CN118466447A - Vehicle-locomotive control fault diagnosis processing method and system - Google Patents
Vehicle-locomotive control fault diagnosis processing method and system Download PDFInfo
- Publication number
- CN118466447A CN118466447A CN202410603445.2A CN202410603445A CN118466447A CN 118466447 A CN118466447 A CN 118466447A CN 202410603445 A CN202410603445 A CN 202410603445A CN 118466447 A CN118466447 A CN 118466447A
- Authority
- CN
- China
- Prior art keywords
- fault
- vehicle
- vehicle control
- control function
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 21
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 230000006870 function Effects 0.000 claims abstract description 113
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000005540 biological transmission Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000007257 malfunction Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000003137 locomotive effect Effects 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A vehicle-to-vehicle fault diagnosis processing method and system relate to the field of Internet of vehicles, the method includes for each command of the vehicle control function, collecting the buried point information in each command transmission process, integrating the buried point information of each vehicle control function into corresponding buried point data, generating a first data set based on the buried point data of all the vehicle control functions; generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set; when the vehicle control function is called, the vehicle control function fault prediction model outputs a vehicle control fault result through the buried point data corresponding to the vehicle control function, wherein the result is a fault or non-fault comprising fault information; and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information. According to the invention, the matching degree of the solution and the fault problem is improved through the fault prediction model and the expert knowledge graph, so that the fault of the vehicle control function can be rapidly positioned and processed.
Description
Technical Field
The application relates to the field of Internet of vehicles, in particular to a vehicle-to-vehicle control fault diagnosis processing method and system.
Background
With the continuous development of the automobile industry, intellectualization, dynamization and networking have become new trends in the industry. As the functions carried by the vehicle control system are increasing, the problems that they create are also growing rapidly. In daily use, users often have difficulty in solving the problems by themselves, and only can resort to professional engineers of the vehicle enterprise, so that negative experience is caused for the users, and after-sales cost of the vehicle enterprise is increased.
In the related art, common fault analysis means include burying points in a vehicle system, searching an expert database for an approximate solution recommendation to a user through collected fault data, so as to deal with a vehicle control problem.
But by simply matching the fault data with the fault solution in the expert database, the matching degree of the obtained solution and the fault problem is low, and it is difficult for a user to quickly locate and process the fault in the vehicle control function through the obtained solution.
Disclosure of Invention
The application provides a vehicle-control fault diagnosis processing method and a vehicle-control fault diagnosis processing system, which can solve the problems that in the prior art, the matching degree of a vehicle-control fault solution and a fault problem is low, and further, the vehicle-control function fault is difficult to quickly locate and process.
In a first aspect, the present application provides a vehicle-to-vehicle control fault diagnosis processing method, including:
For commands of all vehicle control functions, collecting buried point information in the transmission process of each command, integrating the buried point information of each vehicle control function into corresponding buried point data, and generating a first data set based on the buried point data of all the vehicle control functions;
Generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set;
When the vehicle control function is called, the vehicle control function fault prediction model outputs a vehicle control fault result through the buried point data corresponding to the vehicle control function, wherein the result is a non-fault or fault comprising fault information;
and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
With reference to the first aspect, in an implementation manner, the collecting the embedded point information in each instruction transmission process and integrating the embedded point information of each vehicle control function into corresponding embedded point data includes:
when the instruction comprises a voice instruction and a vehicle-end instruction;
and after the command of each vehicle control function is initiated and before the execution of the command at the vehicle end is completed, collecting the embedded point information in the transmission process of the command, and integrating the embedded point information into embedded point data corresponding to the command.
With reference to the first aspect, in one implementation manner, the instruction transmission process includes:
When a user initiates an instruction of a vehicle control function, judging the type of the instruction;
if the instruction initiated by the user is detected to be a voice instruction, triggering voice awakening, analyzing the voice instruction into a vehicle-end instruction, and executing the vehicle-end instruction;
And if the instruction initiated by the user is detected to be the vehicle-end instruction, executing the vehicle-end instruction.
With reference to the first aspect, in an implementation manner, the generating the first data set based on the embedded point data of all the vehicle control functions includes:
And screening out partial buried point data from all the buried point data, and summarizing the partial buried point data into a first data set, wherein the partial buried point data comprises the buried point data with faults.
With reference to the first aspect, in an implementation manner, the generating a vehicle control function fault prediction model based on the first data set includes:
Marking fault codes and fault information on each piece of fault buried data in the first data set, and marking target codes and target information on each piece of fault buried data without faults to obtain a second data set;
and establishing, training and verifying a vehicle control function fault prediction model by using the second data set and a preset machine learning model.
With reference to the first aspect, in an implementation manner, the generating a vehicle control function fault prediction model based on the first data set further includes:
And retraining and verifying the vehicle control function fault prediction model every a first set time period.
With reference to the first aspect, in an implementation manner, the method for generating the expert knowledge graph includes:
marking corresponding fault information, fault codes and expert solutions for each buried data in the first data set to obtain a third data set;
the expert solution comprises longitude and latitude, time and expert opinion when the vehicle fails;
And generating an expert knowledge graph based on the third data set.
With reference to the first aspect, in an implementation manner, the processing, according to the fault information, the fault according to the expert solution matched in the expert knowledge graph includes:
and matching the approximate buried point data with similar fault information in an expert knowledge graph according to the fault information, and recommending expert solutions in the approximate buried point data to a user.
With reference to the first aspect, in an implementation manner, after the processing of the fault according to the expert solution matched in the expert knowledge graph, the method further includes:
if the fault of the vehicle control function is not repaired, corresponding fault information is marked on the buried point data when the vehicle control function is called, fault codes and expert solutions are adopted, and the marked buried point data are added to an expert knowledge graph.
In a second aspect, the present application provides a vehicle-to-vehicle control fault diagnosis processing system, including:
The information acquisition module is used for acquiring the embedded point information in the transmission process of each command for the command of each vehicle control function, integrating the embedded point information of each vehicle control function into corresponding embedded point data, and generating a first data set based on the embedded point data of all the vehicle control functions;
the cloud service module is used for generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set;
The vehicle end service module is used for outputting a vehicle control fault result through the embedded data corresponding to the vehicle control function by the vehicle control function fault prediction model when the vehicle control function is called, wherein the result is a fault which is non-fault or comprises fault information; and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
The technical scheme provided by the embodiment of the application has the beneficial effects that:
According to the application, the embedded point information of each vehicle control function is collected through the instructions of each vehicle control function in the transmission process of the instructions, the embedded point information of each vehicle control function is integrated into corresponding embedded point data, a first data set is generated based on the embedded point data of all the vehicle control functions, a vehicle control function fault prediction model and an expert knowledge map are generated based on the first data set, when the vehicle control function is called, the result of the vehicle control fault is predicted through the model, and an expert solution is matched in the expert knowledge map according to the fault information, so that the matching degree of the solution and the fault problem is improved, and the vehicle control function fault is rapidly positioned and processed.
Drawings
Fig. 1 is a schematic flow chart of a fault diagnosis and processing method for controlling a locomotive according to an embodiment of the present application.
Fig. 2 is a schematic diagram of voice wake-up of a vehicle-to-vehicle fault diagnosis processing method according to an embodiment of the present application.
Fig. 3 is a schematic diagram illustrating analysis of voice command of a vehicle-to-vehicle fault diagnosis processing method according to an embodiment of the present application.
Fig. 4 is a schematic diagram of executing a vehicle-end command of a vehicle-to-vehicle fault diagnosis processing method according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
First, some technical terms in the present application are explained so as to facilitate understanding of the present application by those skilled in the art.
TBOX (TELEMATICS BOX, remote communication terminal): the T-BOX is used as a wireless gateway, and provides a remote communication interface for the whole vehicle through functions of remote wireless communication, satellite positioning, acceleration sensing, communication and the like, and provides services including driving data acquisition, driving track recording, vehicle fault monitoring, vehicle remote inquiry and control (locking and unlocking, air conditioner control, vehicle window control, transmitter torque limitation, engine start and stop), driving behavior analysis, wireless hot spot sharing and the like.
TSP (TELEMATICS SERVICE Provider, car remote service Provider): the remote industry chain of the automobile is at the core position, and the remote industry chain of the automobile is connected with the automobile, the vehicle-mounted equipment manufacturer, the network operator and the content provider. The automobile remote service integrates the modern computer technology such as location service, map service, communication service and the like, and provides powerful services for owners and individuals.
IOT (Internet of Things ): based on information carriers such as Internet, traditional telecommunication network, etc., all common physical objects which can be addressed independently are interconnected and intercommunicated.
XGBoost (eXtreme Gradient Boosting, extreme gradient boost): the engineering implementation of the machine learning algorithm has the characteristics of high efficiency, flexibility and portability.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flow chart illustrating a vehicle-to-vehicle fault diagnosis processing method according to the present application. The embodiment provides a vehicle-locomotive control fault diagnosis processing method, which comprises the following steps:
Step S1: and collecting buried point information in each command transmission process for commands of each vehicle control function, integrating the buried point information of each vehicle control function into corresponding buried point data, and generating a first data set based on the buried point data of all the vehicle control functions.
Specifically, the above-mentioned various car control functions include a voice car control function and a basic car control function. The voice car control function comprises the functions of voice control car windows, voice control skylights, voice control atmosphere lamps, voice control seat heating, voice control seat ventilation and the like. The basic car control functions comprise functions of controlling car windows, controlling skylights, controlling atmosphere lamps, controlling seat heating, controlling seat ventilation and the like.
The above instructions for each vehicle control function refer to instructions initiated by the user for different vehicle control functions. For example, the user controls window closure by voice, i.e., is considered as an instruction by the user to initiate a voice-controlled window function.
In some embodiments, the instructions of the vehicle control function include a voice instruction and a vehicle end instruction, and the collecting the embedded point information of each vehicle control function and integrating the embedded point information into corresponding embedded point data specifically includes:
and collecting and storing all embedded point information in the transmission process of the command from the initiation of the command of each vehicle control function to the completion of the execution of the command at the vehicle end, and integrating the embedded point information into embedded point data corresponding to the command.
In some embodiments, the above instruction transmission process includes the steps of:
Step S11, when a user initiates an instruction of a vehicle control function, judging whether the instruction type is a voice instruction or a vehicle end instruction, and if the instruction type is the voice instruction, entering step S12; if it is the vehicle-end instruction, the process proceeds to step S13.
And S12, triggering voice awakening, analyzing the voice instruction into a vehicle-end instruction, and executing the vehicle-end instruction.
And S13, directly executing the vehicle-end instruction.
Referring to fig. 2, fig. 2 is a schematic voice wake-up diagram in the above step S12, and the voice wake-up process further includes the following steps:
In step S121, after a user initiates a voice command, a vehicle-mounted voice SDK (Software Development Kit ) generates a unique ID, invokes a voice cloud platform wake-up interface, generates buried point information 1 based on the unique ID, a vehicle VIN (Vehicle Identification Number, a vehicle identification code), invoking interface information, voice content and possibly existing fault information, and stores the buried point information 1 in a database.
Step S122, the voice cloud platform feeds back the awakening result to the vehicle voice SDK, generates buried point information 2 based on the unique ID, the vehicle VIN code, the voice awakening result and possibly existing fault information, and stores the buried point information 2 into a database.
Specifically, referring to fig. 3, fig. 3 is a schematic diagram illustrating analysis of a voice command in a vehicle-to-vehicle fault diagnosis processing method according to the present application, wherein the step S12 of analyzing the voice command into a vehicle-end command includes the following steps:
step S123, after voice awakening, the vehicle-mounted voice SDK invokes an instruction analysis interface of the voice cloud platform, generates buried point information 3 based on the unique ID, the vehicle VIN code, voice instruction content and possibly existing fault information, and stores the buried point information 3 into a database.
In step S124, the voice cloud platform analyzes the voice command into a vehicle-end command, feeds back the voice command analysis result to the user after the command analysis is completed, generates buried point information 4 based on the unique ID, the vehicle VIN code, the voice command analysis result and possibly existing fault information, and stores the buried point information 4 in a database.
In step S125, the voice cloud platform transmits the voice command analysis result to the voice SDK, generates buried point information 5 based on the unique ID, the vehicle VIN code, the vehicle end command and possibly existing fault information, and stores the buried point information 5 in the database.
In step S126, after receiving the vehicle-end instruction, the voice SDK transmits the received result to the voice cloud platform, generates buried point information 6 based on the unique ID, the vehicle VIN code, the received result of the vehicle-end instruction by the voice SDK and possible fault information, and stores the buried point information 6 in a database.
In step S127, the voice SDK transmits the vehicle-end instruction to the vehicle-controlled SDK, generates buried point information 7 based on the unique ID, the vehicle VIN code, the vehicle-end instruction and possibly existing fault information, and stores the buried point information 7 in a database.
And S128, after the vehicle-to-vehicle control SDK receives the analyzed voice command, transmitting the receiving result to the voice SDK, generating buried point information 8 based on the unique ID, the vehicle VIN code, the receiving result of the vehicle-to-vehicle control SDK on the vehicle-end command and possible fault information, and storing the buried point information 8 into a database.
Specifically, referring to fig. 4, fig. 4 is a schematic diagram illustrating execution of a vehicle end command in a vehicle-to-vehicle fault diagnosis processing method according to the present application, and the execution of the vehicle end command in the step S12 includes the following steps:
Step S129, the vehicle control SDK calls a TSP cloud platform vehicle control function interface, generates buried point information 9 based on the unique ID, the vehicle VIN code, the vehicle end instruction and possibly existing fault information, and stores the buried point information 9 in a database.
In step S1210, the TSP cloud platform transmits the response information to the vehicle control SDK, generates buried point information 10 based on the unique ID, the vehicle VIN code, the response information of the TSP cloud platform and possible fault information, and stores the buried point information 10 in a database.
Step S1211: the TSP cloud platform invokes the vehicle-cloud IOT connection platform, generates buried point information 11 based on the unique ID, the vehicle VIN code, the vehicle-side instruction, and possibly fault information, and stores the buried point information 11 in a database.
Step S1212: the vehicle-cloud IOT connection platform returns response information, generates buried point information 12 based on the unique ID, the vehicle VIN code, the response information of the vehicle-cloud IOT connection platform, and possibly existing fault information, and stores the buried point information 12 to a database.
Step S1213: the vehicle-cloud IOT connection platform sends a vehicle-side command to the TBOX, generates buried point information 13 based on the unique ID, the vehicle VIN code, the vehicle-side command, and possibly existing fault information, and stores the buried point information 13 in the database.
Step S1214: the TBOX returns response information, generates buried point information 14 based on the unique ID, the vehicle VIN code, the response information of the TBOX, and possibly existing fault information, and stores the buried point information 14 to a database.
Step S1215: the TBOX issues a vehicle control message to each controller, generates buried point information 15 based on the unique ID, the vehicle VIN code, the vehicle control message and possibly existing fault information, and stores the buried point information 15 in a database.
Step S1216: each controller sends a reply message to the TBOX, generates buried point information 16 based on the unique ID, the vehicle VIN code, the reply message, and possibly fault information, and stores the buried point information 16 to the database.
Step S1217: after each controller finishes executing, the executing message is sent to the TBOX, the embedded point information 17 is generated based on the unique ID, the vehicle VIN code, the controller executing message and possible fault information, and the embedded point information 17 is stored in the database.
Step S1218: after the TBOX receives the controller execution message, the TBOX execution message is sent to the vehicle-cloud IOT platform, and buried point information 18 is generated based on the unique ID, the vehicle VIN code, the controller execution message and possibly existing fault information, and the buried point information 18 is stored in the database.
Step S1219: after receiving the TBOX execution message, the vehicle-cloud IOT connection platform sends the execution information to the TSP cloud platform and the large data platform, generates buried point information 19 based on the unique ID, the vehicle VIN code, the execution information and possibly existing fault information, and stores the buried point information 19 in the database.
It should be noted that, if the vehicle control instruction initiated by the user is a voice instruction, all the embedded point information (the embedded point information 1 to the embedded point information 19) stored in the database in steps S121 to S1219 are integrated into one piece of embedded point data, and the embedded point data is stored in the database as the embedded point data corresponding to the current instruction.
Specifically, referring to fig. 4, if it is detected that the instruction initiated by the user is a vehicle-end instruction, the vehicle-end instruction is directly executed in step S13, and then the vehicle-end instruction is directly executed according to steps S129 to S1219.
If the vehicle control command initiated by the user is a vehicle end command, all the embedded point information (the embedded point information 9 to the embedded point information 19) stored in the database in steps S129 to S1219 are integrated into one piece of embedded point data, and the piece of embedded point data is stored in the database as the embedded point data corresponding to the current command.
In some embodiments, in the step S1, generating the first data set based on the buried data of all the vehicle control functions includes:
And screening out partial buried point data from all the buried point data, and summarizing the partial buried point data into a first data set, wherein the partial buried point data comprises the buried point data with faults.
Specifically, buried point data in which a fault exists refers to buried point data in which fault information exists.
In some more preferred embodiments, the first dataset is summarized in the following manner:
The first N pieces of buried point data are screened out from all pieces of buried point data, M pieces of fault data are contained in the N pieces of buried point data, and the M pieces of fault data contain 70% of all fault types, and N is more than M. Therefore, the scale of the data set can be reduced without affecting the model precision, and the operand in model training is reduced.
And step S2, generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set.
In some embodiments, generating a vehicle control malfunction prediction model based on the first data set includes:
step S21: and marking fault codes and fault information on each piece of fault buried data in the first data set, and marking target codes and target information on each piece of fault buried data in the first data set so as to obtain a second data set.
Step S22: and establishing, training and verifying a vehicle control function fault prediction model by using the second data set and a preset machine learning model.
It should be noted that, the buried data with a fault may have one or more faults, so one or more fault codes and corresponding fault information need to be marked when marking.
It should be noted that, the fault information includes a fault type, where the fault type and the fault code are in a one-to-one correspondence, for example, the fault type is TBOX, the TBOX resource abnormality is reported, and the corresponding fault code is 25. The target code has uniqueness, is a value which is not repeated with all fault codes, and the target information is that no fault exists.
In this embodiment, the step S22 of establishing, training and verifying the vehicle control function failure prediction model by using the second data set and the preset machine learning model includes:
step S221: and performing data processing on the buried data in the second data set, and then dividing the second data set into a training set and a testing set.
The vehicle VIN code, the unique ID and the buried point information of all the buried point data in the second data set are taken as characteristic values, and the fault code is taken as a target value, so that the characteristic values of the non-digital type are required to be processed into the digital type for training, and meanwhile, the fault code is required to be processed.
After the non-digital type feature value and fault coding process is completed, 80% of the buried data in the second data set is used as a training set, and the remaining 20% of the buried data is used as a test set.
In this embodiment, the method for processing the feature value of the non-digital type into the digital type is as follows:
for 19 pieces of buried point information of one piece of buried point data, 50 information types are preset for each piece of buried point information, for buried point information 1, the preset information type codes are 1-50, for coded information 2, the preset information type codes are 51-100, and so on. And replacing all the buried point information in the buried point data with corresponding information type codes.
In this embodiment, for the processing method of the fault code, reference is made to formula (1):
in the formula (1), Y Before treatment is the average value of fault codes in one piece of buried point data, y After treatment is the fault code before processing, and y After treatment is the fault code after processing.
Step S222: and (3) establishing and training a vehicle control function fault prediction model based on the preset machine learning model and the training set in the step S221.
The preset machine learning model may be XGBoost or other machine learning models.
Step S223: based on the vehicle control function failure prediction model trained in step S222 and the test set in step S221, the accuracy of the vehicle control function failure prediction model trained in step S222 is verified, and the evaluation index of the accuracy of the vehicle control function failure prediction model is R 2 standard, referring to formula (2).
Y i in the formula (2) is the fault code of the ith buried point data of the test set,The ith fault code predicted by the vehicle control function fault prediction model,To test the average value of the i-th buried point data fault codes in the test set, if R 2 is greater than 0.9, it indicates that the training of the vehicle control function fault prediction model is successful, and if R 2 is less than 0.9, it indicates that the training of the vehicle control function fault prediction model fails, and step S222 needs to be executed again.
It should be noted that, the foregoing vehicle control malfunction prediction model may be generated through step S21 and step S22, or may be generated directly through the first data set, and the accuracy of the model for predicting the vehicle control malfunction may be improved by generating the vehicle control malfunction prediction model through step S21 and step S22.
In some embodiments, generating a vehicle control function failure prediction model based on the first data set in step S2 further includes:
And retraining and verifying the vehicle control function fault prediction model every a first set time period.
The retraining and verifying the model refers to retraining and verifying the model based on the vehicle control function fault prediction model in the last set time period. The first set period of time may be one week or any set period of time.
In some embodiments, the method for generating the expert knowledge graph in step S2 includes:
Marking corresponding fault information, fault codes and expert solutions for each buried data in the first data set to obtain a third data set; and generating an expert knowledge graph based on the third data set. The expert solution comprises longitude and latitude, time and expert opinion when the vehicle fails.
It should be noted that, the expert solution includes longitude, latitude and time when the vehicle fails, so as to increase the matching degree of the failure and the solution, and ensure that the user can find a more accurate expert opinion to solve the failure according to the failure condition, position and time of the vehicle. The time may be recorded in units of months or in more accurate units of time.
Step S3: when the vehicle control function is called, the vehicle control function fault prediction model outputs a vehicle control fault result through the buried point data corresponding to the vehicle control function, wherein the result is a non-fault or fault comprising fault information.
Specifically, the results of the vehicle control faults are two types, namely faults or non-faults, when the results are faults, the vehicle control function fault prediction model can give out predicted fault information, and when the results are non-faults, the vehicle control function fault prediction model cannot give out fault information because no faults exist.
Step S4: and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
In some embodiments, the processing the fault according to the expert solutions matched in the expert knowledge graph according to the fault information includes:
and matching the approximate buried point data with similar fault information in an expert knowledge graph according to the fault information, and recommending expert solutions in the approximate buried point data to a user.
It should be noted that, for the predicted fault information, text comparison is performed with the fault information in the real buried point data in the expert knowledge graph, and after the deviation is corrected, the expert solution in the buried point data with similar fault information is recommended to the user. Therefore, the matching degree of the faults and the solutions can be increased, and a user can conveniently and rapidly locate and process the vehicle control faults.
In some embodiments, after the fault is processed according to the expert solutions matched in the expert knowledge graph, the method further includes:
if the fault of the vehicle control function is not repaired, corresponding fault information is marked on the buried point data when the vehicle control function is called, fault codes and expert solutions are adopted, and the marked buried point data are added to an expert knowledge graph.
In a second aspect, an embodiment of the present application provides a system for diagnosing and processing a failure of controlling a vehicle and a locomotive, the system including:
The information acquisition module is used for acquiring the embedded point information in the transmission process of each command for the command of each vehicle control function, integrating the embedded point information of each vehicle control function into corresponding embedded point data, and generating a first data set based on the embedded point data of all the vehicle control functions;
the cloud service module is used for generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set;
The vehicle end service module is used for outputting a vehicle control fault result through the embedded point data corresponding to the vehicle control function by the vehicle control function fault prediction model when the vehicle control function is called, wherein the result is a fault or non-fault comprising fault information; and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
It should be noted that, the foregoing reference numerals of the embodiments of the present application are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments.
The terms "comprising" and "having" and any variations thereof in the description and claims of the application and in the foregoing drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus. The terms "first," "second," and "third," etc. are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order, and are not limited to the fact that "first," "second," and "third" are not identical.
In describing embodiments of the present application, "exemplary," "such as," or "for example," etc., are used to indicate by way of example, illustration, or description. Any embodiment or design described herein as "exemplary," "such as" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "such as" or "for example," etc., is intended to present related concepts in a concrete fashion.
In the description of the embodiments of the present application, unless otherwise indicated, "/" means or, for example, a/B may represent a or B; the text "and/or" is merely an association relation describing the associated object, and indicates that three relations may exist, for example, a and/or B may indicate: the three cases where a exists alone, a and B exist together, and B exists alone, and furthermore, in the description of the embodiments of the present application, "plural" means two or more than two.
In some of the processes described in the embodiments of the present application, a plurality of operations or steps occurring in a particular order are included, but it should be understood that the operations or steps may be performed out of the order in which they occur in the embodiments of the present application or in parallel, the sequence numbers of the operations merely serve to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. In addition, the processes may include more or fewer operations, and the operations or steps may be performed in sequence or in parallel, and the operations or steps may be combined.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising several instructions for causing a terminal device to perform the method according to the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The vehicle-locomotive control fault diagnosis processing method is characterized by comprising the following steps of:
For commands of all vehicle control functions, collecting buried point information in the transmission process of each command, integrating the buried point information of each vehicle control function into corresponding buried point data, and generating a first data set based on the buried point data of all the vehicle control functions;
Generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set;
When the vehicle control function is called, the vehicle control function fault prediction model outputs a vehicle control fault result through the buried point data corresponding to the vehicle control function, wherein the result is a non-fault or fault comprising fault information;
and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
2. The method for diagnosing and processing a vehicle-control fault as claimed in claim 1, wherein said collecting the embedded point information in each command transmission process, integrating the embedded point information of each vehicle-control function into corresponding embedded point data, comprises:
the instruction comprises a voice instruction and a vehicle end instruction;
and after the command of each vehicle control function is initiated and before the execution of the command at the vehicle end is completed, collecting the embedded point information in the transmission process of the command, and integrating the embedded point information into embedded point data corresponding to the command.
3. The vehicle-to-vehicle fault diagnosis processing method according to claim 2, wherein the instruction transmission process includes:
When a user initiates an instruction of a vehicle control function, judging the type of the instruction;
if the instruction initiated by the user is detected to be a voice instruction, triggering voice awakening, analyzing the voice instruction into a vehicle-end instruction, and executing the vehicle-end instruction;
And if the instruction initiated by the user is detected to be the vehicle-end instruction, executing the vehicle-end instruction.
4. The method for diagnosing and processing a vehicle-controlled fault as recited in claim 1, wherein said generating a first data set based on the buried data of all the vehicle-controlled functions includes:
And screening out partial buried point data from all the buried point data, and summarizing the partial buried point data into a first data set, wherein the partial buried point data comprises the buried point data with faults.
5. The method of claim 1, wherein generating a vehicle control function fault prediction model based on the first data set comprises:
Marking fault codes and fault information on each piece of fault buried data in the first data set, and marking target codes and target information on each piece of fault buried data without faults to obtain a second data set;
and establishing, training and verifying a vehicle control function fault prediction model by using the second data set and a preset machine learning model.
6. The method for diagnosing and processing a vehicle control failure as recited in claim 5, wherein said generating a vehicle control function failure prediction model based on said first data set further comprises:
And retraining and verifying the vehicle control function fault prediction model every a first set time period.
7. The vehicle-to-vehicle fault diagnosis processing method according to claim 1, wherein the expert knowledge graph generation method comprises:
marking corresponding fault information, fault codes and expert solutions for each buried data in the first data set to obtain a third data set;
the expert solution comprises longitude and latitude, time and expert opinion when the vehicle fails;
And generating an expert knowledge graph based on the third data set.
8. The method for diagnosing and processing a vehicle-control fault as claimed in claim 1, wherein said processing a fault according to the expert solutions matched in the expert knowledge graph based on the fault information comprises:
and matching the approximate buried point data with similar fault information in an expert knowledge graph according to the fault information, and recommending expert solutions in the approximate buried point data to a user.
9. The method for diagnosing and processing a vehicle-to-vehicle fault as claimed in claim 8, wherein said processing the fault according to the expert solutions matched in the expert knowledge graph further comprises:
If the fault of the vehicle control function is not repaired, marking corresponding fault information, fault codes and expert solutions for the buried point data when the vehicle control function is called, and adding the marked buried point data to an expert knowledge graph.
10. A vehicle-to-vehicle fault diagnosis processing system, characterized in that the vehicle-to-vehicle fault diagnosis processing system comprises:
The information acquisition module is used for acquiring the embedded point information in the transmission process of each command for the command of each vehicle control function, integrating the embedded point information of each vehicle control function into corresponding embedded point data, and generating a first data set based on the embedded point data of all the vehicle control functions;
the cloud service module is used for generating a vehicle control function fault prediction model and an expert knowledge graph based on the first data set;
The vehicle end service module is used for outputting a vehicle control fault result through the embedded data corresponding to the vehicle control function by the vehicle control function fault prediction model when the vehicle control function is called, wherein the result is a non-fault or fault comprising fault information; and processing the faults according to the expert solutions matched in the expert knowledge graph according to the fault information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410603445.2A CN118466447A (en) | 2024-05-15 | 2024-05-15 | Vehicle-locomotive control fault diagnosis processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410603445.2A CN118466447A (en) | 2024-05-15 | 2024-05-15 | Vehicle-locomotive control fault diagnosis processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118466447A true CN118466447A (en) | 2024-08-09 |
Family
ID=92163185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410603445.2A Pending CN118466447A (en) | 2024-05-15 | 2024-05-15 | Vehicle-locomotive control fault diagnosis processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118466447A (en) |
-
2024
- 2024-05-15 CN CN202410603445.2A patent/CN118466447A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563214B (en) | Vehicle diagnosis method, device and equipment | |
| CN108803580B (en) | Method for matching vehicle CAN protocol and related equipment | |
| CN108773373B (en) | Method and device for operating an autonomous vehicle | |
| US6643600B2 (en) | Method and system for assessing adjustment factors in testing or monitoring process | |
| US20100063668A1 (en) | Telematics-enabled aggregated vehicle diagnosis and prognosis | |
| US20090306849A1 (en) | System for diagnosis of motor vehicles, and for reception of vehicles at a repair facility | |
| CN112925296B (en) | Graphical vehicle-mounted network diagnosis method based on artificial intelligence | |
| CN111182503A (en) | Intelligent vehicle insurance evaluation method and system based on multi-data fusion analysis | |
| DE102018209773A1 (en) | Process for computer-aided determination of a fault diagnosis of a vehicle | |
| KR101282417B1 (en) | Apparatus and method for making CAN data file for test | |
| CN113126589A (en) | Vehicle-mounted self-diagnosis method, vehicle-mounted intelligent system and self-diagnosis system | |
| CN112455460B (en) | Vehicle control method, device, equipment and storage medium | |
| CN118466447A (en) | Vehicle-locomotive control fault diagnosis processing method and system | |
| US7194372B2 (en) | Method and system for verifying an embedded module of a mobile vehicle | |
| CN106444724A (en) | Intelligent vehicle diagnosis method | |
| CN112559000B (en) | Whole vehicle software updating method and device for vehicle | |
| CN116741175A (en) | Block chain-based intelligent data transmission supervision system and method | |
| CN115842861A (en) | Edge connection device adaptation method, device and computer readable storage medium | |
| CN115265566A (en) | Automatic driving positioning data collecting and processing method, device, medium and vehicle | |
| CN114879630A (en) | Vehicle fault diagnosis method, device, equipment and readable storage medium | |
| RU2724596C1 (en) | Method, apparatus, a central device and a system for recognizing a distribution shift in the distribution of data and / or features of input data | |
| CN114510505A (en) | Vehicle fault processing method and device and storage medium | |
| CN115695237A (en) | Vehicle-end network detection method and system, electronic equipment and readable storage medium | |
| CN113945393A (en) | Vehicle safety early warning method and device, electronic equipment and storage medium | |
| CN118277929A (en) | Method and system for data analysis for vehicle road testing |
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 |