25 Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery

Country Status (1)

Country Link
WO (1) WO2015047121A1 (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107831438A (en) * 2017-10-25 2018-03-23 上海交通大学 The Forecasting Methodology and forecasting system of a kind of electrical fault
WO2018189751A1 (en) * 2017-04-13 2018-10-18 Janardhana Swamy Electric driver control system and method thereof
CN109188185A (en) * 2018-08-17 2019-01-11 中国大唐集团科学技术研究院有限公司 A kind of generator rotor interturn short-circuit early stage online test method
WO2019026475A1 (en) * 2017-07-31 2019-02-07 株式会社安川電機 Power conversion device, server, and data generation method
CN110376522A (en) * 2019-09-03 2019-10-25 宁夏西北骏马电机制造股份有限公司 A kind of Method of Motor Fault Diagnosis of the deep learning network of data fusion
CN110687473A (en) * 2019-09-27 2020-01-14 国网四川省电力公司电力科学研究院 Fault positioning method and system for relay protection test of intelligent substation
WO2022043101A1 (en) * 2020-08-28 2022-03-03 Siemens Aktiengesellschaft Method and system for monitoring a machine state
US11639966B2 (en) 2021-03-15 2023-05-02 General Electric Technology Gmbh Enhanced electrical signature analysis for fault detection
US11733301B2 (en) 2021-05-13 2023-08-22 General Electric Technology Gmbh Systems and methods for providing voltage-less electrical signature analysis for fault protection
EP4345562A1 (en) * 2022-09-28 2024-04-03 Rockwell Automation Technologies, Inc. Systems and methods for container-based data collection and analysis in an operational technology network

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4965513A (en) 1986-09-30 1990-10-23 Martin Marietta Energy Systems, Inc. Motor current signature analysis method for diagnosing motor operated devices
US5629870A (en) * 1994-05-31 1997-05-13 Siemens Energy & Automation, Inc. Method and apparatus for predicting electric induction machine failure during operation
US20030042861A1 (en) * 2001-06-11 2003-03-06 Elia Schwartz System and method for predicting mechanical failures in machinery driven by an induction motor
EP1757554A2 (en) * 2005-08-24 2007-02-28 Rockwell Automation Technologies, Inc. Anti-sway control for crane
US20090204267A1 (en) * 2001-08-10 2009-08-13 Rockwell Automation Technologies, Inc. System and method for dynamic multi-objective optimization of machine selection, integration and utilization
US20100169030A1 (en) * 2007-05-24 2010-07-01 Alexander George Parlos Machine condition assessment through power distribution networks

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4965513A (en) 1986-09-30 1990-10-23 Martin Marietta Energy Systems, Inc. Motor current signature analysis method for diagnosing motor operated devices
US5629870A (en) * 1994-05-31 1997-05-13 Siemens Energy & Automation, Inc. Method and apparatus for predicting electric induction machine failure during operation
US20030042861A1 (en) * 2001-06-11 2003-03-06 Elia Schwartz System and method for predicting mechanical failures in machinery driven by an induction motor
US20090204267A1 (en) * 2001-08-10 2009-08-13 Rockwell Automation Technologies, Inc. System and method for dynamic multi-objective optimization of machine selection, integration and utilization
EP1757554A2 (en) * 2005-08-24 2007-02-28 Rockwell Automation Technologies, Inc. Anti-sway control for crane
US20100169030A1 (en) * 2007-05-24 2010-07-01 Alexander George Parlos Machine condition assessment through power distribution networks

Non-Patent Citations (10)

* Cited by examiner, † Cited by third party
Title
BEHBAHANIFARD H ET AL: "Non-invasive on-line detection of winding faults in induction motorsâ A review", CONDITION MONITORING AND DIAGNOSIS, 2008. CMD 2008. INTERNATIONAL CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 21 April 2008 (2008-04-21), pages 188 - 191, XP031292475, ISBN: 978-1-4244-1621-9 *
GUEDIDI S ET AL: "Broken bar fault diagnosis of induction motors using MCSA and neural network", DIAGNOSTICS FOR ELECTRIC MACHINES, POWER ELECTRONICS&DRIVES (SDEMPED), 2011 IEEE INTERNATIONAL SYMPOSIUM ON, IEEE, 5 September 2011 (2011-09-05), pages 632 - 637, XP032067940, ISBN: 978-1-4244-9301-2, DOI: 10.1109/DEMPED.2011.6063690 *
HAMDANI S ET AL: "Neural network technique for induction motor rotor faults classification-dynamic eccentricity and broken bar faults-", DIAGNOSTICS FOR ELECTRIC MACHINES, POWER ELECTRONICS&DRIVES (SDEMPED), 2011 IEEE INTERNATIONAL SYMPOSIUM ON, IEEE, 5 September 2011 (2011-09-05), pages 626 - 631, XP032067939, ISBN: 978-1-4244-9301-2, DOI: 10.1109/DEMPED.2011.6063689 *
MANJEEVAN SEERA ET AL: "Fault Detection and Diagnosis of Induction Motors Using Motor Current Signature Analysis and a Hybrid FMM CART Model", IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 23, no. 1, 1 January 2012 (2012-01-01), pages 97 - 108, XP011391224, ISSN: 2162-237X, DOI: 10.1109/TNNLS.2011.2178443 *
MERUGU SIVA RAMA KRISHNA ET AL: "Neural network for the diagnosis of rotor broken faults of induction motors using MCSA", INTELLIGENT SYSTEMS AND CONTROL (ISCO), 2013 7TH INTERNATIONAL CONFERENCE ON, IEEE, 4 January 2013 (2013-01-04), pages 133 - 137, XP032344440, ISBN: 978-1-4673-4359-6, DOI: 10.1109/ISCO.2013.6481136 *
PARLOS A G ET AL: "Detection of induction motor faults - combining signal-based and model-based techniques", PROCEEDINGS OF THE 2002 AMERICAN CONTROL CONFERENCE. ACC. ANCHORAGE, AL, MAY 8 - 10, 2002; [AMERICAN CONTROL CONFERENCE], NEW YORK, NY : IEEE, US, vol. 6, 8 May 2002 (2002-05-08), pages 4531 - 4536, XP010597637, ISBN: 978-0-7803-7298-6, DOI: 10.1109/ACC.2002.1025365 *
PAWLAK M ET AL: "Low-cost embedded system for the IM fault detection using neural networks", ELECTRICAL MACHINES (ICEM), 2010 XIX INTERNATIONAL CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 6 September 2010 (2010-09-06), pages 1 - 5, XP031779444, ISBN: 978-1-4244-4174-7 *
QIANJIN GUO ET AL: "Broken Rotor Bars Fault Detection in Induction Motors Using Parkâ s Vector Modulus and FWNN Approach", 24 September 2008, ADVANCES IN NEURAL NETWORKS - ISNN 2008; [LECTURE NOTES IN COMPUTER SCIENCE], SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 809 - 821, ISBN: 978-3-540-87733-2, XP019107004 *
THOMSON W.T.; GILMORE R.J., MOTOR CURRENT SIGNATURE ANALYSIS TO DETECT FAULTS IN INDUCTION MOTOR DRIVES - FUNDAMENTALS, DATA INTERPRETATION, AND INDUSTRIAL CASE HISTORIES, 2003
WILLIAM T THOMSON ET AL: "MOTOR CURRENT SIGNATURE ANALYSIS TO DETECT FAULTS IN INDUCTION MOTOR DRIVES-FUNDAMENTALS, DATA INTERPRETATION, AND INDUSTRIAL CASE HISTORIES", PROCEEDINGS OF THE THIRTY-SECOND TURBOMACHINERY SYMPOSIUM, 11 September 2003 (2003-09-11), Houston, Texas, USA, pages 145 - 156, XP055126095, Retrieved from the Internet <URL:http://turbo-lab.tamu.edu/proc/turboproc/T32/t32-16.pdf> [retrieved on 20140701] *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018189751A1 (en) * 2017-04-13 2018-10-18 Janardhana Swamy Electric driver control system and method thereof
WO2019026475A1 (en) * 2017-07-31 2019-02-07 株式会社安川電機 Power conversion device, server, and data generation method
US11038454B2 (en) 2017-07-31 2021-06-15 Kabushiki Kaisha Yaskawa Denki Power conversion device and server
CN107831438A (en) * 2017-10-25 2018-03-23 上海交通大学 The Forecasting Methodology and forecasting system of a kind of electrical fault
CN109188185A (en) * 2018-08-17 2019-01-11 中国大唐集团科学技术研究院有限公司 A kind of generator rotor interturn short-circuit early stage online test method
CN110376522A (en) * 2019-09-03 2019-10-25 宁夏西北骏马电机制造股份有限公司 A kind of Method of Motor Fault Diagnosis of the deep learning network of data fusion
CN110687473A (en) * 2019-09-27 2020-01-14 国网四川省电力公司电力科学研究院 Fault positioning method and system for relay protection test of intelligent substation
CN110687473B (en) * 2019-09-27 2021-08-03 国网四川省电力公司电力科学研究院 Fault positioning method and system for relay protection test of intelligent substation
WO2022043101A1 (en) * 2020-08-28 2022-03-03 Siemens Aktiengesellschaft Method and system for monitoring a machine state
US11639966B2 (en) 2021-03-15 2023-05-02 General Electric Technology Gmbh Enhanced electrical signature analysis for fault detection
US11733301B2 (en) 2021-05-13 2023-08-22 General Electric Technology Gmbh Systems and methods for providing voltage-less electrical signature analysis for fault protection
EP4345562A1 (en) * 2022-09-28 2024-04-03 Rockwell Automation Technologies, Inc. Systems and methods for container-based data collection and analysis in an operational technology network

Similar Documents

Publication Publication Date Title
WO2015047121A1 (en) Method and apparatus for embedded current signature analysis and remote condition monitoring for industrial machinery
Gangsar et al. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review
Seera et al. Fault detection and diagnosis of induction motors using motor current signature analysis and a hybrid FMM–CART model
EP3462602B1 (en) Method and apparatus for online condition monitoring of variable speed motor applications
EP2702374B1 (en) Method for monitoring demagnetization
CN102033200B (en) On-line monitoring and diagnosis method of AC (alternating current) motor based on statistical model
CN107037331B (en) Method and system for monitoring the insulation state of a wind turbine winding in real time
EP3904988A1 (en) Induction motor condition monitoring using machine learning
WO2008148075A1 (en) Machine condition assessment through power distribution networks
WO2011156080A1 (en) Systems and methods for learning of normal sensor signatures, condition monitoring and diagnosis
CN110987166A (en) Method, device, equipment and storage medium for predicting health state of rotating machine
Leonidovich et al. The development and use of diagnostic systems and estimation of residual life in industrial electrical equipment
Hofmeister et al. Prognostic health management (PHM) of electrical systems using condition-based data for anomaly and prognostic reasoning
Rajamany et al. Negative sequence current compensation for induction motor stator inter-turn short circuit and off-diagonal term in sequence impedance matrix as fault indicator
Iorgulescu et al. Faults diagnosis for electrical machines based on analysis of motor current
US11156666B2 (en) System and methods for fault detection
Ranga et al. Advanced tool based condition monitoring of induction machines by using LabVIEW—A review
Bulgakov et al. A cyber-physical system of diagnosing electric drives of building robots
KR102150425B1 (en) Monitoring apparatus for rotary machine and monitoring method for rotary machine
Jose et al. Induction motor fault diagnosis methods: A comparative study
Al-Leythi et al. Motor Watch-Motor Fault Signature Analysis
Brandão et al. Intelligent system for fault detection in wind turbines gearbox
Abed Robust Fault Analysis for Permanent Magnet DC Motor in Safety Critical Applications
KR101386109B1 (en) Method for detecting on-line short-turn rotor windings of synchro generator
Xue et al. Sensor fusion for machine condition monitoring

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13844580

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13844580

Country of ref document: EP

Kind code of ref document: A1