CN115310346A - Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof - Google Patents
Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof Download PDFInfo
- Publication number
- CN115310346A CN115310346A CN202210755924.7A CN202210755924A CN115310346A CN 115310346 A CN115310346 A CN 115310346A CN 202210755924 A CN202210755924 A CN 202210755924A CN 115310346 A CN115310346 A CN 115310346A
- Authority
- CN
- China
- Prior art keywords
- traction seat
- rail vehicle
- bogie
- urban rail
- fault diagnosis
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 30
- 238000010276 construction Methods 0.000 title claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims abstract description 8
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/08—Railway vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The invention belongs to the technical field of fault diagnosis, and discloses a fault diagnosis model of a traction seat of an urban rail vehicle bogie and a construction method thereof, wherein a simulation experiment platform of the urban rail vehicle bogie is firstly built to complete signal acquisition of the traction seat, and vibration signals of the traction seat are analyzed and processed in different domains to construct an energy vector; and then obtaining a sensitive feature set of the traction seat based on a PCA-OVO feature extraction algorithm, establishing and training a state recognition model by utilizing a BP neural network, respectively taking a time domain, a frequency domain, a time frequency and the sensitive feature set as input values, and comparing output state results. The fault diagnosis model for the urban rail vehicle bogie traction seat based on the PCA-OVO back propagation neural network can effectively improve the fault detection efficiency, has high accuracy and provides a new model for fault diagnosis of the urban rail vehicle traction seat.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a fault diagnosis model of a traction seat of an urban rail vehicle bogie and a construction method thereof.
Background
At present, the operation and maintenance mode of urban rail vehicle bogies is mainly based on the traditional mode, and has the problems of over-frequent maintenance, insufficient maintenance, dependence on subjective factors and the like, the state of the bogie cannot be accurately reflected, and huge consumption phenomena exist in the aspects of manpower, material resources, financial resources and the like.
The bogie traction seat is an important part of an urban rail vehicle, potential safety hazards exist in vehicle operation due to the fault state of the traction seat, and the timely diagnosis of the fault state of the traction seat has important significance on safe operation of the urban rail vehicle. Aiming at the defects of low efficiency and low accuracy of the traditional traction seat fault detection method, a fault diagnosis model based on a PCA-OVO Back Propagation (BP) neural network is provided.
Through the above analysis, the problems and defects of the prior art are as follows:
the traditional traction seat fault detection method has the defects of low efficiency and low accuracy.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a fault diagnosis model of a traction seat of an urban rail vehicle bogie and a construction method thereof.
The invention is realized in such a way that the construction method of the urban rail vehicle bogie traction seat fault diagnosis model comprises the following steps:
step one, building an urban rail vehicle bogie simulation experiment platform to complete signal acquisition of a traction seat;
analyzing and processing the vibration signals of the traction seat in different domains to construct an energy vector;
thirdly, obtaining a sensitive feature set of the traction seat based on a feature extraction algorithm of PCA-OVO;
and step four, establishing and training a state recognition model by using the BP neural network, respectively taking a time domain, a frequency domain, a time frequency and a sensitive feature set as input values, and comparing output state results.
The invention also aims to provide a fault diagnosis model for the traction seat of the bogie of the urban rail vehicle.
By combining all the technical schemes, the invention has the advantages and positive effects that:
the method takes the research method of the crack fault of the traction seat of the urban rail vehicle bogie as a starting point, analyzes the diagnosis method of the crack fault of the traction seat of the bogie based on the domestic and foreign fault diagnosis and the analysis of the crack fault diagnosis, and develops a visual bogie state monitoring and fault diagnosis system on the basis.
The fault diagnosis model for the urban rail vehicle bogie traction seat based on the PCA-OVO back propagation neural network can effectively improve the fault detection efficiency, has high accuracy and provides a new model for fault diagnosis of the urban rail vehicle traction seat.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a flow chart of a method for constructing a fault diagnosis model of a traction seat of a bogie of an urban rail vehicle according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a traction seat fault diagnosis model of an urban rail vehicle bogie and a construction method thereof, and the invention is described in detail below by combining the attached drawings.
As shown in fig. 1, a method for constructing a fault diagnosis model of a traction seat of an urban rail vehicle bogie provided by the embodiment of the invention comprises the following steps:
s101, building an urban rail vehicle bogie simulation experiment platform to complete signal acquisition of a traction seat;
s102, analyzing and processing the vibration signals of the traction seat in different domains to construct an energy vector;
s103, obtaining a sensitive feature set of the traction seat based on a feature extraction algorithm of PCA-OVO;
and S104, establishing and training a state identification model by using the BP neural network, respectively taking a time domain, a frequency domain, a time frequency and a sensitive feature set as input values, and comparing output state results.
According to the theory of the traction seat of the bogie, the invention builds an experiment and obtains reliable data. Firstly, designing a traction seat test model according to relevant knowledge of crack faults of a traction seat of a bogie; and then, selecting a proper experimental instrument and constructing an experimental platform of the urban rail vehicle bogie traction seat. And finally, traction seat data are collected from the built experimental platform, so that the current situation that a traction seat data set is difficult to obtain is solved.
The invention provides a feature extraction scheme based on PCA _ OVO by analyzing a feature extraction algorithm of a bogie traction seat. Firstly, processing a traction seat signal by adopting a time-frequency domain analysis VMD based on a common signal processing method; then, determining MPE important parameter values in VMD and entropy theory by using HHO algorithm; finally, a feature extraction algorithm of PCA _ OVO is provided, so that the extracted features are complete and the efficiency is high.
The invention provides a pattern recognition scheme based on HHO _ SVM by analyzing a state recognition algorithm of a bogie traction seat. Firstly, based on the basic theory of SVM, providing a traction seat fault diagnosis model based on H-SVMs to solve the multi-state recognition problem; and then, a classification algorithm of the HHO _ SVM is constructed, and experiments verify that the proposed HHO _ SVM algorithm can ensure high accuracy of traction seat state identification.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. It will be appreciated by those skilled in the art that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, for example such code provided on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware) or a data carrier such as an optical or electronic signal carrier. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. A method for constructing a fault diagnosis model of a traction seat of an urban rail vehicle bogie is characterized by comprising the following steps:
step one, building a simulation experiment platform of the bogie of the urban rail vehicle to complete signal acquisition of a traction seat;
analyzing and processing the vibration signals of the traction seat in different domains to construct an energy vector;
thirdly, obtaining a sensitive feature set of the traction seat based on a feature extraction algorithm of PCA-OVO;
and step four, establishing and training a state recognition model by using the BP neural network, respectively taking a time domain, a frequency domain, a time frequency and a sensitive feature set as input values, and comparing output state results.
2. The method for constructing the fault diagnosis model of the traction seat of the bogie of the urban rail vehicle as claimed in claim 1, wherein in the first step of constructing the simulation experiment platform of the bogie of the urban rail vehicle, an experiment is constructed and reliable data are obtained according to the theory of the traction seat of the bogie, and the method specifically comprises the following steps:
(1) Designing a traction seat test model according to the relevant knowledge of the crack fault of the traction seat of the bogie;
(2) Selecting a proper experimental instrument, and constructing an experimental platform of the traction seat of the bogie of the urban rail vehicle;
(3) The traction seat data are collected from the built experimental platform, and the current situation that a traction seat data set is difficult to obtain is solved.
3. The method for constructing the traction seat fault diagnosis model of the urban rail vehicle bogie according to claim 1, wherein the step three is based on a PCA-OVO feature extraction algorithm to obtain a set of sensitivity features of a traction seat, and comprises the following steps:
(1) Based on a common signal processing method, processing a traction seat signal by adopting a time-frequency domain analysis VMD;
(2) Determining important parameter values of MPE in VMD and entropy theory by using HHO algorithm;
(3) And a feature extraction algorithm of PCA _ OVO is provided, so that the extracted features are complete and the efficiency is high.
4. The method for constructing the fault diagnosis model of the traction seat of the bogie of the urban rail vehicle according to claim 1, wherein the fourth step of establishing and training a state recognition model by using a BP neural network comprises the following steps:
(1) Based on the basic theory of SVM, a traction seat fault diagnosis model based on H-SVMs is provided, and the problem of multi-state recognition is solved;
(2) And constructing a classification algorithm of the HHO _ SVM, wherein the HHO _ SVM algorithm is used for ensuring the high accuracy of the traction seat state identification.
5. The fault diagnosis model for the traction base of the urban rail vehicle bogie, which is constructed by the construction method for the fault diagnosis model for the traction base of the urban rail vehicle bogie according to claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210755924.7A CN115310346A (en) | 2022-06-30 | 2022-06-30 | Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210755924.7A CN115310346A (en) | 2022-06-30 | 2022-06-30 | Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115310346A true CN115310346A (en) | 2022-11-08 |
Family
ID=83854690
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210755924.7A Pending CN115310346A (en) | 2022-06-30 | 2022-06-30 | Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115310346A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111753927A (en) * | 2020-07-22 | 2020-10-09 | 华东交通大学 | Method for identifying crack fault state of locomotive traction seat |
WO2021217364A1 (en) * | 2020-04-27 | 2021-11-04 | 西门子股份公司 | Fault diagnosis method and apparatus therefor |
-
2022
- 2022-06-30 CN CN202210755924.7A patent/CN115310346A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021217364A1 (en) * | 2020-04-27 | 2021-11-04 | 西门子股份公司 | Fault diagnosis method and apparatus therefor |
CN111753927A (en) * | 2020-07-22 | 2020-10-09 | 华东交通大学 | Method for identifying crack fault state of locomotive traction seat |
Non-Patent Citations (2)
Title |
---|
QI CHANG 等: "Intelligent Diagnosis Model of Traction Seat of Urban Rail Vehicle Based on Harris Hawks Optimization" * |
QI CHANG 等: "Research on bogie traction seat crack identification based on OvO multi-feature fusion" * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110533007B (en) | Intelligent identification and extraction method for bridge vehicle-mounted strain influence line features | |
CN116205497B (en) | Landslide intelligent early warning method and system based on artificial intelligence | |
CN113837596B (en) | Fault determination method and device, electronic equipment and storage medium | |
CN114881076B (en) | Rail corrugation identification method, device, equipment and medium based on support vector machine | |
CN104458814A (en) | Preprocessing method and device for online detection signal of steel wire rope | |
CN115122155A (en) | Machine tool remote diagnosis method and system based on industrial internet big data | |
CN110660049A (en) | Tire defect detection method based on deep learning | |
Wagner et al. | OCD: Online convergence detection for evolutionary multi-objective algorithms based on statistical testing | |
CN105426915A (en) | Support vector machine-based prediction method and system | |
CN114238980B (en) | Industrial control equipment vulnerability mining method, system, equipment and storage medium | |
CN110020190B (en) | Multi-instance learning-based suspicious threat index verification method and system | |
Lv et al. | A new performance degradation evaluation method integrating PCA, PSR and KELM | |
Zhou et al. | The impact of provincial port integration on port efficiency: Empirical evidence from China's Coastal Provinces | |
CN115310346A (en) | Fault diagnosis model for traction seat of bogie of urban rail vehicle and construction method thereof | |
CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
CN103293410B (en) | Server energy consumption detection method and device | |
WO2023125586A1 (en) | Training method and apparatus for urban underground gas leakage identification model | |
CN108761250B (en) | Industrial control equipment voltage and current-based intrusion detection method | |
CN116415851A (en) | Intelligent identification and evaluation method for facility operation and maintenance performance indexes based on deep learning | |
CN105469141A (en) | Neural-network-based prediction method and system | |
Zhang et al. | Condition-guided adversarial generative testing for deep learning systems | |
CN114462127A (en) | Structural damage identification method and system based on deep extreme learning machine | |
CN113805106A (en) | Rail transit train position and transformer direct-current magnetic bias correlation analysis method | |
Sae-Lim et al. | Can automated impact analysis techniques help predict decaying modules? | |
CN109187772A (en) | It is applied to the method for impact elasticity wave analysis based on speech recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221108 |
|
RJ01 | Rejection of invention patent application after publication |