CN104236933B - A kind of potential faults method for early warning for train traction system - Google Patents
A kind of potential faults method for early warning for train traction system Download PDFInfo
- Publication number
- CN104236933B CN104236933B CN201310234151.9A CN201310234151A CN104236933B CN 104236933 B CN104236933 B CN 104236933B CN 201310234151 A CN201310234151 A CN 201310234151A CN 104236933 B CN104236933 B CN 104236933B
- Authority
- CN
- China
- Prior art keywords
- hidden danger
- potential faults
- early warning
- train traction
- traction system
- 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.)
- Expired - Fee Related
Links
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The present invention relates to a kind of potential faults method for early warning for train traction system, comprise the following steps：1) real-time running data of train traction system is gathered by sensor, and carries out Multi-sensor Fusion, obtains service data set；2) after being pre-processed to the data in service data set, its hidden danger characteristic value is extracted；3) by hidden danger eigenvalue cluster into hidden danger characteristic vector, the running status of trailer system is characterized；4) hidden danger characteristic vector is handled by fuzzy algorithmic approach, obtains the variation tendency of potential faults；5) chart or curve exporting change trend are used, carries out the early warning of potential faults.Compared with prior art, data compaction of the present invention, accuracy is high, can effectively improve the traffic safety of train.
Description
Technical field
It is hidden more particularly, to a kind of failure for train traction system the present invention relates to a kind of potential faults method for early warning
Suffer from method for early warning.
Background technology
In recent years, urban rail transit in China is greatly developed, and operation mileage and construction mileage constantly increase.Modern subway
Structure becomes increasingly complex, and function is more and more perfect, but with automaticity more and more higher, causes railcar to break down
Probability constantly raises, and fault type complexity is various.One of municipal rail train traction drive train critical system, while be also each
The multiple part of kind electricapparatus failure.
Train traction system main circuit using two level voltage types it is straight-hand over inverter circuit, flowed through OCS and pantograph,
The DC1500V direct currents of input are transformed into the adjustable three-phase alternating current of frequency, voltage by VVVF inverters, to asynchronous traction electricity
Motivation is powered.Electric traction system is by High-Voltage Electrical Appliances, capacitor charging/discharging unit, filter unit, copped wave and Overvoltage suppressing list
Member, inverter unit, asynchronous traction motor and detection unit etc. form.During actual motion, because train is led
Draw system device complexity, the site environment that train is run in addition is severe, and there is a series of potential faults.Tradition is conventional
Detection method be that the data directly measured for sensor need to carry out some signal transactings just to obtain including in data
Characteristic information, commonly use the technological means such as Fourier transformation.But, can not be for these technological means are just for fault diagnosis
Early warning is made to the component potential faults of trailer system before failure generation.Do and be out of order after component hinders damage for some reason
It is extremely disadvantageous to diagnose this safety to driving, or even can threaten the safety of driving.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind is directed to train traction
The potential faults method for early warning of system, the data compaction of this method, accuracy is high, can effectively improve the traffic safety of train.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of potential faults method for early warning for train traction system, comprise the following steps：
1) real-time running data of train traction system is gathered by sensor, and carries out Multi-sensor Fusion, obtains fortune
Line data set closes；
2) after being pre-processed to the data in service data set, its hidden danger characteristic value is extracted；
3) by hidden danger eigenvalue cluster into hidden danger characteristic vector, the running status of trailer system is characterized；
4) hidden danger characteristic vector is handled by fuzzy algorithmic approach, obtains the variation tendency of potential faults；
5) chart or curve exporting change trend are used, carries out the early warning of potential faults.
The real-time running data of inverter and traction electric machine in sensor collection train traction system in step 1), and in step
It is rapid 2) in different hidden danger mining algorithm extraction hidden danger characteristic values are respectively adopted.
Compared with prior art, the present invention has advantages below：
1st, pre-processed by the detection to train operating data, the characteristic vector of potential faults can be obtained, can be accurate
The potential faults development trend reflected present in train traction system, can intuitively observe the deterioration degree of hidden danger.
That is, it is possible to give the early warning of failure and the prediction of hidden danger before the failure of trailer system key component.
2nd, traditional signal processing method time domain recognition differential is avoided, the shortcomings of nonstationary signal detection is not sensitive enough.Pin
There is very strong disposal ability to the service data of trailer system, particularly accidental data and accuracy rate is very high.
3rd, the fusion of decision-making level has been carried out to the result after signal transacting, has realized simplifying for data, with traditional method
Compare, reduce the installation number of sensor, overcome influence of the data deficiencies to prediction result precision
Brief description of the drawings
Fig. 1 is the method flow diagram of the embodiment of the present invention；
Fig. 2 is the handling process for inverter and traction electric machine service data.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.
Embodiment
As shown in figure 1, a kind of potential faults method for early warning for train traction system, comprises the following steps：
First, the real-time of inverter and traction electric machine this two big critical component in train traction system is gathered by sensor
Service data, and Multi-sensor Fusion is carried out, obtain service data set, the input element as whole method.
Then, signal transacting link is entered.Detailed process is：
Signal is pre-processed first, for different pieces of information, according to the demand of input threshold value, signal be filtered.
Dynamical system wavelet algorithm is recycled to handle pretreated data.For the data of different parts, the method for processing
Difference, as shown in Figure 2.The hidden danger characteristic value of traction electric machine is extracted using dynamical system traction electric machine hidden danger mining algorithm, and direct current
Bleed-off circuit hidden danger characteristic value is then extracted by the hidden danger mining algorithm of corresponding dynamical system direct current bleed-off circuit.All numbers
Analyzed again by dynamical system hidden danger Feature Selection according to the characteristic value obtained by after processing, select it is representative can
Reflect the characteristic value of trailer system running status, by these characteristic value composition characteristic hidden danger vector.So, train is in running
The state of this two big critical component of middle dynamical system can just be characterized by the variation tendency of characteristic vector.For feature to
The change of amount, then the processing for passing through fuzzy algorithmic approach, it is possible to accurately realize the prediction of trailer system potential faults.
Finally, the variation tendency of system hidden trouble is represented in the form of chart or curve, carries out the early warning of potential faults.
After all data results are preserved, train dynamicses system can be maintained for later municipal rail train all departments,
Trouble-saving, hidden danger excavation, security evaluation early warning and aid decision etc. provide reference data.
Claims (2)
1. a kind of potential faults method for early warning for train traction system, it is characterised in that comprise the following steps：
1) real-time running data of train traction system is gathered by sensor, and carries out Multi-sensor Fusion, obtains operation number
According to set, the real-time running data of inverter and traction electric machine in sensor collection train traction system and is led inverter
Draw the critical component that motor is train traction system；
2) after being pre-processed to the data in service data set, its hidden danger characteristic value is extracted, for different critical components
Using different processing methods, the hidden danger characteristic value of traction electric machine is extracted using dynamical system traction electric machine hidden danger mining algorithm, directly
Stream bleed-off circuit hidden danger characteristic value is then extracted by the hidden danger mining algorithm of corresponding dynamical system direct current bleed-off circuit；
3) by hidden danger eigenvalue cluster into hidden danger characteristic vector, the running status of trailer system is characterized；
4) hidden danger characteristic vector is handled by fuzzy algorithmic approach, obtains the variation tendency of potential faults；
5) chart or curve exporting change trend are used, carries out the early warning of potential faults.
A kind of 2. potential faults method for early warning for train traction system according to claim 1, it is characterised in that
Different hidden danger mining algorithm extraction hidden danger characteristic values is respectively adopted in step 2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310234151.9A CN104236933B (en) | 2013-06-13 | 2013-06-13 | A kind of potential faults method for early warning for train traction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310234151.9A CN104236933B (en) | 2013-06-13 | 2013-06-13 | A kind of potential faults method for early warning for train traction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104236933A CN104236933A (en) | 2014-12-24 |
| CN104236933B true CN104236933B (en) | 2017-12-26 |
Family
ID=52225450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310234151.9A Expired - Fee Related CN104236933B (en) | 2013-06-13 | 2013-06-13 | A kind of potential faults method for early warning for train traction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104236933B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105044497B (en) * | 2015-06-30 | 2018-02-02 | 株洲南车时代电气股份有限公司 | A kind of traction convertor intelligent fault analysis method |
| CN109747680B (en) * | 2017-11-03 | 2021-04-02 | 株洲中车时代电气股份有限公司 | Method, device and equipment for state evaluation and fault early warning of train traction system |
| CN109754110B (en) * | 2017-11-03 | 2023-07-11 | 株洲中车时代电气股份有限公司 | Early warning method and system for traction converter faults |
| CN109835371B (en) * | 2017-11-27 | 2020-06-26 | 株洲中车时代电气股份有限公司 | Method and system for diagnosing real-time fault of train |
| CN108398934B (en) * | 2018-02-05 | 2019-12-13 | 常州高清信息技术有限公司 | equipment fault monitoring system for rail transit |
| CN110276509A (en) * | 2019-03-05 | 2019-09-24 | 清华大学 | Subway train trailer system dynamic risk analysis appraisal procedure based on characteristic quantity |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101660969A (en) * | 2009-09-25 | 2010-03-03 | 北京工业大学 | Intelligent fault diagnosis method for gear box |
| CN101697006A (en) * | 2009-09-18 | 2010-04-21 | 北京航空航天大学 | Target identification method based on data fusion of airborne radar and infrared imaging sensor |
| CN201575927U (en) * | 2009-12-31 | 2010-09-08 | 中国铁道科学研究院机车车辆研究所 | Bogie condition monitoring device |
| CN102139700A (en) * | 2010-02-01 | 2011-08-03 | 同济大学 | Vehicle working condition online monitoring system for rail transit |
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
| CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199482A1 (en) * | 2002-04-15 | 2004-10-07 | Wilson Scott B. | Systems and methods for automatic and incremental learning of patient states from biomedical signals |
-
2013
- 2013-06-13 CN CN201310234151.9A patent/CN104236933B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697006A (en) * | 2009-09-18 | 2010-04-21 | 北京航空航天大学 | Target identification method based on data fusion of airborne radar and infrared imaging sensor |
| CN101660969A (en) * | 2009-09-25 | 2010-03-03 | 北京工业大学 | Intelligent fault diagnosis method for gear box |
| CN201575927U (en) * | 2009-12-31 | 2010-09-08 | 中国铁道科学研究院机车车辆研究所 | Bogie condition monitoring device |
| CN102139700A (en) * | 2010-02-01 | 2011-08-03 | 同济大学 | Vehicle working condition online monitoring system for rail transit |
| CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| CN102944416A (en) * | 2012-12-06 | 2013-02-27 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
Non-Patent Citations (2)
| Title |
|---|
| 信息融合技术在机车牵引电机故障诊断中的应用研究;程传胜;《中国优秀博硕士学位论文全文数据库 (硕士) 工程科技Ⅱ辑》;20060515(第05期);第1章第1.4节，第2章-第6章 * |
| 高速铁路牵引供电系统健康管理及故障预警体系研究;何正友 等;《电网技术》;20121031;第36卷(第10期);第259-264页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104236933A (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104236933B (en) | A kind of potential faults method for early warning for train traction system | |
| Yao et al. | A novel intelligent method for fault diagnosis of electric vehicle battery system based on wavelet neural network | |
| CN106526400B (en) | The earth fault diagnostic method and device of DC600V power supply system of train | |
| CN107703920B (en) | Fault detection method of train braking system based on multivariate time sequence | |
| JP6557110B2 (en) | Condition diagnosis apparatus and program | |
| CN103838229B (en) | Diagnosis method and device of electric car | |
| CN103116090B (en) | Three-phrase pulse-width modulation (PWM) rectifier fault diagnosis method based on wavelet packet analysis and support vector machine | |
| CN105528741B (en) | Circuit breaker state identification method based on multi-signal feature fusion | |
| CN103901882A (en) | Online monitoring fault diagnosis system and method of train power system | |
| CN105159283A (en) | Remote fault analysis and feedback system of urban rail transit vehicle | |
| CN105403816A (en) | Identification method of DC fault electric arc of photovoltaic system | |
| Fan et al. | Fault diagnosis method for lithium-ion batteries in electric vehicles using generalized dimensionless indicator and local outlier factor | |
| CN106324514A (en) | Vehicle battery performance testing method and vehicle battery performance testing system | |
| JP2020008347A (en) | Device and method for diagnosing state | |
| CN110705038A (en) | Life cycle evaluation and fault early warning method for high-voltage circuit breaker | |
| Zhang et al. | Battery voltage fault diagnosis for electric vehicles considering driving condition variation | |
| Choudhary et al. | Fault diagnosis of induction motor under varying operating condition | |
| Yang et al. | An online multifault diagnosis scheme for battery packs based on voltage envelope relationship | |
| CN107463162A (en) | Energy-conserving and environment-protective electronic logistic car fault diagnosis control system | |
| CN103884904B (en) | Battery voltage checkout gear | |
| CN110276509A (en) | Subway train trailer system dynamic risk analysis appraisal procedure based on characteristic quantity | |
| CN106569126A (en) | Breaker fault diagnosing method based on spectrum analysis algorithm | |
| CN113240002A (en) | Internet of vehicles big data preprocessing system, device and method | |
| CN113128751A (en) | System and method for predicting pull-out value fault of contact network | |
| CN102518012B (en) | Track detection method integrating detection data of various devices |
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 | ||
| 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: 20171226 Termination date: 20200613 |