CN111830934A - Electric locomotive fault source positioning method and device - Google Patents
Electric locomotive fault source positioning method and device Download PDFInfo
- Publication number
- CN111830934A CN111830934A CN202010694631.3A CN202010694631A CN111830934A CN 111830934 A CN111830934 A CN 111830934A CN 202010694631 A CN202010694631 A CN 202010694631A CN 111830934 A CN111830934 A CN 111830934A
- Authority
- CN
- China
- Prior art keywords
- data
- fault source
- fault
- neural network
- network model
- 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
- 230000003137 locomotive effect Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000003062 neural network model Methods 0.000 claims description 57
- 210000002569 neuron Anatomy 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 26
- 238000013024 troubleshooting Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- 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
- G06N3/045—Combinations of 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a method and a device for positioning a fault source of an electric locomotive. The method comprises the following steps: acquiring the operation data of the locomotive sub-equipment unit through the TCMS bus; and carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, wherein the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data. The invention can improve the fault positioning efficiency when the locomotive has faults, greatly reduce the labor capacity of people, reduce the cost of fault troubleshooting time and enable the locomotive fault positioning to be faster and more accurate.
Description
Technical Field
The invention relates to the technical field of electric locomotive fault diagnosis, in particular to a method and a device for positioning a fault source of an electric locomotive.
Background
At present, when an electric locomotive has a fault, the operation data recorded by equipment on the locomotive is comprehensively analyzed mainly in a manual mode, and a locomotive fault source is positioned through logical reasoning.
When a locomotive fails, the failure of a certain device can cause the failure of other devices at the same time, so that a plurality of failure phenomena can occur at the same time; this requires that the analyst be familiar with the correlation between the locomotive data and the fault, or that it is difficult to quickly identify the source of the fault from the operational data. The fault is positioned manually, and the execution efficiency is low.
Disclosure of Invention
According to the technical problem that manual fault locating efficiency is low, the method for locating the fault source of the electric locomotive is provided. The invention can ensure that when the locomotive breaks down, the fault source is quickly, efficiently and accurately positioned, the fault troubleshooting time is shortened, the time cost is reduced, and the locomotive application becomes safer, more efficient and more economical.
The technical means adopted by the invention are as follows:
an electric locomotive fault source positioning method comprises the following steps:
acquiring the operation data of the locomotive sub-equipment unit through the TCMS bus;
and carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, wherein the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data.
Further, the fault source identification model is an error back propagation neural network model, and the error back propagation neural network model is trained by using historical operation data as input data of neurons in an input layer of the error back propagation neural network model and using fault source data corresponding to the historical operation data as output data of neurons in an output layer of the error back propagation neural network model.
Further, the training the error back propagation neural network model by using the historical operation data as the input data of the input layer neurons of the error back propagation neural network model and the actual fault source data corresponding to the historical operation data as the output data of the output layer neurons of the error back propagation neural network model comprises:
and adjusting an error function according to the difference value between the output data of the output layer neuron of the error back propagation neural network model and the actual fault data to make the error function reach the minimum.
Further, the training the error back propagation neural network model by using the historical operation data as the input data of the input layer neurons of the error back propagation neural network model and the actual fault source data corresponding to the historical operation data as the output data of the output layer neurons of the error back propagation neural network model further comprises:
and adjusting the structural parameters of the error back propagation neural network model according to the error function, wherein the structural parameters comprise the associated weight between the nodes of the input layer and the hidden layer, the corresponding threshold value of each node of the hidden layer, the associated weight between the nodes of the hidden layer and the nodes of the output layer and the corresponding threshold value of each node of the output layer.
Further, the method further comprises: storing operational data of the locomotive sub-equipment unit.
An electric locomotive fault source locating device, comprising:
the acquiring unit is used for acquiring the operating data of the locomotive sub-equipment unit through the TCMS bus;
the identification unit is used for carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data.
Further, the fault source identification model is an error back propagation neural network model;
the identification unit comprises a model training module, and the model training module is used for training the error back propagation neural network model by taking historical operation data as input data of an input layer neuron of the error back propagation neural network model and taking fault source data corresponding to the historical operation data as output data of an output layer neuron of the error back propagation neural network model.
Further, the training module is further configured to adjust an error function according to a difference between the output data of the output layer neuron of the error back propagation neural network model and the actual fault data, so that the error function is minimized.
Further, the training module is further configured to: and adjusting the structural parameters of the error back propagation neural network model according to the error function, wherein the structural parameters comprise the associated weight between the nodes of the input layer and the hidden layer, the corresponding threshold value of each node of the hidden layer, the associated weight between the nodes of the hidden layer and the nodes of the output layer and the corresponding threshold value of each node of the output layer.
Further, the device also comprises a storage module used for storing the operation data of the locomotive sub-equipment unit.
Compared with the prior art, the invention has the following advantages:
the invention provides an electric locomotive fault positioning model based on a neural network, which adopts a BP neural network algorithm to position a locomotive fault source and verifies the effectiveness of a model positioning result through simulation. The model solves the problems of complex locomotive fault location, labor waste and time waste to a certain extent, and the location method can be popularized to other types of vehicles, thereby providing a new exploration direction for the fault location of subsequent electric locomotives and similar types of vehicles.
The locomotive fault location model constructed by the invention can improve the fault location efficiency when the locomotive has faults to a great extent, greatly reduce the labor capacity of people, reduce the cost of fault troubleshooting time and enable the locomotive fault location to be faster and more accurate.
Based on the reasons, the invention can be widely popularized in the field of rail transit.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a diagram of a TCMS system topology.
FIG. 2 is a flow chart of a method for locating a source of a locomotive fault according to the present invention.
FIG. 3 is a diagram of a system for locating a source of a locomotive fault in an embodiment.
FIG. 4 is a diagram of a neural network model structure in an embodiment.
FIG. 5 is a graph of the convergence effect of the neural network model and the comparative model training in the embodiment.
FIG. 6 is a diagram showing the effect of positioning errors of the neural network model and the comparison model in the embodiment.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Most existing TCMS buses of electric locomotives take the form of train buses (WTBs) and Multifunction Vehicle Buses (MVBs). The train level bus realizes the control of the train level bus through the reconnection gateway, and the multifunctional vehicle bus realizes the control of the vehicle level bus through the main processing unit. The TCMS system topology is shown in fig. 1. The TCMS has the main function that all the sub-equipment units work in a mutual cooperation mode, and the sub-equipment units upload data of the sub-equipment units to the MPU through the vehicle bus so as to perform relevant logic control and realize safe and stable operation of the locomotive. The invention provides a rapid fault positioning method aiming at the problem that a fault source of a locomotive is difficult to accurately and efficiently position by analyzing and positioning the current situation of the fault of a network control system of an HXD2 electric locomotive by taking an HXD2 electric locomotive as an example. The positioning method can be popularized to other types of vehicles.
As shown in fig. 2, a method for locating a fault source of an electric locomotive includes acquiring operation data of a locomotive sub-equipment unit through a TCMS bus; and carrying out fault identification on the operation data through the trained fault source identification model to obtain a fault source automatic identification result. The fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the category to which the operation data belongs, and the fault source automatic identification result is the fault source data. Further, the method includes storing operational data of the locomotive sub-equipment unit.
Specifically, if a locomotive fails, the source of the failure must be located by the operational data. Therefore, a neural network model can be established, locomotive operation data is used as input, a fault source when the locomotive has a fault is used as output, the model is trained by using historical operation data of the locomotive and a previous fault source analysis conclusion, and the association relationship between the two is analyzed.
Preferably, the method utilizes an error back propagation neural network model (BP neural network) to train the historical operating data of the locomotive and the corresponding fault source and refine a correlation model between the operating data and the fault source. Fig. 4 constructs a simple neural network model.
Assuming that the number of neurons of an input layer, a hidden layer and an output layer of the neural network model is n, p and l respectively, an action function adopts a nonlinear sigmoid function, and an expression form is
f(x)=1/(1+e-x)
In the locomotive running dataThe items of data serve as input data for input layer neurons. Defining an input vector d ═ d for an input layer1,d2,...,dn]Wherein d isjRepresents the state of the input data j: when the item of input data is valid, djEqual to 1; when the input data is invalid, djEqual to 0.
And taking the fault source which is obtained by the previous analysis and corresponds to the operation data as the output data of the neuron of the output layer. Defining the corresponding output vector of the output layer as y ═ y1,y2,...,yl]Wherein, yiRepresents the state of the fault source i: when the failure source fails, yiEqual to 1, no fault, yiEqual to 0.
Then the output b of the hidden layer node is impliedij kCan be expressed as
In the above formula, wijRepresenting the associated weight between the input level node and the hidden level node, ai kRepresenting input data, [ theta ]jRepresenting the corresponding threshold for hidden layer j. The output of the corresponding output layer neuron nodeCan be expressed as
In the above formula, vkjRepresenting the associated weight, γ, between the hidden layer node and the output layer nodejRepresenting the corresponding threshold for output layer j.
Output from output layer neuron nodesWith the corresponding actual output vector y ═ y1,y2,...,yl]Difference of (2)For error function EkAdjusting the value to obtain the minimum value,can be expressed as
Then the error function EkCan be expressed as
Then, using a gradient descent method, w is calculatedik,θk,vkj,γjEach adjustment amount is
In the above formula, α and β represent hyper-parameters and are constant values. The main idea of the algorithm is to realize the back propagation of errors, and the correlation weight w between layers is calculated through the errorsikAnd vkjAnd (6) adjusting.
The scheme and effect of the invention are further illustrated by specific application examples.
Fig. 3 is a general block diagram of a locomotive fault source locating system applied to an electric locomotive in one embodiment. The TCMS ensures that the sub-equipment units work cooperatively, and the sub-equipment units upload data to the MPU through the vehicle bus so as to perform relevant logic control and realize safe and stable operation of the locomotive. Meanwhile, the MPU records the key operation data of the locomotive, and the key operation data is processed by a locomotive fault source positioning system, so that the fault source is positioned when the locomotive has problems.
In the embodiment, a neural network model shown in fig. 2 is applied, and in the neural network-based electric locomotive fault location model, the model takes various data in locomotive operation data as input, takes a locomotive fault source as output, analyzes the association relationship between a large amount of locomotive operation data obtained by accumulation in a real environment and a fault source conclusion obtained by analysis, and trains an effective locomotive fault location model. In the simulation process, 150 sets of operating data were used as sample data. Wherein 130 sets of operation data are used as training data of the model, and 20 sets of operation data are used as verification data for verifying the effectiveness of the model.
And taking the constructed BP neural network model as a basis, and adopting training data to train a fault positioning model. Meanwhile, a Radial Basis Function (RBF) neural network model is adopted as a comparison verification method.
FIG. 5 is a graph of the training effect of two models: as can be seen from the figure, the constructed BP neural network model tends to converge after approximately 160 iterations, and the RBF neural network model tends to converge after approximately 200 iterations; from this it can be concluded that: the training errors of both models gradually converge, and the errors gradually approach 0. This shows that the locomotive fault location model obtained by training the historical operating data of the locomotive by using the neural network algorithm is effective. Moreover, the convergence rate of the BP neural network model is higher than that of the RBF neural network model.
The method of the invention is subjected to effect verification by using 20 groups of locomotive running data as verification data. And using the two neural network models, taking verification data as input, obtaining a locomotive fault source through a fault positioning model, then comparing the locomotive fault source with a previously analyzed real fault source of the locomotive, wherein if the fault source positioned by the model is not deviated from the real fault source, the group of samples is recorded as 0, and if the fault source positioned by the model is inconsistent with the real fault source, the group of samples is recorded as 1.
FIG. 6 is a diagram of the effect of positioning the fault source of the training model, and it can be seen from the diagram that in 20 sets of verification data, the BP model has 1 positioning error; the RBF model has 3 cases of positioning errors. Therefore, the fault positioning accuracy of the BP model is higher than that of the RBF model.
Corresponding to the electric locomotive fault source positioning method in the application, the application also provides a hybrid enhanced physical examination report automatic generation device, and the electric locomotive fault source positioning device comprises: the device comprises an acquisition unit, an identification unit and a storage unit.
And the acquisition unit is used for acquiring the operation data of the locomotive sub-equipment unit through the TCMS bus.
The identification unit is used for carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data.
Further, the fault source identification model is an error back propagation neural network model;
the identification unit comprises a model training module, and the model training module is used for training the error back propagation neural network model by taking historical operation data as input data of an input layer neuron of the error back propagation neural network model and taking fault source data corresponding to the historical operation data as output data of an output layer neuron of the error back propagation neural network model.
Further, the training module is further configured to adjust an error function according to a difference between the output data of the output layer neuron of the error back propagation neural network model and the actual fault data, so that the error function is minimized.
Further, the training module is further configured to: and adjusting the structural parameters of the error back propagation neural network model according to the error function, wherein the structural parameters comprise the associated weight between the nodes of the input layer and the hidden layer, the corresponding threshold value of each node of the hidden layer, the associated weight between the nodes of the hidden layer and the nodes of the output layer and the corresponding threshold value of each node of the output layer.
For the embodiments of the present invention, the description is simple because it corresponds to the above embodiments, and for the related similarities, please refer to the description in the above embodiments, and the detailed description is omitted here.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for locating a fault source of an electric locomotive is characterized by comprising the following steps:
acquiring the operation data of the locomotive sub-equipment unit through the TCMS bus;
and carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, wherein the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data.
2. The electric locomotive fault source location method of claim 1, wherein the fault source identification model is an error back propagation neural network model, and the error back propagation neural network model is trained using historical operating data as input data for input layer neurons of the error back propagation neural network model and fault source data corresponding to the historical operating data as output data for output layer neurons of the error back propagation neural network model.
3. The electric locomotive fault source locating method according to claim 2, wherein the training the error back propagation neural network model using historical operation data as input data for input layer neurons of the error back propagation neural network model and actual fault source data corresponding to the historical operation data as output data for output layer neurons of the error back propagation neural network model comprises:
and adjusting an error function according to the difference value between the output data of the output layer neuron of the error back propagation neural network model and the actual fault data to make the error function reach the minimum.
4. The electric locomotive fault source locating method according to claim 3, wherein the training the error back propagation neural network model using historical operating data as input data for input layer neurons of the error back propagation neural network model and actual fault source data corresponding to the historical operating data as output data for output layer neurons of the error back propagation neural network model, further comprises:
and adjusting the structural parameters of the error back propagation neural network model according to the error function, wherein the structural parameters comprise the associated weight between the nodes of the input layer and the hidden layer, the corresponding threshold value of each node of the hidden layer, the associated weight between the nodes of the hidden layer and the nodes of the output layer and the corresponding threshold value of each node of the output layer.
5. The method of locating a source of an electric locomotive fault according to claim 1, further comprising: storing operational data of the locomotive sub-equipment unit.
6. An electric locomotive fault source locating device, comprising:
the acquiring unit is used for acquiring the operating data of the locomotive sub-equipment unit through the TCMS bus;
the identification unit is used for carrying out fault identification on the operation data through a trained fault source identification model to obtain a fault source automatic identification result, the fault source identification model is used for classifying the operation data to obtain fault source data corresponding to the class to which the operation data belongs, and the fault source automatic identification result is fault source data.
7. The electric locomotive fault source locating device of claim 6, wherein the fault source identification model is an error back propagation neural network model;
the identification unit comprises a model training module, and the model training module is used for training the error back propagation neural network model by taking historical operation data as input data of an input layer neuron of the error back propagation neural network model and taking fault source data corresponding to the historical operation data as output data of an output layer neuron of the error back propagation neural network model.
8. The electric locomotive fault source locating device of claim 7, wherein the training module is further configured to adjust an error function according to a difference between the output data of the output layer neurons of the error back propagation neural network model and the actual fault data to minimize the error function.
9. The electric locomotive fault source locating device of claim 8, wherein the training module is further configured to: and adjusting the structural parameters of the error back propagation neural network model according to the error function, wherein the structural parameters comprise the associated weight between the nodes of the input layer and the hidden layer, the corresponding threshold value of each node of the hidden layer, the associated weight between the nodes of the hidden layer and the nodes of the output layer and the corresponding threshold value of each node of the output layer.
10. The electric locomotive fault source locating device of claim 6, further comprising a storage module for storing operational data of the locomotive sub-equipment unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010694631.3A CN111830934A (en) | 2020-07-17 | 2020-07-17 | Electric locomotive fault source positioning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010694631.3A CN111830934A (en) | 2020-07-17 | 2020-07-17 | Electric locomotive fault source positioning method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111830934A true CN111830934A (en) | 2020-10-27 |
Family
ID=72923639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010694631.3A Pending CN111830934A (en) | 2020-07-17 | 2020-07-17 | Electric locomotive fault source positioning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111830934A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113746674A (en) * | 2021-08-27 | 2021-12-03 | 中车长春轨道客车股份有限公司 | TCMS network fault propagation analysis method based on SIR model |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6636841B1 (en) * | 1997-04-01 | 2003-10-21 | Cybula Ltd. | System and method for telecommunications system fault diagnostics |
CN102332089A (en) * | 2011-06-23 | 2012-01-25 | 北京康拓红外技术股份有限公司 | Railway wagon brake shoe key going-out fault recognition method based on artificial neural network |
CN106330535A (en) * | 2016-08-19 | 2017-01-11 | 北京全路通信信号研究设计院集团有限公司 | Vehicle-ground communication data processing method and device |
CN106470122A (en) * | 2016-09-20 | 2017-03-01 | 北京汇通金财信息科技有限公司 | A kind of network failure locating method and device |
CN108173929A (en) * | 2017-12-26 | 2018-06-15 | 中车大连机车车辆有限公司 | Wireless upload and expert diagnostic system of the medium-and low-speed maglev train based on TRDP agreements |
CN110068759A (en) * | 2019-05-22 | 2019-07-30 | 四川华雁信息产业股份有限公司 | A kind of fault type preparation method and device |
CN110426637A (en) * | 2019-07-04 | 2019-11-08 | 佛山科学技术学院 | A kind of battery failures diagnostic method neural network based and device |
CN110533167A (en) * | 2019-08-23 | 2019-12-03 | 中国石化销售有限公司华南分公司 | A kind of electric valve actuating mechanism method for diagnosing faults and diagnostic system |
CN110533549A (en) * | 2019-07-12 | 2019-12-03 | 杭州电子科技大学 | One kind optimizing RS-BP neural network electric network fault localization method based on GA |
CN111157898A (en) * | 2020-01-07 | 2020-05-15 | 清华大学深圳国际研究生院 | New energy vehicle online battery fault detection and analysis method and device |
CN111310907A (en) * | 2018-12-12 | 2020-06-19 | 北京理工大学 | Microwave assembly fault diagnosis method, device and equipment |
-
2020
- 2020-07-17 CN CN202010694631.3A patent/CN111830934A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6636841B1 (en) * | 1997-04-01 | 2003-10-21 | Cybula Ltd. | System and method for telecommunications system fault diagnostics |
CN102332089A (en) * | 2011-06-23 | 2012-01-25 | 北京康拓红外技术股份有限公司 | Railway wagon brake shoe key going-out fault recognition method based on artificial neural network |
CN106330535A (en) * | 2016-08-19 | 2017-01-11 | 北京全路通信信号研究设计院集团有限公司 | Vehicle-ground communication data processing method and device |
CN106470122A (en) * | 2016-09-20 | 2017-03-01 | 北京汇通金财信息科技有限公司 | A kind of network failure locating method and device |
CN108173929A (en) * | 2017-12-26 | 2018-06-15 | 中车大连机车车辆有限公司 | Wireless upload and expert diagnostic system of the medium-and low-speed maglev train based on TRDP agreements |
CN111310907A (en) * | 2018-12-12 | 2020-06-19 | 北京理工大学 | Microwave assembly fault diagnosis method, device and equipment |
CN110068759A (en) * | 2019-05-22 | 2019-07-30 | 四川华雁信息产业股份有限公司 | A kind of fault type preparation method and device |
CN110426637A (en) * | 2019-07-04 | 2019-11-08 | 佛山科学技术学院 | A kind of battery failures diagnostic method neural network based and device |
CN110533549A (en) * | 2019-07-12 | 2019-12-03 | 杭州电子科技大学 | One kind optimizing RS-BP neural network electric network fault localization method based on GA |
CN110533167A (en) * | 2019-08-23 | 2019-12-03 | 中国石化销售有限公司华南分公司 | A kind of electric valve actuating mechanism method for diagnosing faults and diagnostic system |
CN111157898A (en) * | 2020-01-07 | 2020-05-15 | 清华大学深圳国际研究生院 | New energy vehicle online battery fault detection and analysis method and device |
Non-Patent Citations (2)
Title |
---|
姜寅;任荭葳;陈凯;朱长江;: "基于BP神经网络的风电系统控制器I/O硬件故障自诊断方法", 华电技术, no. 05 * |
姜寅;任荭葳;陈凯;朱长江;: "基于BP神经网络的风电系统控制器I/O硬件故障自诊断方法", 华电技术, no. 05, 25 May 2020 (2020-05-25) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113746674A (en) * | 2021-08-27 | 2021-12-03 | 中车长春轨道客车股份有限公司 | TCMS network fault propagation analysis method based on SIR model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103914735B (en) | A kind of fault recognition method and system based on Neural Network Self-learning | |
US20200285900A1 (en) | Power electronic circuit fault diagnosis method based on optimizing deep belief network | |
CN110262463B (en) | Rail transit platform door fault diagnosis system based on deep learning | |
CN109141847B (en) | Aircraft system fault diagnosis method based on MSCNN deep learning | |
CN114585983B (en) | Method, device and system for detecting abnormal operation state of equipment | |
CN110728360A (en) | Micro-energy device energy identification method based on BP neural network | |
CN112433896B (en) | Method, device, equipment and storage medium for predicting server disk faults | |
CN112766618B (en) | Abnormality prediction method and device | |
CN115204302A (en) | Unmanned aerial vehicle small sample fault diagnosis system and method | |
CN111815056A (en) | Aircraft external field aircraft fuel system fault prediction method based on flight parameter data | |
CN115758208A (en) | Traction converter fault diagnosis method and device, computer equipment and storage medium | |
CN110188837A (en) | A kind of MVB network fault diagnosis method based on fuzzy neural | |
Gao et al. | IMA health state evaluation using deep feature learning with quantum neural network | |
CN116910574A (en) | Mechanical equipment diagnosis method and device based on meta-learning and time convolution network | |
CN114358085B (en) | Line fault diagnosis method and device based on heterogeneous model fusion | |
CN111830934A (en) | Electric locomotive fault source positioning method and device | |
CN112990329B (en) | System abnormality diagnosis method and device | |
CN114330571A (en) | Power system dominant instability mode identification method and system based on transfer learning | |
CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
CN113469013A (en) | Motor fault prediction method and system based on transfer learning and time sequence | |
Zhu et al. | Real-time fault diagnosis for EVs with multilabel feature selection and sliding window control | |
CN117075578A (en) | Vehicle fault analysis method and device, electronic equipment and storage medium | |
Zhou et al. | On vehicle fault diagnosis: A low complexity onboard method | |
CN115222160A (en) | Rail transit traction load prediction method based on measured big data | |
CN111885146B (en) | Data transmission method for industrial data cloud service platform |
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 |