CN104502126A - Modal intervals-based high-speed train bogie fault diagnosis method - Google Patents
Modal intervals-based high-speed train bogie fault diagnosis method Download PDFInfo
- Publication number
- CN104502126A CN104502126A CN201410826118.XA CN201410826118A CN104502126A CN 104502126 A CN104502126 A CN 104502126A CN 201410826118 A CN201410826118 A CN 201410826118A CN 104502126 A CN104502126 A CN 104502126A
- Authority
- CN
- China
- Prior art keywords
- speed train
- vibration signal
- train bogie
- modal intervals
- bogie
- 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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
A modal intervals-based high-speed train bogie fault diagnosis method includes the steps of 1, acquiring a high-speed train bogie vibration signal; 2, preprocessing the high-speed train bogie vibration signal; 3, subjecting the high-speed train bogie vibration signal to modal interval valuing; 4, subjecting the high-speed train bogie vibration signal to EMD (experience modal decomposition); 5, subjecting the high-speed train bogie vibration signal to feature extraction; 6, constructing and training an initial interval neural network model; and 7, performing high-speed train bogie fault diagnosis. Uncertainty in bogie vibration signals is processed by the modal interval method, and high-speed train bogie faults are diagnosed by a classified recognition method of the interval neural network model; the uncertainty in the high-speed train bogie fault diagnosis is handled by the modal interval method, and reliability of fault diagnosis results is greatly improved. The method is applicable to the fault diagnosis for high-speed train bogies.
Description
Technical field
The present invention relates to bullet train fault diagnosis field, particularly the method for diagnosing faults of high-speed train bogie.
Background technology
Bogie takes on the task of guiding, carrying, vibration damping in bullet train runs, and is also traction simultaneously and brakes final executor, is bullet train critical component.Bogie bullet train operation due in subject Random dynamic loads frequently, the key position of bogie structure part may be caused to occur various fault, and the appearance of fault can cause the vibration aggravation of bullet train each position, riding quality declines, derailing overturning even can be caused to wait major accident.Therefore carry out high-speed train bogie Performance Detection and fault diagnosis research, the operation safe and reliable to bullet train is significant.
Conventional high-speed train bogie method for diagnosing faults is: obtain bogie vibration sensing signal by sensor, obtain bogie fault characteristic value by time frequency analysis, last application class model of cognition is to bogie diagnosing malfunction.This conventional method, from the extraction getting characteristic quantity of bogie fault-signal and to last failure modes, is all that the basis based on exact value is carried out.Due to uncertainty and the contingency of influence factor change various in the complicacy of high-speed train bogie structure, running status, typotron vibration measurement result will be caused to have uncertainty and randomness equally, traditional diagnostic model method is seldom carried out corresponding to these uncertain problems, and this reduces causing the reliability of diagnostic result.
Modal Intervals is theoretical as one of effective handling implement of uncertain problem, Joaquim has carried out detailed elaboration in " Applicationof Modal Interval Analysis to the Simulation of the Behavior of Dynamic Systemswith Uncertain Parameters ": its application Modal Intervals is to process in engineering due to small sample, historical data is incomplete, randomness, the uncertain problem that priori scarcity waits and formed, Uncertainty is converted to Modal Intervals, quantization uncertainty size is carried out by the width of Modal Intervals.Uncertainty Analysis Method based on Modal Intervals considers uncertain problem, and the result of Modal Intervals form comprises, and quantity of information is abundanter, confidence level is higher.By theoretical for Modal Intervals with solving the uncertain problem related in bullet train fault diagnosis, the reliability of bogie fault diagnosis result can be improved.
Summary of the invention
The object of the invention is the uncertain problem for existing in high-speed train bogie fault diagnosis, a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals is provided.
Realize the concrete technical scheme that object of the present invention adopts as follows:
A kind of high-speed train bogie method for diagnosing faults based on Modal Intervals, utilize the uncertain problem existed in Modal Intervals theoretical treatment diagnostic procedure, extract fault characteristic information by empirical mode decomposition (EMD), by the recognition methods of Interval neural networks category of model, reliable diagnosis is carried out to high-speed train bogie fault.The inventive method concrete steps are as follows:
(1) high-speed train bogie vibration signal obtains
Utilize survey instrument to obtain high-speed train bogie vibration signal, and be stored in computing machine by the information of data collecting card by acquisition.Wherein vibration signal can be the arbitrary class in the signals such as power, acceleration, displacement and moment of torsion, and the survey instrument corresponding with vibration signal is dynamometer, acceleration transducer, displacement transducer and torque sensor etc.
(2) high-speed train bogie vibration signal pre-service
The vibration signal of the high-speed train bogie collected is carried out wavelet packet threshold filter, and stress release treatment disturbs, and forms the high-speed train bogie vibration signal x without making an uproar
jt (), wherein t is the signals collecting corresponding moment, and x is collection signal amplitude, and j is any in the middle survey instrument of vibration signal correspondence (1).
(3) high-speed train bogie vibration signal Modal Intervals
Consider the uncertain problem in high-speed train bogie vibration measurement and process of data preprocessing, the theoretical and theory of errors according to Modal Intervals, by pretreated vibrate signal x
jt () converts Modal Intervals form x to
j(t),
to increase the reliability of the vibration signal got.Wherein
x jt () is vibration signal lower bound,
for the vibration signal upper bound.
The mathematical definition of Modal Intervals x is:
Namely Modal Intervals x is by a pair real number
x,
define,
xfor lower bound,
for the upper bound, kR represents the real number set of mode closed interval, and the x in formula is not subject to
any constraint, namely in Modal Intervals, bound size is unrestricted, if classical interval can only be [2,5], can not be [5,2], but Modal Intervals is unrestricted, and two intervals are all licenses.Modal Intervals mathematical operation theoretical foundation is Kaucher algorithm.
(4) high-speed train bogie vibration signal EMD decomposes
Respectively EMD decomposition is carried out to lower bound vibration signal and upper bound vibration signal, obtain vibration signal lower bound intrinsic mode function (IMF)
c(t) and vibration signal lower bound
(5) high-speed train bogie vibration signal characteristics extracts
Bound IMF after vibration signal EMD decomposes is screened, selects the bound IMF of characteristic remarkable, and calculate the energy square of lower bound IMF respectively
e i,
with the energy square of upper bound IMF
wherein Δ t is sampling interval, and n is total sample number, and i is i-th IMF corresponding after EMD decomposes.And respectively bound energy square is normalized, wherein lower bound energy square method for normalizing is
upper bound energy square method for normalizing is
upper and lower energy square is combined into Modal Intervals proper vector T,
as the input of subsequent classification model.
(6) build and train neural network model between original area
According to Modal Intervals proper vector and high-speed train bogie fault performance kind, build neural network model between original area, and bogie fault performance kind is encoded, form Interval neural networks ideal and export target.According to Interval neural networks model learning method, by the part of vibrate signal proper vector T extracted described in (5) as training sample, gradient descent method is adopted to train neural network model between original area, until between original area till neural network model parameter optimization.
Wherein, Interval neural networks is the popularization of classical neural network, and it is theoretical according to Modal Intervals by the parameter of classical neural network, changes in order to Modal Intervals form.
(7) high-speed train bogie fault diagnosis
Using the residue vibrate signal proper vector T that extracts as test sample book, in Interval neural networks model after input optimization, computation interval neural network model Output rusults, the result obtained utilizes Modal Intervals size to compare rule and compares, and Modal Intervals maximal value correspondence coding place state is bogie fault diagnosis result.
The present invention is compared with existing high-speed train bogie fault diagnosis technology, propose the uncertain row problem processed by Modal Intervals method in vibrate signal, and utilize the classifying identification method of Interval neural networks model to high-speed train bogie diagnosing malfunction.Because it passes through the uncertain problem in method process of Modal Intervals high-speed train bogie fault diagnosis, will the reliability of fault diagnosis result be improved, there is following advantage specifically:
1) Uncertainty in the vibrate signal of acquisition is converted to Modal Intervals form, obtained the uncertain problem existed in signal by Modal Intervals theoretical treatment, effectively can solve the numerical value uncertain problem in bogie fault diagnosis in mode input;
2) using the vibrate signal energy square via Modal Intervals theoretical treatment as proper vector, between application area, neural network model classifying identification method carries out fault diagnosis to bogie, because the uncertain problem in diagnostic procedure obtains effective process, the reliability of high-speed train bogie fault diagnosis result will be improved.
The inventive method is suitable for the fault diagnosis of high-speed train bogie.
Accompanying drawing explanation
Fig. 1 is the FB(flow block) of the high-speed train bogie method for diagnosing faults embodiment that the present invention is based on Modal Intervals;
Fig. 2 is the high-speed train bogie fault diagnosis flow scheme block diagram based on Modal Intervals in the embodiment of the present invention.
Embodiment
The present invention will by be further described high-speed train bogie fault diagnosis embodiment.
(1) high-speed train bogie acceleration signal obtains
Survey instrument is utilized to obtain high-speed train bogie vibration signal, and by data collecting card, the information of acquisition is stored in computing machine, wherein vibration signal can power, acceleration, an arbitrary class in the signal such as displacement and moment of torsion, and the survey instrument corresponding with vibration signal is dynamometer, acceleration transducer, displacement transducer and torque sensor etc.
The preferred survey instrument of the present embodiment is acceleration transducer, obtains vibrate signal by acceleration transducer.
(2) high-speed train bogie acceleration signal pre-service
The vibration signal of the train bogie collected is carried out wavelet packet threshold filter, and stress release treatment disturbs, and forms the high-speed train bogie vibration signal x without making an uproar
jt (), wherein t is the signals collecting corresponding moment, and x is collection signal amplitude, and j is any in the middle survey instrument of vibration signal correspondence (1).
The survey instrument that the present embodiment is selected is acceleration transducer, and what obtain after pre-service is acceleration signal x (t) without vibration signal of making an uproar.
(3) high-speed train bogie acceleration signal Modal Intervals
Consider the uncertain problem in the measurement of high-speed train bogie acceleration signal and process of data preprocessing, theoretical and the theory of errors according to Modal Intervals, convert pretreated bogie acceleration signal x (t) to Modal Intervals form x (t)
to increase the reliability of the acceleration signal got.Wherein
xt () is acceleration signal lower bound,
for the acceleration signal upper bound.
The mathematical definition of Modal Intervals x is:
Namely Modal Intervals x is by a pair real number
x,
define,
xfor lower bound,
for the upper bound, kR represents the real number set of mode closed interval, and the x in formula is not subject to
any constraint, namely in Modal Intervals, bound size is unrestricted, if classical interval can only be [2,5], can not be [5,2], but Modal Intervals is unrestricted, and two intervals are all licenses.Modal Intervals mathematical operation theoretical foundation is Kaucher algorithm.
(4) high-speed train bogie acceleration signal EMD decomposes
Respectively to lower bound acceleration signal
x(t) and upper bound acceleration signal
carry out EMD decomposition, obtain acceleration signal lower bound intrinsic mode function (IMF)
c(t) and acceleration signal lower bound
(5) high-speed train bogie acceleration signal feature extraction
Bound IMF after acceleration signal EMD decomposes is screened, selects the bound IMF of characteristic remarkable, and calculate the energy square of lower bound IMF respectively
e i,
with the energy square of upper bound IMF
wherein Δ t is sampling interval, and n is total sample number, and i is i-th IMF corresponding after EMD decomposes.And respectively bound energy square is normalized, wherein lower bound energy square method for normalizing is
upper bound energy square method for normalizing is
upper and lower energy square is combined into Modal Intervals proper vector T,
as the input of subsequent classification model.
(6) build and train neural network model between original area
According to Modal Intervals proper vector and high-speed train bogie fault performance kind, build neural network model between original area.In the present embodiment, assuming that the bogie number of faults needing diagnosis is 4 kinds, comprise wheel tread damage, anti-snakelike defective shock absorber, lateral damper lost efficacy and air spring loses gas, to each fault preferred 9 Modal Intervals characteristic quantities from proper vector T, thus composition matrix be 9 × 3 original area between neural network model.4 kinds of high-speed train bogie faults are encoded simultaneously, the ideal forming Interval neural networks exports target, wherein wheel tread damage is encoded to ([1,1] [0,0] [0,0] [0,0]), anti-snakelike defective shock absorber is encoded to ([0,0] [1,1] [0,0] [0,0]), lateral damper lost efficacy and was encoded to ([0,0] [0,0] [1,1] [0,0]) and air spring lose gas be encoded to ([0,0] [0,0] [0,0] [1,1]).According to Interval neural networks model learning method, by the part of bogie acceleration signal characteristic vector T extracted described in (5) as training sample, gradient descent method is adopted to train neural network model between original area, until between original area till neural network model parameter optimization.
Wherein, Interval neural networks is the popularization of classical neural network, and it is theoretical according to Modal Intervals by the parameter of classical neural network, changes in order to Modal Intervals form.
(7) high-speed train bogie fault diagnosis
Using the residue bogie acceleration signal characteristic vector T that extracts as test sample book, Interval neural networks model after input optimization, computation interval neural network model Output rusults, the result obtained utilizes Modal Intervals size to compare rule and compares, and Modal Intervals maximal value correspondence coding place state is bogie fault diagnosis result.
Above-described embodiment is only a preferred scheme of the inventive method, but method of the present invention is not limited to it turns to fault diagnosis to bullet train, all applicable to the fault diagnosis of other bullet train upper member.
Claims (8)
1. the high-speed train bogie method for diagnosing faults based on Modal Intervals, it is characterized in that, described method utilizes the uncertain problem existed in Modal Intervals theoretical treatment diagnostic procedure, extract fault characteristic information by empirical mode decomposition, by the recognition methods of Interval neural networks category of model, reliable diagnosis is carried out to high-speed train bogie fault; Described method specifically comprises the steps:
(1) high-speed train bogie vibration signal obtains;
(2) high-speed train bogie vibration signal pre-service;
(3) high-speed train bogie vibration signal Modal Intervals;
(4) high-speed train bogie vibration signal EMD decomposes;
(5) high-speed train bogie vibration signal characteristics extracts;
(6) build and train neural network model between original area;
(7) high-speed train bogie fault diagnosis.
2. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, during described high-speed train bogie vibration signal obtains, vibration signal can be the arbitrary class in power, acceleration, displacement and torque signal, and the survey instrument corresponding with vibration signal is dynamometer, acceleration transducer, displacement transducer and torque sensor.
3. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, the pre-service of described high-speed train bogie vibration signal, the vibration signal of the high-speed train bogie collected is carried out wavelet packet threshold filter, stress release treatment disturbs, and forms the high-speed train bogie vibration signal x without making an uproar
jt (), wherein t is the signals collecting corresponding moment, and x is collection signal amplitude, and j is any in vibration signal corresponding dynamometer, acceleration transducer, displacement transducer and torque sensor.
4. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, is characterized in that, described high-speed train bogie vibration signal Modal Intervals, by pretreated vibrate signal x
jt () converts Modal Intervals form x to
j(t),
to increase the reliability of the vibration signal got;
Wherein
x jt () is vibration signal lower bound,
for the vibration signal upper bound.
5. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, described high-speed train bogie vibration signal EMD decomposes, namely respectively EMD decomposition is carried out to lower bound vibration signal and upper bound vibration signal, obtain vibration signal lower bound intrinsic mode function (IMF)
c(t) and vibration signal lower bound
6. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, high-speed train bogie vibration signal characteristics extracts, and screens the bound IMF after vibration signal EMD decomposes, select the bound IMF of characteristic remarkable
And calculate the energy square of lower bound IMF respectively
e i,
with the energy square of upper bound IMF
Wherein Δ t is sampling interval, and n is total sample number, and i is i-th IMF corresponding after EMD decomposes; And respectively bound energy square is normalized, wherein lower bound energy square method for normalizing is
upper bound energy square method for normalizing is
upper and lower energy square is combined into Modal Intervals proper vector T,
as the input of subsequent classification model.
7. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, described structure and training original area between neural network model, using a part of vibrate signal proper vector T as training sample, gradient descent method is adopted to train neural network model between original area, until between original area till neural network model parameter optimization.
8. a kind of high-speed train bogie method for diagnosing faults based on Modal Intervals according to claim 1, it is characterized in that, described high-speed train bogie fault diagnosis, using the residue vibrate signal proper vector T that extracts as test sample book, in Interval neural networks model after input optimization, computation interval neural network model Output rusults, the result obtained utilizes Modal Intervals size to compare rule and compares, and Modal Intervals maximal value correspondence coding place state is bogie fault diagnosis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410826118.XA CN104502126B (en) | 2014-12-28 | 2014-12-28 | A kind of high-speed train bogie method for diagnosing faults based on Modal Intervals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410826118.XA CN104502126B (en) | 2014-12-28 | 2014-12-28 | A kind of high-speed train bogie method for diagnosing faults based on Modal Intervals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104502126A true CN104502126A (en) | 2015-04-08 |
CN104502126B CN104502126B (en) | 2017-08-15 |
Family
ID=52943546
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410826118.XA Expired - Fee Related CN104502126B (en) | 2014-12-28 | 2014-12-28 | A kind of high-speed train bogie method for diagnosing faults based on Modal Intervals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104502126B (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105022921A (en) * | 2015-07-14 | 2015-11-04 | 福州大学 | Fuzzy system reliability design method in combination with modal interval algorithm |
CN105141282A (en) * | 2015-07-30 | 2015-12-09 | 株洲南车时代电气股份有限公司 | Vibration signal filtering device and method for high-speed train unstability detection |
CN105403420A (en) * | 2015-12-15 | 2016-03-16 | 广州地铁集团有限公司 | Bogie fault diagnosis method integrated with multiple sensors |
CN105628403A (en) * | 2016-03-14 | 2016-06-01 | 重庆工商大学 | Damper fault detection method and system |
CN106017879A (en) * | 2016-05-18 | 2016-10-12 | 河北工业大学 | Universal circuit breaker mechanical fault diagnosis method based on feature fusion of vibration and sound signals |
CN106441946A (en) * | 2016-11-15 | 2017-02-22 | 重庆工商大学 | Fault recognition method and fault recognition system for hydraulic shock absorber of vehicle based on vibration signal |
CN107862152A (en) * | 2017-11-20 | 2018-03-30 | 中车株洲电力机车有限公司 | The nonlinear Design of Structural parameters method for resisting snakelike shock absorber |
CN109163913A (en) * | 2018-09-30 | 2019-01-08 | 深圳市元征科技股份有限公司 | A kind of Diagnosis method of automobile faults and relevant device |
CN109946389A (en) * | 2019-01-31 | 2019-06-28 | 青岛理工大学 | Damage Detection of Structures based on overall experience mode decomposition and convolutional neural networks |
CN110084185A (en) * | 2019-04-25 | 2019-08-02 | 西南交通大学 | A kind of bullet train slightly crawls the rapid extracting method of operation characteristic |
CN111208436A (en) * | 2020-02-21 | 2020-05-29 | 河海大学 | Energy storage battery overcharge diagnosis method based on IMF energy moment and genetic algorithm optimization SVM |
CN111753927A (en) * | 2020-07-22 | 2020-10-09 | 华东交通大学 | Method for identifying crack fault state of locomotive traction seat |
CN111814404A (en) * | 2020-07-22 | 2020-10-23 | 华东交通大学 | Locomotive bogie bolt loosening fault detection method |
CN112464152A (en) * | 2020-11-04 | 2021-03-09 | 中国计量大学 | Vehicle electromagnetic valve fault diagnosis method based on wavelet neural network |
CN112498413A (en) * | 2019-09-13 | 2021-03-16 | 纳博特斯克有限公司 | Railway condition monitoring device, railway vehicle bogie, railway vehicle, and railway brake control device |
CN114397121A (en) * | 2022-01-21 | 2022-04-26 | 西南交通大学 | Bogie fault diagnosis method |
CN114781450A (en) * | 2022-04-24 | 2022-07-22 | 华东交通大学 | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN |
CN117347054A (en) * | 2023-12-01 | 2024-01-05 | 华东交通大学 | Motor bearing fault diagnosis method, system, computer and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009294147A (en) * | 2008-06-06 | 2009-12-17 | Tokyu Car Corp | Method of detecting abnormality of moving body |
CN202200999U (en) * | 2011-07-12 | 2012-04-25 | 北京瑞航威尔科技有限公司 | Device for monitoring and diagnosing bogie |
CN103018046A (en) * | 2012-12-13 | 2013-04-03 | 唐山轨道客车有限责任公司 | Method, device and system for monitoring high-speed electric multiple unit train bogie bearing faults |
US20130261879A1 (en) * | 2012-04-03 | 2013-10-03 | Institute For Information Industry | Method and System for Diagnosing Breakdown Cause of Vehicle and Computer Readable Storage Medium Storing the Method |
CN103914617A (en) * | 2014-03-25 | 2014-07-09 | 北京交通大学 | Fault diagnosis method for subway vehicle bogie bearings |
CN103984865A (en) * | 2014-05-19 | 2014-08-13 | 华东交通大学 | Bearing temperature rise prediction method based on interval time sequence |
CN104236911A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Train bogie bearing service process monitoring and fault diagnosis system and method |
-
2014
- 2014-12-28 CN CN201410826118.XA patent/CN104502126B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009294147A (en) * | 2008-06-06 | 2009-12-17 | Tokyu Car Corp | Method of detecting abnormality of moving body |
CN202200999U (en) * | 2011-07-12 | 2012-04-25 | 北京瑞航威尔科技有限公司 | Device for monitoring and diagnosing bogie |
US20130261879A1 (en) * | 2012-04-03 | 2013-10-03 | Institute For Information Industry | Method and System for Diagnosing Breakdown Cause of Vehicle and Computer Readable Storage Medium Storing the Method |
CN103018046A (en) * | 2012-12-13 | 2013-04-03 | 唐山轨道客车有限责任公司 | Method, device and system for monitoring high-speed electric multiple unit train bogie bearing faults |
CN103914617A (en) * | 2014-03-25 | 2014-07-09 | 北京交通大学 | Fault diagnosis method for subway vehicle bogie bearings |
CN103984865A (en) * | 2014-05-19 | 2014-08-13 | 华东交通大学 | Bearing temperature rise prediction method based on interval time sequence |
CN104236911A (en) * | 2014-09-28 | 2014-12-24 | 江苏润仪仪表有限公司 | Train bogie bearing service process monitoring and fault diagnosis system and method |
Non-Patent Citations (4)
Title |
---|
何晓峰: "基于模态区间方法的不确定参数***动力特征值的算法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
杨鑫: "列车转向架轴承服役过程监测与故障诊断***研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
樊久铭 等: "模态区间分析在具有不确定性参数***故障诊断中的应用", 《汽轮机技术》 * |
翟冰 等: "基于EEMD和球SVM的高速列车转向架故障估计", 《计算机测量与控制》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105022921A (en) * | 2015-07-14 | 2015-11-04 | 福州大学 | Fuzzy system reliability design method in combination with modal interval algorithm |
CN105022921B (en) * | 2015-07-14 | 2018-02-09 | 福州大学 | With reference to the fuzzy system reliability design approach of Modal Intervals algorithm |
CN105141282A (en) * | 2015-07-30 | 2015-12-09 | 株洲南车时代电气股份有限公司 | Vibration signal filtering device and method for high-speed train unstability detection |
CN105141282B (en) * | 2015-07-30 | 2017-10-31 | 株洲南车时代电气股份有限公司 | The filter and method of vibration signal in a kind of detection for bullet train unstability |
CN105403420A (en) * | 2015-12-15 | 2016-03-16 | 广州地铁集团有限公司 | Bogie fault diagnosis method integrated with multiple sensors |
CN105403420B (en) * | 2015-12-15 | 2018-02-09 | 广州地铁集团有限公司 | A kind of bogie method for diagnosing faults for merging multisensor |
CN105628403A (en) * | 2016-03-14 | 2016-06-01 | 重庆工商大学 | Damper fault detection method and system |
CN106017879A (en) * | 2016-05-18 | 2016-10-12 | 河北工业大学 | Universal circuit breaker mechanical fault diagnosis method based on feature fusion of vibration and sound signals |
CN106017879B (en) * | 2016-05-18 | 2018-07-03 | 河北工业大学 | Omnipotent breaker mechanical failure diagnostic method based on acoustic signal Fusion Features |
CN106441946A (en) * | 2016-11-15 | 2017-02-22 | 重庆工商大学 | Fault recognition method and fault recognition system for hydraulic shock absorber of vehicle based on vibration signal |
CN106441946B (en) * | 2016-11-15 | 2018-10-19 | 重庆工商大学 | Vehicle hydraulic damper fault recognition method based on vibration signal and system |
CN107862152A (en) * | 2017-11-20 | 2018-03-30 | 中车株洲电力机车有限公司 | The nonlinear Design of Structural parameters method for resisting snakelike shock absorber |
CN109163913A (en) * | 2018-09-30 | 2019-01-08 | 深圳市元征科技股份有限公司 | A kind of Diagnosis method of automobile faults and relevant device |
CN109163913B (en) * | 2018-09-30 | 2021-02-09 | 深圳市元征科技股份有限公司 | Automobile fault diagnosis method and related equipment |
CN109946389A (en) * | 2019-01-31 | 2019-06-28 | 青岛理工大学 | Damage Detection of Structures based on overall experience mode decomposition and convolutional neural networks |
CN110084185A (en) * | 2019-04-25 | 2019-08-02 | 西南交通大学 | A kind of bullet train slightly crawls the rapid extracting method of operation characteristic |
CN110084185B (en) * | 2019-04-25 | 2021-03-16 | 西南交通大学 | Method for rapidly extracting small-amplitude snaking operation characteristics of high-speed train |
CN112498413A (en) * | 2019-09-13 | 2021-03-16 | 纳博特斯克有限公司 | Railway condition monitoring device, railway vehicle bogie, railway vehicle, and railway brake control device |
CN111208436A (en) * | 2020-02-21 | 2020-05-29 | 河海大学 | Energy storage battery overcharge diagnosis method based on IMF energy moment and genetic algorithm optimization SVM |
CN111753927A (en) * | 2020-07-22 | 2020-10-09 | 华东交通大学 | Method for identifying crack fault state of locomotive traction seat |
CN111814404A (en) * | 2020-07-22 | 2020-10-23 | 华东交通大学 | Locomotive bogie bolt loosening fault detection method |
CN112464152A (en) * | 2020-11-04 | 2021-03-09 | 中国计量大学 | Vehicle electromagnetic valve fault diagnosis method based on wavelet neural network |
CN114397121A (en) * | 2022-01-21 | 2022-04-26 | 西南交通大学 | Bogie fault diagnosis method |
CN114781450A (en) * | 2022-04-24 | 2022-07-22 | 华东交通大学 | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN |
CN114781450B (en) * | 2022-04-24 | 2024-03-29 | 华东交通大学 | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN |
CN117347054A (en) * | 2023-12-01 | 2024-01-05 | 华东交通大学 | Motor bearing fault diagnosis method, system, computer and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104502126B (en) | 2017-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104502126A (en) | Modal intervals-based high-speed train bogie fault diagnosis method | |
CN109612708B (en) | Power transformer on-line detection system and method based on improved convolutional neural network | |
Han et al. | Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis | |
CN106441946B (en) | Vehicle hydraulic damper fault recognition method based on vibration signal and system | |
CN100485342C (en) | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault | |
CN110261109B (en) | Rolling bearing fault diagnosis method based on bidirectional memory cyclic neural network | |
CN103335617B (en) | A kind of railway track geometric deformation detection method based on vibration signal | |
CN105973595A (en) | Diagnosis method of rolling bearing fault | |
CN103728551B (en) | A kind of analog-circuit fault diagnosis method based on cascade integrated classifier | |
CN105760839A (en) | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine | |
CN106326929B (en) | The diagnostic method of track train EEF bogie rolling bearing fault | |
CN104819846A (en) | Rolling bearing sound signal fault diagnosis method based on short-time Fourier transform and sparse laminated automatic encoder | |
CN109612729A (en) | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings | |
CN104729853A (en) | Rolling bearing performance degradation evaluation device and method | |
CN113188807B (en) | Automatic abs result judging algorithm | |
CN106197999A (en) | A kind of planetary gear method for diagnosing faults | |
CN105424366A (en) | Bearing fault diagnosis method based on EEMD adaptive denoising | |
CN103471865A (en) | Train suspension system failure isolation method based on LDA method | |
CN105022912A (en) | Rolling bearing fault prediction method based on wavelet principal component analysis | |
CN104316167B (en) | Structural response method for detecting abnormality under a kind of low signal-to-noise ratio | |
CN107403139A (en) | A kind of municipal rail train wheel flat fault detection method | |
CN108664673A (en) | A kind of wheel rail force load identification feature-based data model method for building up and device | |
CN110608884A (en) | Rolling bearing state diagnosis method based on self-attention neural network | |
CN105626502A (en) | Plunger pump health assessment method based on wavelet packet and Laplacian Eigenmap | |
CN105160359A (en) | Complex structure damage cooperative identification method based on ultrasonic guided-wave |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170815 Termination date: 20171228 |