CN104260754A - Track height irregularity prediction system and method based on axle box vibration acceleration - Google Patents
Track height irregularity prediction system and method based on axle box vibration acceleration Download PDFInfo
- Publication number
- CN104260754A CN104260754A CN201410526294.1A CN201410526294A CN104260754A CN 104260754 A CN104260754 A CN 104260754A CN 201410526294 A CN201410526294 A CN 201410526294A CN 104260754 A CN104260754 A CN 104260754A
- Authority
- CN
- China
- Prior art keywords
- axle box
- vibration acceleration
- box vibration
- track transition
- signal
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
Abstract
The invention discloses a track height irregularity prediction system and method based on axle box vibration acceleration. The track height irregularity prediction system comprises an axle box vibration acceleration sensor, a rotation pulse tacho-generator, a simulation preprocessing circuit, an A/D (analog/digital) conversion circuit, an embedded system, a wireless network router and an upper computer. The axle box vibration acceleration sensor is arranged on an axle box disposed on a running part of a train. The rotation pulse tacho-generator is arranged in an end cover of a train axle. Axle box vibration signals collected by the axle box vibration acceleration sensor and train speed signals collected by the rotation pulse tacho-generator are subject to low-pass filtering processing through the simulation preprocessing circuit, analog signals are converted to digital signals through the A/D conversion circuit, the digital signals are sent to the upper computer by the embedded system through the wireless network router to be processed, and the upper computer measures the track height irregularity result through the vibration signals. The track height irregularity prediction system and method have the advantages of low cost and good implementation.
Description
Technical field
The present invention relates to the technical field, particularly a kind of track transition prognoses system based on axle box vibration acceleration and method of track irregularity prediction.
Background technology
Track irregularity refers to the deviation of track geometry shape, size its normal condition relative to locus.Rectilinear orbit is uneven, straight, to position of center line and orbit altitude, the departing from of width just size; Curve track is not smoother, deflection curve position of center line, departs from the correct value of curvature, superelevation, gauge, departs from along track geometry deviation common name track irregularities such as slope varying dimensions.It is the major influence factors that rolling stock generation random vibration, track structure fatigue damage and rolling stock safety in operation decline.
The reason and the influence factor that produce track irregularity are a lot.Track irregularity often originates from manufacturing errors or the tolerance of the track components such as the defect of rail material and rail, and the various initial irregularity directly produced in line construction quality and work progress.After operation opened by track, under High-speed Train Loads, new track irregularity will produce development further, and the various initial irregularity originating from manufacture and track construction process will increase deterioration gradually.In operation process, the effect of rolling stock is the major cause that track irregularity occurs, develops and worsen.In addition, the change of natural environment, orbital maintenance operation, the factors such as track construction have very important impact to the generation of track irregularity, development, deterioration.
Yang Wenzhong studies (the loyal axle box acceleration of base Yu Xiaobo of Yang Wen and the research Tongji University Ph.D. Dissertation 2008 of track irregularity relation) axle box acceleration and track transition, the method calculates track transition by axle box acceleration double integrator, but the method needs the accelerometer of multiple different bandwidth to realize, and engineering construction is poor.
Lee again curtain etc. proposes to utilize Hilbert-Huang transform method to analyze (Lee's curtain again to longitudinal irregularity in vehicle-rail system and Vertical Vibration of Vehicle acceleration/accel relation, practice pine good, the application of Liu Xiao boat HHT in vehicle-rail system vertical vibration time frequency analysis, vibration-testing and diagnosis 2013), utilize Empirical mode decomposition (empirical mode decomposition, be called for short EMD) longitudinal irregularity of surveying and Vertical Vibration of Vehicle acceleration signal are decomposed, obtain both intrinsic mode functions; Then, by time domain waveform and the Hilbert energy spectrum of both comparative analysis intrinsic mode functions, deterministic corresponding relation between longitudinal irregularity intrinsic mode functions and Vertical Vibration of Vehicle acceleration/accel intrinsic mode functions is described, Vertical Vibration of Vehicle acceleration/accel can be utilized to identify the bad section of track transition, the method needs, according to track checking car collection vibration and track transition data, can not be applicable to common vehicle in use.
Summary of the invention
The object of the present invention is to provide a kind of cost is low, engineering construction is good the track transition prognoses system based on axle box vibration acceleration and method, by the vibration acceleration signal gathered on vehicle in use axle box, real time on-line monitoring is carried out to track transition.
The technical solution realizing the object of the invention is: a kind of track transition prognoses system based on axle box vibration acceleration, comprises axle box vibration acceleration sensor, rotary pulsed tachogenerator, simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer; Described axle box vibration acceleration sensor is arranged on train EEF bogie axle box, rotary pulsed tachogenerator is arranged in train axle end cap, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
The axle box vibration signal of described axle box vibration acceleration sensor collection and the vehicle speed signal of rotary pulsed tachogenerator collection first carry out low-pass filtering treatment through simulation pre-process circuit, analog signal is converted to digital signal again through A/D change-over circuit, digital signal is sent to upper computer by embedded system through wireless network route and processes, and upper computer obtains track transition result by vibration signal prediction.
Based on a track transition Forecasting Methodology for axle box vibration acceleration, comprise following steps:
Step 1, train EEF bogie axle box arranges axle box vibration acceleration sensor, in train axle end cap, rotary pulsed tachogenerator is set, and simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer are set on operation train;
Step 2, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
Step 3, vehicle is in operation process, gather axle box vibration acceleration signal by axle box vibration acceleration sensor, rotary pulsed tachogenerator gathers vehicle speed signal, the signal gathered carries out filtering through simulation pre-process circuit, convert analog signal to digital signal input embedded system through A/D change-over circuit again, the data of collection are sent to upper computer by wireless network route by embedded system;
Step 4, existing axle box vibration acceleration signal is composed as output as input, track transition by upper computer, adopt exogenous nonlinear Recurrent neural network NARX training, obtain network-related parameters, described network-related parameters comprises internodal link weight coefficients, each Node B threshold;
Step 5, upper computer utilizes the axle box vibration acceleration signal collected by NARX neural network real-time estimate current orbit longitudinal irregularity.
Compared with prior art, its remarkable advantage is in the present invention: (1) detects track irregularity on vehicle in use, avoids the operation expense that traditional detection method needs special track checking car to bring; (2) engineering construction is good, and described axle box vibration acceleration sensor and the convenient installation of rotary pulsed tachogenerator, reliability is high.
Accompanying drawing explanation
Fig. 1 is the constructional drawing of the track transition prognoses system that the present invention is based on axle box vibration acceleration.
Fig. 2 is the scheme of installation of sensor in present system.
Fig. 3 is the diagram of circuit of the track transition Forecasting Methodology that the present invention is based on axle box vibration acceleration.
Fig. 4 is for training obtained NARX neural network output valve and real system output valve in embodiment.
Fig. 5 is for testing obtained NARX neural network output valve and real system output valve in embodiment.
Detailed description of the invention
Below in conjunction with drawings and the specific embodiments, the present invention is described in further detail.
Composition graphs 1, the present invention is based on the track transition prognoses system of axle box vibration acceleration, comprise axle box vibration acceleration sensor, rotary pulsed tachogenerator, simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer; Described axle box vibration acceleration sensor is arranged on train EEF bogie axle box, rotary pulsed tachogenerator is arranged in train axle end cap, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
The axle box vibration signal of described axle box vibration acceleration sensor collection and the vehicle speed signal of rotary pulsed tachogenerator collection first carry out low-pass filtering treatment through simulation pre-process circuit, analog signal is converted to digital signal again through A/D change-over circuit, digital signal is sent to upper computer by embedded system through wireless network route and processes, upper computer obtains track transition result by vibration signal prediction, and result is carried out show, storage etc.
Composition graphs 1 ~ 2, the present invention is based on the track transition Forecasting Methodology of axle box vibration acceleration, comprises following steps:
Step 1, train EEF bogie axle box arranges axle box vibration acceleration sensor, in train axle end cap, rotary pulsed tachogenerator is set, and simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer are set on operation train;
Step 2, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
Step 3, vehicle is in operation process, gather axle box vibration acceleration signal by axle box vibration acceleration sensor, rotary pulsed tachogenerator gathers vehicle speed signal, the signal gathered carries out filtering through simulation pre-process circuit, convert analog signal to digital signal input embedded system through A/D change-over circuit again, the data of collection are sent to upper computer by wireless network route by embedded system;
Step 4, existing axle box vibration acceleration signal is composed as output as input, track transition by upper computer, adopt exogenous nonlinear Recurrent neural network NARX (Nonlinear Auto-Regressive with eXogenous input Neural Networks) training, obtain network-related parameters, described network-related parameters comprises internodal link weight coefficients, each Node B threshold;
Step 5, upper computer utilizes the axle box vibration acceleration signal collected by NARX neural network real-time estimate current orbit longitudinal irregularity.
Composition graphs 3, upper computer utilizes the axle box vibration acceleration signal collected by NARX neural network real-time estimate current orbit longitudinal irregularity, specific as follows:
(1) according to the track transition data having axle box vibration acceleration signal and historical accumulation, be normalized respectively this axle box vibration acceleration signal and track transition data, normalization method formula is:
In formula,
for the data after normalization method, x
ifor i-th data, x in vibration acceleration signal or track transition data
minfor minimum value, x in vibration acceleration signal or track transition data
maxfor maxim in vibration acceleration signal or track transition data;
(2) NARX neural network structure is determined, comprise input number of nodes, output node number, hidden layers numbers, the input and output layer neuron number of setting NARX network, input layer is 1, output layer neuron is 1, select the activation function of hidden node and output layer node, activation function comprises threshold function table, piecewise linear function and nonlinear function;
(3) determine hidden node number, adopting experience traversal, namely carrying out training network by choosing different Hidden nodes, choose hidden node number during performance the best;
(4) time delay exponent number is determined, get and postpone exponent number and output time input time and postpone exponent number and be consistent, employing experience traversal constructs the NARX neural network that one group of different time postpones exponent number, selects the time delay exponent number that test root-mean-square error (RMS error) is minimum;
(5) training algorithm being applicable to this NARX neural network is selected, NARX neural network BP training algorithm comprises: Real Time Recurrent Learning Algorithm (RTRL), BP algorithm (BPTT) in time, dynamic BP algorithm (DBP), hierarchical optimization algorithm (Layer-By-Layer optimizing), Bayesian regularization (BR) algorithm etc., this NARX neural network due to BPTT can not on-line operation, DBP computation complexity is higher, RTRL efficiency is lower, and BR algorithm can reduce actv. network parameter to make up larger network error, therefore select BR algorithm;
(6) utilize the input of axial vibration acceleration information as NARX neural network of historical accumulation, track transition data train NARX as the output of NARX neural network, obtain NARX neural metwork training index, described NARX neural metwork training index comprises root-mean-square error (RMS error) and network exports and the actual coefficient of correlation exported, relatively train the coefficient of correlation between the NARX neural network output valve obtained and real system output valve, evaluating network performance, root-mean-square error (RMS error) is less, close to 1, coefficient of correlation more shows that network performance is more superior;
(7) the real-time axle box vibration acceleration signal gathered is inputted as NARX neural network, predicted orbit longitudinal irregularity, transfinite in point system according to railway interests's local irregularity amplitude and track transition state is judged to the Rail inspection allowance deviation of longitudinal irregularity, calculate train operation distance and track transition data with reference to speed signal, extrapolate track transition position.
Embodiment 1
Composition graphs 1, the present invention is based on the track transition prognoses system of axle box vibration acceleration, comprise axle box vibration acceleration sensor, rotary pulsed tachogenerator, simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer; Described axle box vibration acceleration sensor is arranged on train EEF bogie axle box, rotary pulsed tachogenerator is arranged in train axle end cap, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system; The axle box vibration signal of described axle box vibration acceleration sensor collection and the vehicle speed signal of rotary pulsed tachogenerator collection first carry out low-pass filtering treatment through simulation pre-process circuit, analog signal is converted to digital signal again through A/D change-over circuit, digital signal is sent to upper computer by embedded system through wireless network route and processes, and upper computer obtains track transition result by vibration signal prediction.
The DH112 type piezoelectric acceleration transducer that described axle box vibration acceleration sensor adopts the test of east China to produce, range is 1000m/s
2, frequency response range is 0.5 ~ 1KHz, and sensitivity is 0 ~ 5mV/ms
-2.
Described embedded system adopts arm processor to be the embedded system device of core, this equipment comprises wireless network module, and the model of this arm processor is AT91SAM9263, dominant frequency 200MHz, have peripheral hardware resource in abundant sheet, can embedded Linux system be run; Described embedded system is integrated with MAC circuit, adopt the Ethernet interface of PHY chip DM9161, by arranging IP address and MAC carries out ethernet connection, be configured with the USB-WIFI module based on RT3070 chip, this USB-WIFI module is connected with mainboard by USB interface, transfer rate 150Mbps, can realize the wireless connections of simulating platform and wireless routing by the driving adding this USB-WIFI module in the motherboard.
Described wireless network route adopts the AR151W-P/AR151W-P-type wireless router of Huawei Company, and IMX is 100Mbps, and memory size is 512M, has serial and assists/control desk port.
The ITX3010 core main frame that described upper computer adopts Sheng Bo scientific & technical corporation to produce, this main frame adopts Intel atom treater D525, supports that Surface Mount internal memory, DIMM bar are expanded, internal memory reaches 2GB/4GB, supports 2 SATA, supports that 18 VGA are aobvious with independent pair, Linux, VxWorks, Windows can be run, PC/104 and PC/104+ bus extension is provided.
Composition graphs 3 ~ 5, utilizes the algorithm flow of axle box vibration acceleration signal predicted orbit longitudinal irregularity to be:
(1) according to existing axial vibration acceleration information and track transition data, data are normalized, by data normalization in [01] scope:
In formula,
for the data after normalization method, x
ifor i-th data, x in vibration acceleration signal or track transition data
minfor minimum value, x in vibration acceleration signal or track transition data
maxfor maxim in vibration acceleration signal or track transition data.
(2) NARX neural network structure is determined, the input layer of setting NARX network is axle box vibration acceleration, input number of nodes is 1, output layer neuron is track transition, output node number is 1, select hidden node activation function to be Sigmoid function, output layer node activation function is linear function.
(3) determine hidden node number, empirically, select suitable hidden node number to be 17.
(4) determine time delay exponent number, get and postpone exponent number and output time input time and postpone exponent number and be consistent, empirically or test determine that time delay exponent number is 45.
(5) training algorithm of this NARX neural network is selected to be Bayesian Regularization algorithm.
(6) Fig. 4, Fig. 5 give the comparison between NARX neural network output valve and real system output valve that training and testing obtains, and training coefficient R is 0.8030, and test coefficient R is 0.7730.Visible, NARX neural network exports the good relationship exported with real system,
(7) the real-time axle box vibration acceleration signal gathered is inputted as NARX neural network, predicted orbit longitudinal irregularity, according to threshold determination longitudinal irregularity, track transition position can be calculated with reference to speed signal.
In sum, the present invention detects track irregularity on vehicle in use, avoids the operation expense that traditional detection method needs special track checking car to bring; Engineering construction is good, and described axle box vibration acceleration sensor and the convenient installation of rotary pulsed tachogenerator, reliability is high.
Claims (7)
1. the track transition prognoses system based on axle box vibration acceleration, it is characterized in that, comprise axle box vibration acceleration sensor, rotary pulsed tachogenerator, simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer; Described axle box vibration acceleration sensor is arranged on train EEF bogie axle box, rotary pulsed tachogenerator is arranged in train axle end cap, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
The axle box vibration signal of described axle box vibration acceleration sensor collection and the vehicle speed signal of rotary pulsed tachogenerator collection first carry out low-pass filtering treatment through simulation pre-process circuit, analog signal is converted to digital signal again through A/D change-over circuit, digital signal is sent to upper computer by embedded system through wireless network route and processes, and upper computer obtains track transition result by vibration signal prediction.
2. the track transition prognoses system based on axle box vibration acceleration according to claim 1, is characterized in that, the DH112 type piezoelectric acceleration transducer that described axle box vibration acceleration sensor adopts the test of east China to produce, and range is 1000m/s
2, frequency response range is 0.5 ~ 1KHz, and sensitivity is 0 ~ 5mV/ms
-2.
3. the track transition prognoses system based on axle box vibration acceleration according to claim 1, it is characterized in that, described embedded system adopts arm processor to be the embedded system device of core, this equipment comprises wireless network module, the model of this arm processor is AT91SAM9263, dominant frequency 200MHz; Described embedded system is integrated with MAC circuit, adopt the Ethernet interface of PHY chip DM9161, by arranging IP address and MAC carries out ethernet connection, be configured with the USB-WIFI module based on RT3070 chip, this USB-WIFI module is connected with mainboard by USB interface, transfer rate 150Mbps.
4. the track transition prognoses system based on axle box vibration acceleration according to claim 1, it is characterized in that, described wireless network route adopts the AR151W-P/AR151W-P-type wireless router of Huawei Company, IMX is 100Mbps, memory size is 512M, has serial and assists/control desk port.
5. the track transition prognoses system based on axle box vibration acceleration according to claim 1, it is characterized in that, the ITX3010 core main frame that described upper computer adopts Sheng Bo scientific & technical corporation to produce, this main frame adopts Intel atom treater D525, supports that Surface Mount internal memory, DIMM bar are expanded, internal memory reaches 2GB/4GB, supports 2 SATA, supports that 18 VGA are aobvious with independent pair, Linux, VxWorks, Windows can be run, PC/104 and PC/104+ bus extension is provided.
6., based on a track transition Forecasting Methodology for axle box vibration acceleration, it is characterized in that, comprise following steps:
Step 1, train EEF bogie axle box arranges axle box vibration acceleration sensor, in train axle end cap, rotary pulsed tachogenerator is set, and simulation pre-process circuit, A/D change-over circuit, embedded system, wireless network route, upper computer are set on operation train;
Step 2, the mouth of described axle box vibration acceleration sensor, rotary pulsed tachogenerator all accesses simulation pre-process circuit, and the mouth of simulation pre-process circuit is by A/D change-over circuit access embedded system;
Step 3, vehicle is in operation process, gather axle box vibration acceleration signal by axle box vibration acceleration sensor, rotary pulsed tachogenerator gathers vehicle speed signal, the signal gathered carries out filtering through simulation pre-process circuit, convert analog signal to digital signal input embedded system through A/D change-over circuit again, the data of collection are sent to upper computer by wireless network route by embedded system;
Step 4, existing axle box vibration acceleration signal is composed as output as input, track transition by upper computer, adopt exogenous nonlinear Recurrent neural network NARX training, obtain network-related parameters, described network-related parameters comprises internodal link weight coefficients, each Node B threshold;
Step 5, upper computer utilizes the axle box vibration acceleration signal collected by NARX neural network real-time estimate current orbit longitudinal irregularity.
7. the track transition Forecasting Methodology based on axle box vibration acceleration according to claim 6, it is characterized in that, upper computer described in step 5 utilizes the axle box vibration acceleration signal collected by NARX neural network real-time estimate current orbit longitudinal irregularity, specific as follows:
(1) according to the track transition data having axle box vibration acceleration signal and historical accumulation, be normalized respectively this axle box vibration acceleration signal and track transition data, normalization method formula is:
In formula,
for the data after normalization method, x
ifor i-th data, x in vibration acceleration signal or track transition data
minfor minimum value, x in vibration acceleration signal or track transition data
maxfor maxim in vibration acceleration signal or track transition data;
(2) NARX neural network structure is determined, comprise input number of nodes, output node number, hidden layers numbers, the input and output layer neuron number of setting NARX network, input layer is 1, output layer neuron is 1, select the activation function of hidden node and output layer node, activation function comprises threshold function table, piecewise linear function and nonlinear function;
(3) determine hidden node number, adopting experience traversal, namely carrying out training network by choosing different Hidden nodes, choose hidden node number during performance the best;
(4) time delay exponent number is determined, get and postpone exponent number and output time input time and postpone exponent number and be consistent, employing experience traversal constructs the NARX neural network that one group of different time postpones exponent number, selects the time delay exponent number that test root-mean-square error (RMS error) is minimum;
(5) training algorithm and the Regularization algorithms that are applicable to this NARX neural network is selected;
(6) the input data of axial vibration acceleration information as NARX neural network of historical accumulation are utilized, track transition data are trained NARX as the output data of NARX neural network, obtain NARX neural metwork training index, described NARX neural metwork training index comprises root-mean-square error (RMS error) and network exports and the actual coefficient of correlation exported, relatively train the coefficient of correlation evaluating network performance between the NARX neural network output valve obtained and real system output valve, root-mean-square error (RMS error) is less, close to 1, coefficient of correlation more shows that network performance is more superior,
(7) the real-time axle box vibration acceleration signal gathered is inputted as NARX neural network, predicted orbit longitudinal irregularity, transfinite in point system according to railway interests's local irregularity amplitude and track transition state is judged to the Rail inspection allowance deviation of longitudinal irregularity, calculate train operation distance and track transition data with reference to speed signal, extrapolate track transition position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410526294.1A CN104260754B (en) | 2014-10-08 | 2014-10-08 | Track transition forecasting system and method based on axle box vibration acceleration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410526294.1A CN104260754B (en) | 2014-10-08 | 2014-10-08 | Track transition forecasting system and method based on axle box vibration acceleration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104260754A true CN104260754A (en) | 2015-01-07 |
| CN104260754B CN104260754B (en) | 2017-06-27 |
Family
ID=52152390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410526294.1A Active CN104260754B (en) | 2014-10-08 | 2014-10-08 | Track transition forecasting system and method based on axle box vibration acceleration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104260754B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105372080A (en) * | 2015-12-22 | 2016-03-02 | 成都市新筑路桥机械股份有限公司 | Tramcar, and embedded track coupling dynamics test device and method thereof |
| CN106840717A (en) * | 2017-01-15 | 2017-06-13 | 华东交通大学 | Train wheel method for testing vibration based on axle box acceleration electromagnetism interference |
| CN107264569A (en) * | 2017-06-15 | 2017-10-20 | 山东交通职业学院 | A kind of track quality state evaluation method and system |
| CN109034192A (en) * | 2018-06-20 | 2018-12-18 | 西南交通大学 | A kind of track based on deep learning-body oscillating trend prediction method |
| CN110789566A (en) * | 2019-11-11 | 2020-02-14 | 成都西交智众科技有限公司 | Track defect monitoring method and monitoring equipment based on axle box acceleration signal |
| CN111979859A (en) * | 2020-08-19 | 2020-11-24 | 中国铁道科学研究院集团有限公司 | Track irregularity detection system and method |
| CN112014593A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Device and method for monitoring and evaluating quality condition of railway track basic equipment |
| CN113358053A (en) * | 2021-04-27 | 2021-09-07 | 中车青岛四方机车车辆股份有限公司 | Track irregularity detection and evaluation system and method, electronic equipment and railway vehicle |
| CN114993461A (en) * | 2022-08-08 | 2022-09-02 | 成都久和建设设备有限责任公司 | System and method for detecting vibration of motor of tower crane mechanism |
| CN116307302A (en) * | 2023-05-23 | 2023-06-23 | 西南交通大学 | Inversion method, system and storage medium for track irregularity dynamic and static detection data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0253663A (en) * | 1988-08-12 | 1990-02-22 | Teito Kousokudo Kotsu Eidan | Parallel recording system for train oscillation data and track data |
| JPH08184426A (en) * | 1994-12-28 | 1996-07-16 | Hitachi Ltd | Misalignment detector for rail based on oscillatory acceleration of axle box |
| JP2001063570A (en) * | 1999-08-30 | 2001-03-13 | Railway Technical Res Inst | Track measuring device using inertial mid-chord offset method |
| US20040064235A1 (en) * | 2000-12-20 | 2004-04-01 | Cole Colin Robert | Vehicle dynamics production system and method |
| KR20110134547A (en) * | 2010-06-09 | 2011-12-15 | 한국철도기술연구원 | Rail irregularity measurement system using accelerometers and method thereof |
| CN102548828A (en) * | 2009-08-13 | 2012-07-04 | 代尔夫特工业大学 | Method and instrumentation for detection of rail defects, in particular rail top defects |
| CN102798458A (en) * | 2012-08-01 | 2012-11-28 | 北京铁科工程检测中心 | Low-frequency wireless accelerometer |
| CN102890143A (en) * | 2012-10-19 | 2013-01-23 | 西南交通大学 | Rail local defect vehicle-mounting detection method merging with vehicle speed information and front and rear axle box acceleration information |
| CN103332207A (en) * | 2013-06-11 | 2013-10-02 | 大连理工大学 | Method and device for on-line acquisition of steel rail temperature, strain and acceleration data |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
-
2014
- 2014-10-08 CN CN201410526294.1A patent/CN104260754B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0253663A (en) * | 1988-08-12 | 1990-02-22 | Teito Kousokudo Kotsu Eidan | Parallel recording system for train oscillation data and track data |
| JPH08184426A (en) * | 1994-12-28 | 1996-07-16 | Hitachi Ltd | Misalignment detector for rail based on oscillatory acceleration of axle box |
| JP2001063570A (en) * | 1999-08-30 | 2001-03-13 | Railway Technical Res Inst | Track measuring device using inertial mid-chord offset method |
| US20040064235A1 (en) * | 2000-12-20 | 2004-04-01 | Cole Colin Robert | Vehicle dynamics production system and method |
| CN102548828A (en) * | 2009-08-13 | 2012-07-04 | 代尔夫特工业大学 | Method and instrumentation for detection of rail defects, in particular rail top defects |
| KR20110134547A (en) * | 2010-06-09 | 2011-12-15 | 한국철도기술연구원 | Rail irregularity measurement system using accelerometers and method thereof |
| CN102798458A (en) * | 2012-08-01 | 2012-11-28 | 北京铁科工程检测中心 | Low-frequency wireless accelerometer |
| CN102890143A (en) * | 2012-10-19 | 2013-01-23 | 西南交通大学 | Rail local defect vehicle-mounting detection method merging with vehicle speed information and front and rear axle box acceleration information |
| CN103332207A (en) * | 2013-06-11 | 2013-10-02 | 大连理工大学 | Method and device for on-line acquisition of steel rail temperature, strain and acceleration data |
| CN104228872A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Portable track irregularity online monitoring device and method |
Non-Patent Citations (1)
| Title |
|---|
| 张伟: "基于轴箱谱的轨道短波不平顺识别方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105372080A (en) * | 2015-12-22 | 2016-03-02 | 成都市新筑路桥机械股份有限公司 | Tramcar, and embedded track coupling dynamics test device and method thereof |
| CN106840717B (en) * | 2017-01-15 | 2024-03-29 | 华东交通大学 | Train wheel vibration testing method based on axle box acceleration electromagnetic interference resistance |
| CN106840717A (en) * | 2017-01-15 | 2017-06-13 | 华东交通大学 | Train wheel method for testing vibration based on axle box acceleration electromagnetism interference |
| CN107264569A (en) * | 2017-06-15 | 2017-10-20 | 山东交通职业学院 | A kind of track quality state evaluation method and system |
| CN109034192A (en) * | 2018-06-20 | 2018-12-18 | 西南交通大学 | A kind of track based on deep learning-body oscillating trend prediction method |
| CN109034192B (en) * | 2018-06-20 | 2022-03-08 | 西南交通大学 | Track-vehicle body vibration state prediction method based on deep learning |
| CN112014593A (en) * | 2019-05-28 | 2020-12-01 | 浙江德盛铁路器材股份有限公司 | Device and method for monitoring and evaluating quality condition of railway track basic equipment |
| CN110789566A (en) * | 2019-11-11 | 2020-02-14 | 成都西交智众科技有限公司 | Track defect monitoring method and monitoring equipment based on axle box acceleration signal |
| CN110789566B (en) * | 2019-11-11 | 2021-01-12 | 成都西交智众科技有限公司 | Track defect monitoring method and monitoring equipment based on axle box acceleration signal |
| CN111979859A (en) * | 2020-08-19 | 2020-11-24 | 中国铁道科学研究院集团有限公司 | Track irregularity detection system and method |
| CN111979859B (en) * | 2020-08-19 | 2022-03-11 | 中国铁道科学研究院集团有限公司 | Track irregularity detection system and method |
| CN113358053A (en) * | 2021-04-27 | 2021-09-07 | 中车青岛四方机车车辆股份有限公司 | Track irregularity detection and evaluation system and method, electronic equipment and railway vehicle |
| CN113358053B (en) * | 2021-04-27 | 2023-02-24 | 中车青岛四方机车车辆股份有限公司 | Track irregularity detection and evaluation system and method, electronic equipment and track vehicle |
| CN114993461B (en) * | 2022-08-08 | 2022-11-04 | 成都久和建设设备有限责任公司 | System and method for detecting vibration of motor of tower crane mechanism |
| CN114993461A (en) * | 2022-08-08 | 2022-09-02 | 成都久和建设设备有限责任公司 | System and method for detecting vibration of motor of tower crane mechanism |
| CN116307302A (en) * | 2023-05-23 | 2023-06-23 | 西南交通大学 | Inversion method, system and storage medium for track irregularity dynamic and static detection data |
| CN116307302B (en) * | 2023-05-23 | 2023-07-25 | 西南交通大学 | Inversion method, system and storage medium for track irregularity dynamic and static detection data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104260754B (en) | 2017-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104260754B (en) | Track transition forecasting system and method based on axle box vibration acceleration | |
| Shao et al. | Modified stacked autoencoder using adaptive Morlet wavelet for intelligent fault diagnosis of rotating machinery | |
| CN103901882B (en) | A kind of system and method for train dynamics system on-line monitoring fault diagnosis | |
| Zou et al. | Bearing fault diagnosis method based on EEMD and LSTM | |
| CN108489719B (en) | A kind of combined failure of rotating machinery diagnostic method based on the unusual spectral factorization of G-P | |
| CN109858104A (en) | A kind of rolling bearing health evaluating and method for diagnosing faults and monitoring system | |
| CN114109859B (en) | Centrifugal pump performance neural network prediction method without flow sensing | |
| CN102521604B (en) | Device and method for estimating performance degradation of equipment based on inspection system | |
| CN114239377A (en) | Method and system for evaluating health state of urban rail electromechanical equipment and storage medium | |
| CN113609608A (en) | Train traction motor bearing full life cycle management method based on digital twinning | |
| CN111878322B (en) | Wind power generator device | |
| CN111071291A (en) | Train wheel set monitoring system and train wheel set monitoring method | |
| CN109919511B (en) | Existing railway line shape evaluation method and system | |
| CN116796644A (en) | Wind farm parameter identification method based on multi-agent SAC deep reinforcement learning | |
| CN106656669A (en) | Equipment parameter abnormity detection system and method based on self-adaptive setting of threshold | |
| CN111695201A (en) | Data-based monitoring method for running state of magnetic-levitation train | |
| Xie et al. | A data-driven convolutional regression scheme for on-board and quantitative detection of rail corrugation roughness | |
| CN116593159A (en) | Combined bearing fault diagnosis method and system | |
| CN107849904A (en) | Movement overseas compensation winch real-time performance monitoring and prediction | |
| Wang et al. | Wavelet packet transform-assisted least squares support vector machine for gear wear degree diagnosis | |
| CN113625104B (en) | Line length correction method for traveling wave fault location | |
| CN115062867A (en) | Bearing fault prediction method based on Teager energy spectrum and improved CNN model | |
| CN113109666B (en) | Rail circuit fault diagnosis method based on deep convolutional neural network | |
| CN107884617A (en) | A kind of rail vehicle interference electric current test device and rail vehicle | |
| CN103713619A (en) | Test method for ore grinding process operation control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210113 Address after: 210046 room 296, No.1 Tianzuo Road, Sheshan Xingcheng, Xigang street, Qixia District, Nanjing City, Jiangsu Province Patentee after: Nanjing hangxuan Rail Transit Technology Co.,Ltd. Address before: 210094 No. 200, Xiaolingwei, Jiangsu, Nanjing Patentee before: NANJING University OF SCIENCE AND TECHNOLOGY |