CN112863007A - Fault early warning model of traction converter, modeling method, early warning method and early warning system - Google Patents
Fault early warning model of traction converter, modeling method, early warning method and early warning system Download PDFInfo
- Publication number
- CN112863007A CN112863007A CN202110225044.4A CN202110225044A CN112863007A CN 112863007 A CN112863007 A CN 112863007A CN 202110225044 A CN202110225044 A CN 202110225044A CN 112863007 A CN112863007 A CN 112863007A
- Authority
- CN
- China
- Prior art keywords
- traction converter
- early warning
- fault early
- warning model
- fault
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 19
- 230000004913 activation Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 9
- 238000012544 monitoring process Methods 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0081—On-board diagnosis or maintenance
-
- 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
- G06N3/047—Probabilistic or stochastic networks
-
- 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
- G06N3/048—Activation functions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a fault early warning model of a traction converter, a modeling method, an early warning method and a system, wherein the modeling method comprises the following steps: step 1, collecting a plurality of groups of modeling data of a traction converter in M different operation states, wherein each group of modeling data comprises a plurality of groups of operation parameter values and operation state data corresponding to a time point next to an operation parameter value collection time point; the M different operating states comprise M fault states of the traction converter; or the M different operation states comprise M-1 fault states and normal states of the traction converter; and 2, learning to obtain a fault early warning model of the traction converter by taking the operation parameter values in the modeling data as input and the operation state data as output. The method can predict the fault state of the traction converter in the running process of the train and perform early warning before the fault of the traction converter occurs, thereby providing enough stress protection time and better ensuring the running safety of the train.
Description
Technical Field
The invention belongs to the field of rail transit vehicle traction fault analysis, and particularly relates to a traction converter fault early warning model, a modeling method, an early warning method and an early warning system.
Background
With the development of high-speed train technology and the massive construction of high-speed railways, the running speed of trains is faster and faster, the load bearing capacity of the trains is larger and larger, and the fault probability of parts on the trains is larger and larger. Among the system devices of the train, the traction converter provides electric energy for train traction and auxiliary power utilization, and is a very important part of the train. The traction converter is composed of a plurality of components, the integration level of each component is high, when a certain component breaks down, a large chain reaction is likely to be caused, and a mechanical failure can be caused when a train runs seriously.
The severity level of the fault of the traction converter can be divided into three types of slight fault, medium fault and serious fault, wherein the slight fault and the medium fault cannot cause the train to be incapable of running, and can be processed after the train returns to a warehouse, but the serious fault can cause the train to be incapable of running and needs to be processed immediately. When the traction converter has a serious fault, the train is late, so that the dispatching of a line is influenced, and certain potential safety hazards are caused.
At present, when a train traction converter has a serious fault, a train system only gives out a serious alarm when the serious fault occurs, and a driver is prompted to make a related protection action. The mechanism of the after-accident protection is very much testful to the reaction and quality of a driver, and if the operation is improper, the safety of the line operation is influenced.
Therefore, if the train traction converter can give out early warning in advance when the train traction converter fails and give out enough reaction time, a driver can better protect the train and better guarantee the running safety of the train.
Disclosure of Invention
The invention aims to provide a traction converter fault early warning model, a modeling method, an early warning method and a system aiming at the defect that the fault of a train traction converter cannot be early warned in the prior art, and the fault state of the traction converter can be predicted in the running process of the train, and early warning is carried out before the fault of the traction converter occurs, so that enough stress protection time is provided, and the running safety of the train is better guaranteed.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a traction converter fault early warning model modeling method is characterized by comprising the following steps:
and 2, learning to obtain a fault early warning model of the traction converter by taking the operation parameter values in the modeling data as input and the operation state data in the modeling data as output.
As a preferable mode, in the step 2, learning is performed by adopting a BP neural network algorithm to obtain a traction converter fault early warning model.
As a preferable mode, the step 2 includes:
step 201, setting the number of nodes, activation functions and weight matrixes of a BP neural network input layer; setting the number of nodes, an activation function and a weight matrix of a hidden layer of the BP neural network; setting the number of nodes and an activation function of an output layer of the BP neural network; setting a loss function, an iteration threshold and a loss threshold of a BP neural network algorithm;
step 202, after the operation parameter values in the modeling data are transmitted to an input layer of the BP neural network, an output layer of the BP neural network outputs a predicted value;
step 203, performing loss calculation on the predicted value obtained in step 202 and the running state data in the corresponding modeling data to obtain a loss value; judging whether the loss value is smaller than a loss threshold value, if so, finishing learning of the fault early warning model of the traction converter, and otherwise, executing a step 204;
and 204, judging whether the iteration times are less than an iteration time threshold, if so, finishing learning of the fault early warning model of the traction converter, otherwise, performing weight correction on each weight matrix through loss values and jumping to the step 202.
Further, in step 202, the operation parameter values in the modeling data are preprocessed and then transmitted to the input layer of the BP neural network.
In a preferred embodiment, the pretreatment method is a principal component analysis method.
Based on the same inventive concept, the invention also provides a traction converter fault early warning model obtained by using the traction converter fault early warning model modeling method.
Based on the same invention concept, the invention also provides a fault early warning method for the traction converter, which is characterized by comprising the following steps:
and 4, inputting a plurality of groups of measured operation parameter values into the traction converter fault early warning model, and taking the output of the traction converter fault early warning model as a prediction result.
Based on the same invention concept, the invention also provides a traction converter fault early warning system which is characterized by comprising an actual measurement operation parameter value detection module and a server, wherein the server is provided with the traction converter fault early warning model; wherein:
actual measurement operation parameter value detection module: the system is used for acquiring a plurality of groups of measured operation parameter values of a traction converter on the train;
a server: the system comprises a traction converter fault early warning model, a fault early warning model and a prediction result output module, wherein the traction converter fault early warning model is used for receiving a plurality of groups of received measured operation parameter values and outputting the output of the traction converter fault early warning model as the prediction result.
Preferably, the server is a local server of the traction converter or a vehicle-mounted main server.
Compared with the prior art, the fault early warning model of the traction converter is established based on the neural network, and the fault early warning system of the traction converter is established, so that the fault state of the traction converter can be predicted in the running process of a train, and early warning is performed before the fault of the traction converter occurs, so that enough stress protection time is given, and the running safety of the train is better guaranteed.
Drawings
Fig. 1 is a learning flow chart of a fault early warning model of a traction converter.
Fig. 2 is a flowchart of a traction converter fault early warning method.
Fig. 3 is a block diagram of a fault warning system of the traction converter.
The system comprises a traction converter 1, an actual measurement operation parameter value detection module 2, a server 3, a local server 301, a vehicle-mounted main server 302 and a display screen 4.
Detailed Description
The technical idea of the invention is as follows: in the running process of a train, collecting main monitoring data (including running parameter values and running state data) of a traction converter 1, and establishing a database; then, a traction converter fault early warning model is established based on the BP neural network, a traction converter fault early warning system is established, the traction converter fault early warning system can be used for monitoring the traction converter 1, and early warning is given out before the traction converter 1 has serious faults.
The invention discloses a traction converter fault early warning model modeling method which comprises the following steps:
The modeling data acquisition process specifically comprises the following steps:
and setting a fixed acquisition time interval, and acquiring the operation parameter value and the operation state data of the traction converter 1 of each time node according to the set acquisition time interval. Acquiring an operation parameter value and operation state data of the traction converter 1 of each time node in the train positive line running process; under a test environment, simulating a serious fault condition of the traction converter 1 in a driving process, and acquiring an operation parameter value and operation state data of the traction converter 1 at each time node. And after data acquisition, establishing a database of the operating parameter values and the operating state data of the traction converter 1.
And 2, learning to obtain a traction converter fault early warning model by taking the operation parameter values in the modeling data as input and taking the operation state data corresponding to the next time point of the operation parameter value acquisition time point in the modeling data as output.
Preferably, in the step 2, a fault early warning model of the traction converter is obtained by learning through a BP neural network algorithm. As shown in fig. 1, the learning process of the traction converter fault early warning model based on the BP neural network in step 2 includes:
step 201, setting a BP neural network into three layers: an input layer, a hidden layer and an output layer; setting the number of nodes, an activation function and a weight matrix of a BP neural network input layer; setting the number of nodes, an activation function and a weight matrix of a hidden layer of the BP neural network; setting the number of nodes and an activation function of an output layer of the BP neural network; setting a loss function, an iteration threshold and a loss threshold of a BP neural network algorithm;
step 202, preprocessing the operation parameter values in the modeling data, transmitting the preprocessed operation parameter values to an input layer of a BP (back propagation) neural network, transmitting the preprocessed operation parameter values to a hidden layer after the calculation of the input layer, transmitting the preprocessed operation parameter values to an output layer after the calculation of the hidden layer, and finally outputting a predicted value by the output layer of the BP neural network after the calculation of the output layer;
step 203, performing loss calculation on the predicted value obtained in step 202 and the running state data in the corresponding modeling data to obtain a loss value; judging whether the loss value is smaller than a loss threshold value, if so, finishing learning of the fault early warning model of the traction converter, and otherwise, executing a step 204;
and 204, judging whether the iteration times are less than an iteration time threshold, if so, finishing learning of the fault early warning model of the traction converter, otherwise, performing weight correction on each weight matrix through loss values and jumping to the step 202.
Preferably, the pretreatment method is a principal component analysis method.
Preferably, the number of the BP neural network input layer nodes is 8, and the activation function is a ReLU function; the number of hidden layer nodes is 11, and the activation function is a sigmoid function; the number of output layer nodes is 4, and the activation function is a softmax function; the loss function is the MSE (mean square error) loss.
The invention also provides a traction converter fault early warning model obtained by the traction converter fault early warning model modeling method.
As shown in fig. 2, the present invention further provides a fault early warning method for a traction converter, including:
and 3, collecting multiple groups of actually measured operation parameter values of the traction converter 1 on the train.
And 4, inputting a plurality of groups of measured operation parameter values into the traction converter fault early warning model, and taking the output of the traction converter fault early warning model as a prediction result.
As shown in fig. 3, the invention further provides a traction converter fault early warning system, which comprises an actual measurement operation parameter value detection module 2 and a server 3, wherein the server 3 is provided with the traction converter fault early warning model; wherein:
the actual measurement operation parameter value detection module 2: the system is used for collecting a plurality of groups of measured operation parameter values of a traction converter 1 on the train;
the server 3: the system comprises a traction converter fault early warning model, a fault early warning model and a prediction result output module, wherein the traction converter fault early warning model is used for receiving a plurality of groups of received measured operation parameter values and outputting the output of the traction converter fault early warning model as the prediction result.
The server 3 is a local server 301 or an on-board main server 302 of the traction converter 1.
The actual measurement operation parameter value detection module 2 is a sensor.
In this embodiment, the traction converter fault early warning model is set in the vehicle-mounted main server 302, and the working process of the fault early warning system is as follows: the method comprises the steps that multiple groups of actual measurement operation parameter values of a traction converter 1 on a train are collected through an actual measurement operation parameter value detection module 2 (a sensor) and are sent to a vehicle-mounted main server 302 through a local server 301, a traction converter fault early warning model in the vehicle-mounted main server 302 carries out prediction to obtain a predicted value, and the vehicle-mounted main server 302 outputs the predicted value to a display screen 4. And if the predicted value is a fault value, sending out a fault early warning, wherein the corresponding fault is a fault type corresponding to the predicted value.
Optionally, the operation parameter value of the traction converter 1 comprises a network voltage X of the traction converter 11Intermediate voltage X2D.C. current X3D.C. current X4Output current X5Output current X6Charging contact state X7Short-circuit contactor state X8. The traction converter 1 operating status data includes serious faults that can cause the train to fail to operate: VVVF fault Y1Charging failure Y2Short-circuit contactor clamping Y3And the short-circuit contactor is clamped with Y4。
X7、X8、Y1、Y2、Y3、Y4The value is 0 or 1, 0 represents normal, 1 represents fault, and X1、X2、X3、X4、X5、X6Are all analog values.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A traction converter fault early warning model modeling method is characterized by comprising the following steps:
step 1, collecting a plurality of groups of modeling data of a traction converter (1) in M different operation states, wherein each group of modeling data comprises a plurality of groups of operation parameter values and operation state data corresponding to a time point next to an operation parameter value collection time point; the M different operating states comprise M fault states of the traction converter (1); or the M different operation states comprise M-1 fault states and normal states of the traction converter (1);
and 2, learning to obtain a fault early warning model of the traction converter by taking the operation parameter values in the modeling data as input and the operation state data in the modeling data as output.
2. The modeling method for the fault early warning model of the traction converter as claimed in claim 1, wherein in the step 2, a BP neural network algorithm is adopted to learn and obtain the fault early warning model of the traction converter.
3. The traction converter fault warning model modeling method of claim 2, wherein the step 2 comprises:
step 201, setting the number of nodes, activation functions and weight matrixes of a BP neural network input layer; setting the number of nodes, an activation function and a weight matrix of a hidden layer of the BP neural network; setting the number of nodes and an activation function of an output layer of the BP neural network; setting a loss function, an iteration threshold and a loss threshold of a BP neural network algorithm;
step 202, after the operation parameter values in the modeling data are transmitted to an input layer of the BP neural network, an output layer of the BP neural network outputs a predicted value;
step 203, performing loss calculation on the predicted value obtained in step 202 and the running state data in the corresponding modeling data to obtain a loss value; judging whether the loss value is smaller than a loss threshold value, if so, finishing learning of the fault early warning model of the traction converter, and otherwise, executing a step 204;
and 204, judging whether the iteration times are less than an iteration time threshold, if so, finishing learning of the fault early warning model of the traction converter, otherwise, performing weight correction on each weight matrix through loss values and jumping to the step 202.
4. The traction converter fault early warning model modeling method as claimed in claim 3, wherein in step 202, the operation parameter values in the modeling data are preprocessed and then transmitted to the input layer of the BP neural network.
5. The traction converter fault early warning model modeling method of claim 4, wherein the preprocessing method is a principal component analysis method.
6. A traction converter fault early warning model obtained by the traction converter fault early warning model modeling method according to any one of claims 1 to 5.
7. A fault early warning method for a traction converter is characterized by comprising the following steps:
step 3, collecting a plurality of groups of actually measured operation parameter values of the traction converter (1) on the train;
and 4, inputting a plurality of groups of measured operation parameter values into the traction converter fault early warning model in claim 6, and taking the output of the traction converter fault early warning model as a prediction result.
8. A traction converter fault early warning system is characterized by comprising an actual measurement operation parameter value detection module (2) and a server (3), wherein the server (3) is provided with the traction converter fault early warning model according to claim 6; wherein:
actual measurement operation parameter value detection module (2): the system is used for collecting multiple groups of measured operation parameter values of a traction converter (1) on the train;
server (3): the system comprises a traction converter fault early warning model, a fault early warning model and a prediction result output module, wherein the traction converter fault early warning model is used for receiving a plurality of groups of received measured operation parameter values and outputting the output of the traction converter fault early warning model as the prediction result.
9. The traction converter fault pre-warning system according to claim 8, characterized in that the server (3) is a local server (301) or an on-board main server (302) of the traction converter (1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110225044.4A CN112863007A (en) | 2021-03-01 | 2021-03-01 | Fault early warning model of traction converter, modeling method, early warning method and early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110225044.4A CN112863007A (en) | 2021-03-01 | 2021-03-01 | Fault early warning model of traction converter, modeling method, early warning method and early warning system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112863007A true CN112863007A (en) | 2021-05-28 |
Family
ID=75990652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110225044.4A Pending CN112863007A (en) | 2021-03-01 | 2021-03-01 | Fault early warning model of traction converter, modeling method, early warning method and early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112863007A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502758A (en) * | 2014-12-17 | 2015-04-08 | 西北工业大学 | Fault diagnosis method for aeronautical static inverter |
| CN107992959A (en) * | 2017-04-26 | 2018-05-04 | 国网浙江省电力公司 | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology |
| CN108320043A (en) * | 2017-12-19 | 2018-07-24 | 江苏瑞中数据股份有限公司 | A kind of distribution network equipment state diagnosis prediction method based on electric power big data |
| CN111242357A (en) * | 2020-01-06 | 2020-06-05 | 北京锦鸿希电信息技术股份有限公司 | Neural network learning-based train-mounted equipment fault prediction method and device |
| CN111551872A (en) * | 2020-02-27 | 2020-08-18 | 西北工业大学 | Online diagnosis method for open-circuit fault of PMSM (permanent magnet synchronous motor) driving system inverter |
-
2021
- 2021-03-01 CN CN202110225044.4A patent/CN112863007A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502758A (en) * | 2014-12-17 | 2015-04-08 | 西北工业大学 | Fault diagnosis method for aeronautical static inverter |
| CN107992959A (en) * | 2017-04-26 | 2018-05-04 | 国网浙江省电力公司 | A kind of power failure Forecasting Methodology based on electric power big data visualization Neural Network Data digging technology |
| CN108320043A (en) * | 2017-12-19 | 2018-07-24 | 江苏瑞中数据股份有限公司 | A kind of distribution network equipment state diagnosis prediction method based on electric power big data |
| CN111242357A (en) * | 2020-01-06 | 2020-06-05 | 北京锦鸿希电信息技术股份有限公司 | Neural network learning-based train-mounted equipment fault prediction method and device |
| CN111551872A (en) * | 2020-02-27 | 2020-08-18 | 西北工业大学 | Online diagnosis method for open-circuit fault of PMSM (permanent magnet synchronous motor) driving system inverter |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102139700B (en) | Vehicle working condition online monitoring system for rail transit | |
| CN102879680B (en) | The general detection of rail transit vehicle equipment and method for diagnosing faults and system | |
| CN102510125B (en) | Method and device for monitoring operation conditions of power primary equipment | |
| KR20190107080A (en) | Cloud-based vehicle fault diagnosis method, apparatus and system | |
| CN110865628B (en) | New energy automobile electric control system fault prediction method based on working condition data | |
| CN107862763B (en) | Train safety early warning evaluation model training method, module and monitoring evaluation system | |
| CN111351664A (en) | Bearing temperature prediction and alarm diagnosis method based on LSTM model | |
| CN102063119B (en) | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data | |
| CN102139701B (en) | Train working condition on-line monitoring method for rail transit | |
| CN111695201B (en) | Data-based monitoring method for running state of maglev train | |
| CN113761728A (en) | Airport electric special vehicle fault early warning method based on Internet of vehicles platform | |
| Zhao et al. | Multi-step ahead voltage prediction and voltage fault diagnosis based on gated recurrent unit neural network and incremental training | |
| Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
| CN113465953B (en) | Fault prediction and health management device for motor train unit transmission system and using method thereof | |
| Zhang et al. | Battery voltage fault diagnosis for electric vehicles considering driving condition variation | |
| CN112863007A (en) | Fault early warning model of traction converter, modeling method, early warning method and early warning system | |
| CN110264585A (en) | Public transport diagnostic system after sale | |
| CN115062867A (en) | Bearing fault prediction method based on Teager energy spectrum and improved CNN model | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN105426665A (en) | Dynamic reliability determination method based on state monitoring | |
| CN114280955B (en) | Intelligent hydropower plant system based on field information model and digital twin and architecture method | |
| CN105138755A (en) | Design method of fault response generator for testbed of liquid propellant rocket engine | |
| Liu et al. | Research of prognostics and health management for EMU | |
| Li et al. | A hazard causation analysis method for battery electric vehicles based on STPA and complex network | |
| Peng et al. | Fault prediction method for on-board equipment of CTCS based on Seq2Seq model using LSTM |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210528 |