CN112434832A - Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network - Google Patents
Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network Download PDFInfo
- Publication number
- CN112434832A CN112434832A CN202011425297.8A CN202011425297A CN112434832A CN 112434832 A CN112434832 A CN 112434832A CN 202011425297 A CN202011425297 A CN 202011425297A CN 112434832 A CN112434832 A CN 112434832A
- Authority
- CN
- China
- Prior art keywords
- detection
- weight
- fault
- detection method
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Optimization (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses an intelligent recommendation method of a vehicle fault detection scheme based on a Bayesian network, which comprises the steps of obtaining detection methods of fault reason nodes of an associated fault tree network, and setting category weight, effectiveness weight and relevance weight for each detection method according to the attributes of the detection methods; according to a recommendation engine, combining detection methods corresponding to the highest class weights in a first preset range to obtain optimal detection methods of all fault reason nodes; according to the result of executing the optimal detection method, the posterior probabilities of all fault reason nodes are obtained, and the probability that all detection method nodes are abnormal is updated; and inputting the probability, the class weight, the effectiveness weight and the relevance weight of the abnormal nodes of the residual detection method into a recommendation engine to obtain the next round of optimal detection method of the fault tree network. The intelligent recommendation method provided by the invention enables the process of constructing the detection method to be more intelligent, improves the troubleshooting efficiency and reduces the maintenance cost.
Description
Technical Field
The invention relates to the technical field of vehicle intelligent diagnosis, in particular to an intelligent recommendation method for a vehicle fault detection scheme based on a Bayesian network.
Background
At present, in order to reduce a maintenance threshold of a vehicle electric control system and improve maintenance efficiency, an artificial intelligence algorithm is usually introduced into a fault maintenance process of a commercial vehicle, so as to assist a technician in rapidly reasoning faults. However, such inspection methods generally fail to determine whether the inspection sequence is optimal, but rely entirely on the working experience of the technician, thereby resulting in inefficient troubleshooting procedures and increased maintenance costs.
Disclosure of Invention
The invention aims to provide an intelligent recommendation method of a vehicle fault detection scheme based on a Bayesian network, which is characterized in that probability sequencing of detection methods is performed under the condition that a current round of reasoning result is known, weighting calculation is performed by combining difficulty in an actual execution process, and an optimal detection method is finally obtained, so that the process of constructing the detection method is more intelligent, the troubleshooting efficiency is improved, and the maintenance cost is reduced.
In order to overcome the defects in the prior art, an embodiment of the present invention provides an intelligent recommendation method for a vehicle fault detection scheme based on a bayesian network, including:
acquiring detection methods of fault cause nodes of the associated fault tree network, and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
according to a recommendation engine, combining detection methods corresponding to the highest class weights in a first preset range to obtain optimal detection methods of all fault reason nodes;
according to the result of executing the optimal detection method, the posterior probabilities of all fault reason nodes are obtained, and the probability that all detection method nodes are abnormal is updated;
and inputting the probability that the nodes of the residual detection methods are abnormal, the class weight, the effectiveness weight and the relevance weight into the recommendation engine to obtain the next round of optimal detection method of the fault tree network.
Further, the attributes of the detection method include execution difficulty, execution cost, easy evaluation degree and execution mode; the execution mode comprises automatic execution, interactive detection and disassembly detection.
Further, the effectiveness weight comprises a timeliness weight, an economy weight and an evaluability weight.
Further, the recommendation engine comprises a Bayesian inference engine and a Bayesian self-learning engine.
An embodiment of the present invention further provides an intelligent recommendation apparatus for a vehicle fault detection scheme based on a bayesian network, including:
the fault tree network construction module is used for obtaining detection methods of fault reason nodes of the associated fault tree network and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
the optimal detection method recommendation module is used for combining the detection methods corresponding to the highest class weights in the first preset range according to the recommendation engine to obtain the optimal detection methods of all fault reason nodes;
the abnormal probability acquisition module is used for acquiring the posterior probabilities of all the fault reason nodes according to the result of executing the optimal detection method and updating the probabilities that all the detection method nodes are abnormal;
and the detection method updating module is used for inputting the probability that the nodes of the residual detection methods are abnormal, the category weight, the effectiveness weight and the relevance weight into the recommendation engine to obtain the next round of optimal detection method of the fault tree network.
Further, the attributes of the detection method include execution difficulty, execution cost, easy evaluation degree and execution mode; the execution mode comprises automatic execution, interactive detection and disassembly detection.
Further, the effectiveness weight comprises a timeliness weight, an economy weight and an evaluability weight.
Further, the recommendation engine comprises a Bayesian inference engine and a Bayesian self-learning engine.
An embodiment of the present invention further provides a computer terminal device, including:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the intelligent recommendation method for a Bayesian network based vehicle fault detection scheme as any one of the above.
An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the intelligent recommendation method for a bayesian network-based vehicle fault detection scheme as set forth in any of the above.
Compared with the prior art, the embodiment of the invention has at least the following beneficial effects:
1) a multidimensional weight factor is introduced, so that the recommendation of the detection method is more consistent with the actual maintenance process;
2) through calculation of the weighted recommendation index, the optimal path for fault maintenance is recommended intelligently, so that the fault maintenance process is simpler and more intelligent.
Drawings
Fig. 1 is a schematic flow chart of a bayesian network-based intelligent inference method of vehicle faults according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a fault tree network established based on fault codes P0087 according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a bayesian network-based intelligent vehicle fault inference device according to an embodiment of the present invention.
Detailed Description
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. 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.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
In a first aspect:
referring to fig. 1, an embodiment of the present invention provides an intelligent recommendation method for a vehicle fault detection scheme based on a bayesian network, including:
s10, obtaining detection methods of each fault reason node of the associated fault tree network, and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
s20, combining the detection methods corresponding to the highest class weights in the first preset range according to the recommendation engine to obtain the optimal detection methods of all fault reason nodes;
s30, according to the result of executing the optimal detection method, obtaining the probability that the current fault reason node is abnormal, and updating the probability that the residual fault reason node is abnormal;
and S40, inputting the probability that the nodes of the residual detection method are abnormal, the class weight, the effectiveness weight and the relevance weight into the recommendation engine to obtain the next round of optimal detection method of the fault tree network.
It should be noted that, in the conventional vehicle maintenance process, a technician manually infers the possibility of the cause of the failure based on the detection result by performing various detection methods, and the process is very similar to the bayesian network algorithm. The existing fault reasoning which is most similar to the fault reasoning method based on the decision tree is based on expert experience, a perfect fault tree network is established, the troubleshooting sequence of the fault tree network and the troubleshooting method of each node are determined, the branch of each node is determined through the troubleshooting method, the fault sample reason of the bottom layer is found out layer by layer in a downward reasoning mode. Therefore, if the fault cause is in a rear position, many unnecessary troubleshooting steps are wasted, the maintenance efficiency is greatly reduced, and the requirement for the technician per se is very high due to the strong logic of the fault tree network listed according to the manual experience, so that the maintenance based on the pure manual experience is increasingly difficult to meet the requirement of rapid fault handling of the vehicle owner. Therefore, the embodiment of the invention is based on a Bayesian network algorithm, an incidence relation Bayesian network model between the fault tree network and the detection method is established by utilizing work order data and expert experience which are generated by vehicle history, and in the fault reason reasoning process, the probability of each detection method is reversely inferred through the probability of each reason chain of the fault tree network, so that the probability sequence of each detection method under the condition of the known current round of reasoning result is obtained; on the basis, weighting calculation is carried out by combining the difficulty degree of the detection method in the actual execution process, meanwhile, weighting combination is carried out aiming at the detection methods supporting automatic detection and automatic judgment through a diagnostic apparatus or TBOX and other equipment, and finally the detection method with the highest comprehensive weighting probability is the optimal detection method recommended by the system. Through intelligent recommendation of the optimal detection method, technicians are helped to find an optimal maintenance way, fault maintenance time is shortened, maintenance cost is reduced, and maintenance efficiency is improved.
Furthermore, the bayesian network, also called belief network, is an extension of Bayes method, and is one of the most effective theoretical models in the field of uncertain knowledge expression and reasoning at present. A bayesian network is a Directed Acyclic Graph (DAG) consisting of nodes representing variables and Directed edges connecting these nodes. The nodes represent random variables, the directed edges among the nodes represent the mutual correlation system (the father node points to the son node), the relation strength is expressed by conditional probability, and the prior probability is used for expressing information without the father node. The node variables may be abstractions of any problem, such as: test values, observations, opinion polls, etc. The method is applicable to expressing and analyzing uncertain and probabilistic events, and to making decisions that are conditionally dependent on a variety of control factors, and can make inferences from incomplete, inaccurate, or uncertain knowledge or information.
In step S10 of this embodiment, it is first necessary to obtain a detection method for associating each fault cause node of the fault tree network, where the fault tree network is constructed by sorting out possible fault points based on big data and manual experience with data of historical worksheets and prompt information of service manuals, and then constructing each fault cause as a node, and the detection method for associating each fault cause node may be one or multiple, so that when constructing the detection scheme, it is actually a combination including the detected fault cause node and the detection method. The priority is that the fault reason node is determined first, and then the corresponding detection method is selected. The method for determining the fault cause node mainly comprises the steps of calculating the probability of possible occurrence according to historical data, wherein the priority of a detection sequence is higher than that of a detection sequence before the probability is lower; the first-time push detection method is mainly determined according to the weight of the detection method, and in the step, a category weight, an effectiveness weight and a relevance weight related to the previous detection method are set for each detection method according to the self attribute of the detection method;
furthermore, the attributes of the detection method include execution difficulty, execution cost, easy evaluation degree and execution mode; the execution mode comprises automatic execution, interactive detection and disassembly detection. It can be understood that the difficulty level, the execution cost, the easy evaluation level, and the execution mode all directly affect the recommendation index of the current detection method, and in the case that other conditions are uniform, generally, the easy execution priority is greater than the difficult execution priority, the low cost priority is greater than the high cost priority, the easy evaluation priority is greater than the difficult evaluation priority, and the execution mode is automatic priority greater than the interactive detection or the disassembly detection, so the weights of these attributes are integrated in step S10 to recommend the detection method, where the automatic execution refers to a method capable of performing fault detection automatically by a system or a detection device, the interactive detection refers to a method that requires combination of machine and manual detection, and a determination result is given under the interactive detection of the two.
Furthermore, the validity weight includes a timeliness weight, an economic weight, and an evaluability weight, that is, the validity of the detection method is determined by comprehensively considering the timeliness, economic cost, and evaluability of the detection method. And the weight of the relevance of the last detection method is also related, namely the higher the relevance of the last detection method is, the higher the occupied weight is.
After the step S10 is executed, the process proceeds to step S20, in this step, the optimal detection method of the first round of recommendation is selected according to the class weight of the detection method, mainly by setting a preset range, for example, the weight is 2-5, then the recommendation engine will automatically combine all detection methods with class weights within this preset range, and finally output an optimal detection method, wherein the recommendation engine is based on bayesian inference network, and includes a bayesian engine and a bayesian self-learning engine, the former is used for calculation based on big data, and the latter is used for updating and self-learning, continuously adjusting the recommended model, and improving the accuracy. After obtaining the optimal detection method, an operator executes the current fault point according to the currently recommended optimal detection method, and correspondingly, an execution result is obtained and fed back to the recommendation engine for processing, so in step S30, the probability that the current fault point is abnormal is first calculated, it should be noted that the first time the current fault cause node is selected to be executed is because the frequency of the history occurrence times is highest, that is, the machine algorithm based on the big data defaults to be the most probable fault point, and after the optimal detection method is adopted for detection, the fault cause node is found to be abnormal, which means that the troubleshooting process is ended, and meanwhile, the probability of the fault cause node detected next time can be updated by combining the current data with the history data. However, under normal circumstances, a fault point is not detected only once, that is, the current detection result is normal, the occurrence frequency of the node fault in the database is changed, and correspondingly, the probability of other fault cause nodes is also affected. Therefore, step S30 mainly obtains the probability that the failure cause node corresponding to the remaining detection method is abnormal, and then selects the node with the highest probability as the next failure detection node, and in step S40, the probability that the node of the remaining detection method is abnormal is input to the recommendation engine, and the system regenerates the optimal detection method of the next failure detection node according to the data, the category weight, the validity weight, and the relevance weight associated with the previous detection method until the failure point is found, and updates the prior probabilities of all nodes.
According to the embodiment of the invention, the optimal detection method is finally obtained by carrying out the probability sequencing of the detection methods under the condition that the current round of reasoning result is known and combining the difficulty level in the actual execution process to carry out the weighted calculation, so that the process of constructing the detection method is more intelligent, the troubleshooting efficiency is further improved, and the maintenance cost is reduced.
Referring to fig. 2, in order to help understand the present solution, in a certain embodiment, a recommendation of an optimal method based on a fault code P0087 is further provided, it is to be noted that in a maintenance and inspection process of the fault code P0087, a fault is locked between a fuel filter and a high-pressure oil pump through several rounds of inspection, a probability of the fault of the high-pressure oil pump is higher than a probability of the fault of the fuel filter, a detection method for inspecting the high-pressure oil pump should be preferentially recommended only in case of probability on a probability level, but actually, difficulty and cost for inspecting the high-pressure oil pump are much higher than those for inspecting the filter, and thus, consideration of various factors is required to recommend the optimal method.
In this embodiment, the detection methods are defined by weights, taking detection methods a and B as examples, and the index table of each weight of detection methods a and B is shown in table 1:
TABLE 1
After the detection method is subjected to weighted evaluation, the comprehensive recommendation index of the detection method A is found to be significantly higher than that of the detection method B, so that the detection method A is preferentially recommended in the detection of the first fault point. It should be noted that the detection method included in the recommendation engine is based on historical data and a maintenance manual, and if a new detection method priority influence factor is found in the maintenance process, the detection method priority influence factor can be manually added to the detection method recommendation engine at any time to correct the recommendation logic.
Furthermore, the technician obtains the first failure cause node to be normal through execution, then data are input into the reasoning engine, the reasoning engine can automatically update the failure probability of all the nodes, then the probability peak is taken as the first execution point, and meanwhile, the optimal detection method of the next failure cause node can be correspondingly updated for the next round of inspection until the failure is eliminated.
In a second aspect:
an embodiment of the present invention further provides an intelligent recommendation apparatus for a vehicle fault detection scheme based on a bayesian network, including:
the fault tree network building module 01 is used for obtaining detection methods associated with fault cause nodes of the fault tree network and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
the optimal detection method recommending module 02 is used for combining the detection methods corresponding to the highest class weights in the first preset range according to the recommending engine to obtain the optimal detection methods of all fault cause nodes;
an abnormal probability obtaining module 03, configured to obtain posterior probabilities of all fault cause nodes according to a result of executing the optimal detection method, and update probabilities that all detection method nodes are abnormal;
and the detection method updating module 04 is configured to input the probability that the nodes of the remaining detection methods are abnormal, the category weight, the validity weight, and the relevance weight to the recommendation engine, so as to obtain a next round of optimal detection method of the fault tree network.
It should be noted that, in this embodiment, the four modules respectively execute steps S10-S40, and when step S10 is executed, it is first required to obtain a detection method for associating fault cause nodes of a fault tree network, where the fault tree network is constructed by sorting out possible fault points for data of a historical work order and prompt information of a service manual based on big data and manual experience, and then constructing each fault cause as a node, and the detection method for associating each fault cause node may be one or multiple, so when constructing a detection scheme, it is actually a combination including a detected fault cause node and a detection method. The priority is that the fault reason node is determined first, and then the corresponding detection method is selected. The method for determining the fault cause node mainly comprises the steps of calculating the probability of possible occurrence according to historical data, wherein the priority of a detection sequence is higher than that of a detection sequence before the probability is lower; the first-time push detection method is mainly determined according to the weight of the detection method, and in the step, a category weight, an effectiveness weight and a relevance weight related to the previous detection method are set for each detection method according to the self attribute of the detection method;
furthermore, the attributes of the detection method include execution difficulty, execution cost, easy evaluation degree and execution mode; the execution mode comprises automatic execution, interactive detection and disassembly detection. It can be understood that the difficulty level, the execution cost, the easy evaluation level, and the execution mode all directly affect the recommendation index of the current detection method, and in the case that other conditions are uniform, generally, the easy execution priority is greater than the difficult execution priority, the low cost priority is greater than the high cost priority, the easy evaluation priority is greater than the difficult evaluation priority, and the execution mode is automatic priority greater than the interactive detection or the disassembly detection, so the weights of these attributes are integrated in step S10 to recommend the detection method, where the automatic execution refers to a method capable of performing fault detection automatically by a system or a detection device, the interactive detection refers to a method that requires combination of machine and manual detection, and a determination result is given under the interactive detection of the two.
Furthermore, the validity weight includes a timeliness weight, an economic weight, and an evaluability weight, that is, the validity of the detection method is determined by comprehensively considering the timeliness, economic cost, and evaluability of the detection method. And the weight of the relevance of the last detection method is also related, namely the higher the relevance of the last detection method is, the higher the occupied weight is.
After the step S10 is executed, the process proceeds to step S20, in this step, the optimal detection method of the first round of recommendation is selected according to the class weight of the detection method, mainly by setting a preset range, for example, the weight is 2-5, then the recommendation engine will automatically combine all detection methods with class weights within this preset range, and finally output an optimal detection method, wherein the recommendation engine is based on bayesian inference network, and includes a bayesian engine and a bayesian self-learning engine, the former is used for calculation based on big data, and the latter is used for updating and self-learning, continuously adjusting the recommended model, and improving the accuracy. After obtaining the optimal detection method, an operator executes the current fault point according to the currently recommended optimal detection method, and correspondingly, an execution result is obtained and fed back to the recommendation engine for processing, so in step S30, the probability that the current fault point is abnormal is first calculated, it should be noted that the first time the current fault cause node is selected to be executed is because the frequency of the history occurrence times is highest, that is, the machine algorithm based on the big data defaults to be the most probable fault point, and after the optimal detection method is adopted for detection, the fault cause node is found to be abnormal, which means that the troubleshooting process is ended, and meanwhile, the probability of the fault cause node detected next time can be updated by combining the current data with the history data. However, under normal circumstances, a fault point is not detected only once, that is, the current detection result is normal, the occurrence frequency of the node fault in the database is changed, and correspondingly, the probability of other fault cause nodes is also affected. Therefore, step S30 mainly obtains the probability that the failure cause node corresponding to the remaining detection method is abnormal, and then selects the node with the highest probability as the next failure detection node, and in step S40, the probability that the node of the remaining detection method is abnormal is input to the recommendation engine, and the system regenerates the optimal detection method of the next failure detection node according to the data, the category weight, the validity weight, and the relevance weight associated with the previous detection method until the failure point is found, and updates the prior probabilities of all nodes.
In a third aspect:
an embodiment of the present invention further provides a computer terminal device, including:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the intelligent recommendation method for a Bayesian network based vehicle fault detection scheme as described above.
The processor is used for controlling the overall operation of the computer terminal equipment so as to complete all or part of the steps of the intelligent recommendation method of the Bayesian network-based vehicle fault detection scheme. The memory is used to store various types of data to support the operation at the computer terminal device, which data may include, for example, instructions for any application or method operating on the computer terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The computer terminal Device may be implemented by one or more Application Specific integrated circuits (AS 1C), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components, and is configured to perform the intelligent recommendation method for the bayesian network-based vehicle fault detection scheme according to any of the embodiments described above, and achieve the technical effects consistent with the above methods.
An embodiment of the present invention further provides a computer readable storage medium including program instructions, which when executed by a processor, implement the steps of the intelligent recommendation method for a bayesian network based vehicle fault detection scheme as described in any of the above embodiments. For example, the computer readable storage medium may be the above-mentioned memory including program instructions executable by the processor of the computer terminal device to perform the intelligent recommendation method for the bayesian network based vehicle fault detection scheme according to any of the above-mentioned embodiments, and achieve the technical effects consistent with the above-mentioned method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. An intelligent recommendation method for a vehicle fault detection scheme based on a Bayesian network is characterized by comprising the following steps:
acquiring detection methods of fault cause nodes of the associated fault tree network, and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
according to a recommendation engine, combining detection methods corresponding to the highest class weights in a first preset range to obtain optimal detection methods of all fault reason nodes;
according to the result of executing the optimal detection method, the posterior probabilities of all fault reason nodes are obtained, and the probability that all detection method nodes are abnormal is updated;
and inputting the probability that the nodes of the residual detection methods are abnormal, the class weight, the effectiveness weight and the relevance weight into the recommendation engine to obtain the next round of optimal detection method of the fault tree network.
2. The intelligent Bayesian network-based vehicle fault detection scheme recommendation method according to claim 1, wherein the attributes of the detection method include execution difficulty, execution cost, ease of evaluation degree, execution manner; the execution mode comprises automatic execution, interactive detection and disassembly detection.
3. The intelligent Bayesian network-based vehicle fault detection scheme recommendation method as recited in claim 1, wherein the effectiveness weights comprise a timeliness weight, an economy weight, and an evaluability weight.
4. The intelligent Bayesian network-based vehicle fault detection scheme recommendation method as recited in claim 1, wherein said recommendation engine comprises a Bayesian inference engine and a Bayesian self-learning engine.
5. An intelligent recommendation device for a Bayesian network-based vehicle fault detection scheme, comprising:
the fault tree network construction module is used for obtaining detection methods of fault reason nodes of the associated fault tree network and setting a category weight, an effectiveness weight and an association weight for each detection method according to the attributes of the detection methods;
the optimal detection method recommendation module is used for combining the detection methods corresponding to the highest class weights in the first preset range according to the recommendation engine to obtain the optimal detection methods of all fault reason nodes;
the abnormal probability acquisition module is used for acquiring the posterior probabilities of all the fault reason nodes according to the result of executing the optimal detection method and updating the probabilities that all the detection method nodes are abnormal;
and the detection method updating module is used for inputting the probability that the nodes of the residual detection methods are abnormal, the category weight, the effectiveness weight and the relevance weight into the recommendation engine to obtain the next round of optimal detection method of the fault tree network.
6. The intelligent Bayesian network-based vehicle fault detection scheme recommendation device according to claim 5, wherein the attributes of the detection method include execution difficulty, execution cost, easy evaluation degree, execution manner; the execution mode comprises automatic execution, interactive detection and disassembly detection.
7. The intelligent Bayesian network-based vehicle fault detection scheme recommendation device as recited in claim 5, wherein the effectiveness weights comprise a timeliness weight, an economy weight, and an evaluability weight.
8. The intelligent Bayesian network-based vehicle fault detection scheme recommendation device as recited in claim 5, wherein the recommendation engine comprises a Bayesian inference engine and a Bayesian self-learning engine.
9. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the intelligent recommendation method for a Bayesian network based vehicle fault detection scheme of any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the intelligent recommendation method of the bayesian network based vehicle fault detection scheme according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425297.8A CN112434832B (en) | 2020-12-09 | 2020-12-09 | Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425297.8A CN112434832B (en) | 2020-12-09 | 2020-12-09 | Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112434832A true CN112434832A (en) | 2021-03-02 |
| CN112434832B CN112434832B (en) | 2021-08-17 |
Family
ID=74691757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011425297.8A Active CN112434832B (en) | 2020-12-09 | 2020-12-09 | Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112434832B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112036A (en) * | 2021-04-07 | 2021-07-13 | 东软睿驰汽车技术（沈阳）有限公司 | Data processing method and device for vehicle and computer equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426671A (en) * | 2011-07-29 | 2012-04-25 | 北京航星机器制造公司 | Optimal troubleshooting method based on comprehensive cost |
| CN107301296A (en) * | 2017-06-27 | 2017-10-27 | 西安电子科技大学 | Circuit breaker failure influence factor method for qualitative analysis based on data |
| CN107563069A (en) * | 2017-09-06 | 2018-01-09 | 国电联合动力技术有限公司 | A kind of wind power generating set intelligent fault diagnosis method |
| CN109657797A (en) * | 2018-12-24 | 2019-04-19 | 中国人民解放军32181部队 | Trouble diagnosibility analysis method based on hybrid diagnosis Bayesian network |
| CN110674468A (en) * | 2019-09-25 | 2020-01-10 | 郑州轻工业学院 | Quantitative analysis method for spun yarn breakage factor based on improved rough set algorithm |
| CN110968619A (en) * | 2019-11-28 | 2020-04-07 | 机械工业仪器仪表综合技术经济研究所 | Hydraulic press self-learning fault diagnosis method and system based on Fault Tree (FTA) |
| CN111027879A (en) * | 2019-12-17 | 2020-04-17 | 西安工程大学 | SOM-FAT-based cascading failure prediction method for power system |
| CN111931424A (en) * | 2020-08-12 | 2020-11-13 | 北京卫星环境工程研究所 | Abnormal data equalization processing method, device, equipment and storage medium |
| CN111950084A (en) * | 2020-08-11 | 2020-11-17 | 中国民航大学 | Implementation method of avionics fault diagnosis system for airborne route maintenance |
-
2020
- 2020-12-09 CN CN202011425297.8A patent/CN112434832B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426671A (en) * | 2011-07-29 | 2012-04-25 | 北京航星机器制造公司 | Optimal troubleshooting method based on comprehensive cost |
| CN107301296A (en) * | 2017-06-27 | 2017-10-27 | 西安电子科技大学 | Circuit breaker failure influence factor method for qualitative analysis based on data |
| CN107563069A (en) * | 2017-09-06 | 2018-01-09 | 国电联合动力技术有限公司 | A kind of wind power generating set intelligent fault diagnosis method |
| CN109657797A (en) * | 2018-12-24 | 2019-04-19 | 中国人民解放军32181部队 | Trouble diagnosibility analysis method based on hybrid diagnosis Bayesian network |
| CN110674468A (en) * | 2019-09-25 | 2020-01-10 | 郑州轻工业学院 | Quantitative analysis method for spun yarn breakage factor based on improved rough set algorithm |
| CN110968619A (en) * | 2019-11-28 | 2020-04-07 | 机械工业仪器仪表综合技术经济研究所 | Hydraulic press self-learning fault diagnosis method and system based on Fault Tree (FTA) |
| CN111027879A (en) * | 2019-12-17 | 2020-04-17 | 西安工程大学 | SOM-FAT-based cascading failure prediction method for power system |
| CN111950084A (en) * | 2020-08-11 | 2020-11-17 | 中国民航大学 | Implementation method of avionics fault diagnosis system for airborne route maintenance |
| CN111931424A (en) * | 2020-08-12 | 2020-11-13 | 北京卫星环境工程研究所 | Abnormal data equalization processing method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 马德仲等: "贝叶斯网络和模糊评判结合的滚动轴承故障诊断", 《哈尔滨理工大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112036A (en) * | 2021-04-07 | 2021-07-13 | 东软睿驰汽车技术（沈阳）有限公司 | Data processing method and device for vehicle and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112434832B (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418458B (en) | Intelligent vehicle fault reasoning method and system based on Bayesian network | |
| CN113282461B (en) | Alarm identification method and device for transmission network | |
| CN113935497A (en) | Intelligent operation and maintenance fault processing method, device and equipment and storage medium thereof | |
| CN113822388B (en) | Parameter setting method, device, electronic device and storage medium | |
| CN109861206B (en) | Transient power angle stability fault screening system and method based on support vector machine | |
| CN110062918A (en) | The method of software upgrading is carried out in gateway beyond the clouds, execute the computer program of this method and implements the processing unit of this method | |
| CN112434832B (en) | Intelligent recommendation method for vehicle fault detection scheme based on Bayesian network | |
| CN112580712A (en) | Fault processing aid decision method and system for relay protection device | |
| KR102641502B1 (en) | Apparatus and method for multi-model parallel execution automation and verification on digital twin | |
| CN116467674B (en) | Intelligent fault processing fusion updating system and method for power distribution network | |
| US10310929B2 (en) | Diagnosing combinations of failures in a system | |
| CN111971545A (en) | Diagnostic system and method for processing data of a motor vehicle | |
| CN110866634A (en) | Underground cable fault early warning method and device based on model selection | |
| CN113435699A (en) | Intelligent quality control method and system | |
| Mittal et al. | Prioritizing test cases for regression techniques using metaheuristic techniques | |
| CN115421950A (en) | Automatic system operation and maintenance management method and system based on machine learning | |
| CN109523030B (en) | Telemetering parameter abnormity monitoring system based on machine learning | |
| CN111524023A (en) | Greenhouse adjusting method and system | |
| CN115996169A (en) | Network fault analysis method and device, electronic equipment and storage medium | |
| CN116302774A (en) | Scheduling task monitoring method and device, electronic equipment and readable storage medium | |
| KR20230147359A (en) | Equipment system for predicting resin content of towpreg and recommending process conditions, and prediction and recommendation method using the same | |
| CN115166414A (en) | Power grid fault monitoring method and system | |
| CN114202500A (en) | Microscope system and method for monitoring the learning process of a machine learning model | |
| CN115764926B (en) | Power detection method and system for new energy station | |
| WO2023044907A1 (en) | Method and device for monitoring equipment health and computer readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |