CN116400672A - Remote vehicle diagnosis method and system based on knowledge graph and rule engine - Google Patents
Remote vehicle diagnosis method and system based on knowledge graph and rule engine Download PDFInfo
- Publication number
- CN116400672A CN116400672A CN202310487489.9A CN202310487489A CN116400672A CN 116400672 A CN116400672 A CN 116400672A CN 202310487489 A CN202310487489 A CN 202310487489A CN 116400672 A CN116400672 A CN 116400672A
- Authority
- CN
- China
- Prior art keywords
- log
- knowledge graph
- rule
- knowledge
- graph
- 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 50
- 238000000034 method Methods 0.000 title abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 97
- 238000012216 screening Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims description 22
- 238000013145 classification model Methods 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000012423 maintenance Methods 0.000 claims description 11
- 238000002405 diagnostic procedure Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 40
- 230000003993 interaction Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000013024 troubleshooting Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—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)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention relates to the technical field of vehicle diagnosis, in particular to a remote vehicle diagnosis method and system based on a knowledge graph and a rule engine, wherein the method comprises the following steps: acquiring a sample vehicle running log and screening a sample abnormal log; establishing a knowledge graph comprising a sample abnormal entity and a path for generating the sample abnormal entity; constructing a rule base according to the sample abnormal log and the knowledge graph; collecting a target running log of a vehicle to be diagnosed, and screening out a target abnormal log of the vehicle to be diagnosed; inputting the target abnormal log of the vehicle to be diagnosed into a rule engine loaded with the rule base, matching the target abnormal entity in the knowledge graph, and then matching a path which leads to the generation of the target abnormal entity to obtain a diagnosis result. The method and the system realize the effect of fully utilizing the running logs and utilizing the rule engine technology loaded with the rule base to quickly locate faults.
Description
Technical Field
The invention relates to the technical field of vehicle diagnosis, in particular to a remote vehicle diagnosis method and system based on a knowledge graph and a rule engine.
Background
With the rapid development of the fields of intelligent networking, electronic integration and the like, faults and data generated by automobiles are rapidly increased. The running log is the maximum and most comprehensive data generated by the automobile, and various automobile faults are presented in the log.
The traditional automobile diagnosis is finished in a 4S shop through a diagnostic instrument, the diagnostic instrument has less detection data and low multiplexing rate of diagnostic results, and effective and unified diagnosis experience knowledge cannot be formed for reference.
How to fully utilize the running logs and establish a standard shared knowledge base and quickly locate the fault cause is a problem to be solved.
Disclosure of Invention
The invention aims to provide a remote vehicle diagnosis method based on a knowledge graph and a rule engine, which solves the problems that how to fully utilize a vehicle log, establish a standard shared knowledge base and quickly locate fault causes in the prior art; and the second object is to provide a remote vehicle diagnosis system based on a knowledge graph and a rule engine.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a remote vehicle diagnosis method based on a knowledge graph and a rule engine comprises the following steps:
acquiring a sample vehicle running log and screening a sample abnormal log;
establishing a knowledge graph comprising a sample abnormal entity and a path for generating the sample abnormal entity;
constructing a rule base according to the sample abnormal log and the knowledge graph;
collecting a target running log of a vehicle to be diagnosed, and screening out a target abnormal log of the vehicle to be diagnosed;
inputting the target abnormal log of the vehicle to be diagnosed into a rule engine loaded with the rule base, matching the target abnormal entity in the knowledge graph, and then matching a path which leads to the generation of the target abnormal entity to obtain a diagnosis result.
According to the technical means, the diagnosis result is obtained by screening the sample abnormal log, establishing the knowledge graph, constructing the rule base between the sample abnormal log and the knowledge graph, inputting the target abnormal log of the vehicle to be diagnosed into a rule engine loaded with the rule base, matching the target abnormal entity in the knowledge graph, and matching a path which leads to the generation of the target abnormal entity. And screening a sample abnormal log by using a sample vehicle running log, then establishing the knowledge graph and the rule base, namely equivalent to establishing a shared knowledge base, and finally, rapidly positioning the fault by using a rule engine technology loaded with the rule base, thereby solving the problems of how to fully utilize the running log, establish a standard shared knowledge base and rapidly positioning the fault cause in the prior art.
Further, a classification model is established, and the sample abnormal log is screened through machine learning of the classification model.
According to the technical means, a classification model is firstly established, then the classification model is learned by a machine, and the sample abnormal logs are screened for the sample driving logs input into the classification model. And establishing the classification model, and realizing the rapid screening of the sample abnormal logs in the sample running logs through machine learning.
Further, the target traveling logs are input into the classification model, and the target abnormal logs are screened through machine learning.
According to the technical means, the target traveling logs are input into the established classification model, and the target abnormal logs in the target traveling logs are rapidly screened through machine learning, so that the efficiency is improved.
Further, the entities of the knowledge graph include vehicle faults, fault codes, anomalies and vehicle types.
Further, the relation between the sample abnormal log and the knowledge graph is established, and the rule base is generated.
According to the technical means, the rule base is established by constructing the relation between the sample abnormal log and the knowledge graph.
Further, corresponding parameters and corresponding values are screened from the sample abnormal log, the results caused by the parameters and the corresponding values correspond to the sample abnormal entities of the knowledge graph, and the relation rules are stored to generate the rule base.
According to the technical means, the corresponding parameters, the corresponding values and the results, namely the occurrence of the sample abnormal entity in the knowledge graph, are screened from the sample abnormal log, and the relation rules are stored to generate the rule base.
Further, according to the matched paths which cause the generation of the target abnormal entity, performing manual fault verification, verifying whether the paths are correct, and if so, performing maintenance; and if not, updating the knowledge graph and the rule base.
According to the technical means, according to the matched paths which lead to the generation of the target abnormal entity, a maintainer performs troubleshooting, and the maintainer performs manual fault verification on the vehicle to be diagnosed to check whether the troubleshooting fault path is consistent with the matched paths which lead to the generation of the target abnormal entity, if not, the knowledge graph and the rule base are supplemented with the data of the situation, the knowledge graph and the rule base are updated, and the data in the knowledge graph and the rule base are kept to be updated, supplemented and iterated in time, so that the data of the knowledge graph and the rule base are more comprehensive. Of course, if the paths are consistent, the maintenance personnel can maintain in time according to the paths.
Further, if the target abnormal entity is matched but the path which causes the generation of the target abnormal entity is not matched, manual investigation is performed, and if a fault exists, the knowledge graph and the rule base are updated.
According to the technical means, if the target abnormal entity is matched but the path which causes the generation of the target abnormal entity is not matched, a maintenance person performs manual fault verification on the vehicle to be diagnosed, namely, whether a fault exists or not is checked by virtue of maintenance experience, if the fault exists, the data of the situation is supplemented to the knowledge graph and the rule base, the knowledge graph and the rule base are updated, the diagnosis accuracy is improved, the condition that the fault is missed due to the lack of the data next time is avoided, the continuous iterative updating of the data in the knowledge graph and the rule base is kept as much as possible, and a reference is provided for fault diagnosis of a large number of vehicles.
The remote vehicle diagnosis system based on the knowledge graph and the rule engine comprises a cloud system and an automobile terminal system which are in communication connection, wherein the automobile terminal system is used for collecting a target running log of a vehicle to be diagnosed and sending a diagnosis request to the cloud system, and the cloud system is used for constructing a rule base of the relation between the abnormal log and the knowledge graph, receiving the diagnosis request of the automobile terminal system and utilizing the rule base to conduct fault diagnosis according to the target running log of the vehicle to be diagnosed.
According to the technical means, the rule base is constructed through the cloud system, then the automobile terminal system sends the collected target running logs of the vehicle to be diagnosed to the cloud system and sends a diagnosis request, the cloud system processes the running logs of the vehicle to be diagnosed by using the rule base, then the extraction parameters are matched with the target abnormal entity in the rule base, then the path which causes the target abnormal entity to be generated is matched, and the diagnosis result is obtained. The vehicle running log of the vehicle is fully utilized, a sharable rule base is established, namely a standard shared knowledge base is established, and the rapid positioning of faults is realized.
Further, the cloud system comprises a rule building module and a data receiving and processing module, the rule building module is in communication connection with the data receiving and processing module, the automobile terminal system comprises a data acquisition module and a control center module, the data acquisition module is in communication connection with the control center module, and the control center module is in communication connection with the data receiving and processing module.
According to the technical means, the data acquisition module is used for acquiring the running logs of the vehicle to be diagnosed, the running logs are transmitted to the control center module of the automobile terminal, the control center module is used for sending a diagnosis request to the data receiving and processing module of the cloud system and sending the running logs to the data receiving and processing module, and the data receiving and processing module is used for carrying out fault diagnosis according to the rule base constructed by the rule construction module to obtain a diagnosis result.
The invention has the beneficial effects that:
(1) The vehicle running log is fully utilized, a sharable knowledge graph and a rule base are established, the rapid positioning of faults is realized, and the problems that how to fully utilize the vehicle running log, establish a standard shared knowledge base and rapidly position the fault causes in the prior art are solved.
(2) And continuously iterating and updating the knowledge graph and the rule base, continuously perfecting the diagnosis knowledge base, and providing reference for fault diagnosis of a large number of vehicles.
Drawings
FIG. 1 is a flow chart of a remote vehicle diagnostic method of the knowledge graph and rules engine of the present invention;
FIG. 2 is a comprehensive flow chart of a remote vehicle diagnostic method based on a knowledge graph and a rules engine;
FIG. 3 is a schematic block diagram of a remote vehicle diagnostic system based on a knowledge graph and a rules engine of the present invention;
FIG. 4 is a functional block diagram of the relationship between the cloud system and the internal modules of the vehicle terminal system;
fig. 5 is an overall schematic block diagram of a remote vehicle diagnostic system based on a knowledge graph and a rules engine.
Wherein, 1-cloud system; 2-an automotive terminal system; 11-a rule construction module; 12, a data receiving and processing module; 21-a data acquisition module; 22-a control center module; 121-includes a diagnostic management module; 122-a data processing module; 123-a data update module; 221-a diagnostic center module; 222-a log center module; 223-man-machine interaction module.
Detailed Description
Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
As shown in fig. 1, the present embodiment provides a remote vehicle diagnosis method based on a knowledge graph and a rule engine, which includes the following steps:
acquiring a sample vehicle running log and screening a sample abnormal log;
establishing a knowledge graph comprising a sample abnormal entity and a path for generating the sample abnormal entity;
constructing a rule base according to the sample abnormal log and the knowledge graph;
collecting a target running log of a vehicle to be diagnosed, and screening out a target abnormal log of the vehicle to be diagnosed;
inputting the target abnormal log of the vehicle to be diagnosed into a rule engine loaded with the rule base, matching the target abnormal entity in the knowledge graph, and then matching a path which leads to the generation of the target abnormal entity to obtain a diagnosis result.
Specifically: and establishing a standard shared knowledge graph and a rule base, processing log data when a vehicle fault occurs, namely a target running log of the vehicle to be diagnosed, namely screening a target abnormal log of the vehicle to be diagnosed, taking the target abnormal log as input of a rule engine, matching paths, namely possible fault links, of the target abnormal entity in the knowledge graph, and rapidly positioning fault reasons.
In this embodiment, as shown in fig. 1, in step 110, a classification model is established, and the sample anomaly log is screened by machine learning the classification model.
Specifically: the log belongs to semi-structured data, which contains constants and variables, and can be decomposed into a regular message part and a characteristic message part, wherein the regular message part is data such as a log grade, a timestamp and the like, the characteristic message part is composed of a character string constant and a special symbol, the character string constant is called a log template, the category of the log is indicated, and the parameter variables indicate the value of the system state. The analysis of the log needs to separate the log template and the variables. And extracting the characteristics on the log template and distinguishing the categories.
The specific steps of the abnormal log screening are as follows: firstly, acquiring the data of the running logs generated by a large number of vehicles, namely taking the data as sample running logs; and vectorizing the sample traveling log, labeling the sample traveling log by using methods such as clustering and the like, and finally training a classification model by using the labeled sample traveling log data to carry out abnormal log screening. And screening out logs of sample anomalies by machine learning the classification model, and manually confirming again. It should be noted that, vectorization is performed on the sample running log, and labeling is performed on the sample running log by using methods such as clustering, which is to sort and label the data of the sample running log, for example, sorting of engines, sorting of vehicle bodies, and labeling of sorting of good categories.
And screening the target running logs of the vehicle to be diagnosed through machine learning to find out target abnormal logs. And acquiring relevant parameters and data from the target abnormal log, inputting the parameters and the data into a rule engine, matching the target abnormal entity, then matching the target abnormal entity in a possible path, and if a matched path exists, reserving the path, otherwise, performing on-site investigation and confirmation by a maintainer.
In this embodiment, as shown in fig. 1, in step 140, the target traveling log is input into the classification model, and the target abnormal log is screened through machine learning. And inputting the running logs of the vehicle to be diagnosed into the established classification model, and realizing quick screening of abnormal logs in the running logs through machine learning, thereby improving the efficiency.
In this embodiment, as shown in fig. 1, in step 120, the entities of the knowledge graph include a vehicle fault, a fault code, an anomaly, and a vehicle type.
Specifically: knowledge graph is essentially a semantic network, embodying objective experience knowledge in a huge network. Nodes in the network represent entities and edges represent semantic relationships. Knowledge-graph is generally considered a table of triples, the first, three representing entities and the second representing relationships.
In this embodiment, the knowledge-graph entities include vehicle faults, fault codes, anomalies and vehicle types, but of course, there are many knowledge-graph entities, and the knowledge-graph entities are not limited to these. And these entities also include a number of categories, such as anomalies with a number of anomalies, like lights, pre-warnings, etc. The fault code belongs to the vehicle type, the abnormality can lead to the vehicle fault and generate the fault code, the fault code can lead to the vehicle fault, and the vehicle fault and the fault code correspond to each other.
The establishment of the knowledge graph is based on maintenance experience knowledge such as vehicle fault codes, vehicle condition data, history maintenance data and the like, the semi-structured data and unstructured data in the knowledge graph are extracted and normalized, and the relationship between the entities constructing the knowledge graph, namely the abnormal entity constructing the knowledge graph and the path causing the abnormal entity are constructed and stored in a database.
In this embodiment, as shown in fig. 1, in step 130, a relationship between the sample anomaly log and the knowledge graph is established, and the rule base is generated. And screening corresponding parameters and corresponding values from the sample abnormal log, wherein the results caused by the parameters and the corresponding values correspond to the sample abnormal entity of the knowledge graph, and storing the relation rule to generate the rule base.
Specifically: and screening out corresponding parameters, corresponding values and the results from the sample abnormal log, and storing the results into a MySQL database, wherein the results are sample abnormal entities in the knowledge graph. The rule base is used as input of the rule engine and as a matching rule of the corresponding abnormal entity matched by the abnormal log. For example, the voltage of the battery of the vehicle is less than 10V, which results in the failure of starting the electric power steering system.
In this embodiment, as shown in fig. 1, in step 150, according to the path that is matched to cause the generation of the target abnormal entity, a manual fault verification is performed to verify whether the path is correct, and if so, maintenance is performed; and if not, updating the knowledge graph and the rule base.
Specifically: according to the matched paths which lead to the generation of the target abnormal entity, a maintainer performs troubleshooting, the maintainer performs manual fault verification on the vehicle to be diagnosed, and checks whether the fault path is consistent with the matched paths which lead to the generation of the target abnormal entity, if not, the knowledge graph and the rule base are supplemented with data of the situation, the knowledge graph and the rule base are updated, and the knowledge graph and the data in the rule base are maintained to be updated, supplemented and iterated in time, so that the data of the knowledge graph and the rule base are more comprehensive. Of course, if the paths are consistent, the maintenance personnel can maintain in time according to the paths.
In this embodiment, as shown in fig. 1, in step 150, if the target abnormal entity is matched but the path that causes the generation of the target abnormal entity is not matched, manual investigation is performed, and if a fault exists, the knowledge graph and the rule base are updated.
Specifically: and if the fault exists, supplementing the data of the situation to the knowledge graph and the rule base, updating the knowledge graph and the rule base, avoiding missing the situation of the fault caused by the lack of the data next time, keeping the continuous iterative updating of the data in the knowledge graph and the rule base as much as possible, and providing reference for fault diagnosis of a large number of vehicles.
In summary, as shown in fig. 2, the method for remote vehicle diagnosis based on the knowledge graph and the rule engine comprises the following steps:
acquiring a vehicle running log, and screening an abnormal log through machine learning;
establishing a knowledge graph according to maintenance data such as automobile fault codes, maintenance data and the like;
constructing a rule base according to the abnormal log and the entities in the knowledge graph;
diagnosing according to the fault code of the vehicle and the log data when the fault code appears;
and updating the knowledge graph and the rule base.
As shown in fig. 3, the embodiment further provides a remote vehicle diagnosis system based on a knowledge graph and a rule engine, which comprises a cloud system 1 and an automobile terminal system 2 which are in communication connection, wherein the automobile terminal system 2 is used for collecting a driving log of a vehicle to be diagnosed and sending a diagnosis request to the cloud system 1, and the cloud system 1 is used for constructing a rule base of a relation between the abnormal log and the knowledge graph, receiving the diagnosis request of the automobile terminal system 2 and carrying out fault diagnosis according to the driving log of the vehicle to be diagnosed by using the rule base to obtain a diagnosis result. In this embodiment, the cloud system 1 and the automobile terminal system 2 communicate through MQTT (Message Queuing Telemetry Transport, message queue transmission probe) protocol.
As shown in fig. 4, in the present embodiment, the cloud system 1 includes a rule building module 11 and a data receiving and processing module 12, the rule building module 11 and the data receiving and processing module 12 are in communication connection, the automobile terminal system 2 includes a data acquisition module 21 and a control center module 22, the data acquisition module 21 is in communication connection with the control center module 22, and the control center module 22 is in communication connection with the data receiving and processing module 12. The method comprises the steps that a data acquisition module 21 is used for acquiring a running log of a vehicle to be diagnosed, the running log is transmitted to a control center module 22 of an automobile terminal, the control center module 22 sends a diagnosis request to a data receiving and processing module 12 of a cloud system and the running log is sent to the data receiving and processing module 12, and the data receiving and processing module 12 performs fault diagnosis according to a rule base constructed by a rule construction module 11 to obtain a diagnosis result.
In this embodiment, the control center module 22 includes a diagnostic center module 221, a log center module 222, and a man-machine interaction module 223, where the diagnostic center module 221 is configured to initiate a diagnostic request; the log center module 222 is used for collecting logs of each ECU (electronic control unit) and performing log level control; the man-machine interaction module 223 is configured to feed back an abnormal link issued by the cloud.
In the present embodiment, the data receiving and processing module 12 includes a diagnosis management module 121, a data processing module 122, and a data updating module 123, where the diagnosis management module 121 is configured to manage each diagnosis request and diagnosis result;
the data processing module 122 is configured to collect log data of a vehicle, learn by using a machine, screen out abnormal log backup, and collect data related to diagnosis of an automobile, and construct a knowledge graph;
the data updating module 123 is configured to reversely update the rule base and the knowledge graph according to each diagnosis result.
Specifically: as shown in fig. 5, the cloud part includes a diagnosis management module 121, a data processing module 122, a data updating module 123, and a rule constructing module 11; the automobile terminal comprises a diagnosis center module 221, a log center module 222, a data acquisition module 21 and a man-machine interaction module 223. The cloud end and the automobile terminal communicate through an MQTT protocol, and a diagnosis center module 221, a log center module 222, a data acquisition module 21 and a man-machine interaction module 223 are operated on an SOC (system on chip) in a TBOX (vehicle networking system) of the automobile terminal. Each ECU of the automobile is connected to an MCU (micro controller) in the TBOX through a CAN (Controller Area Network) network, and the MCU forwards data sent by each ECU (electronic control unit) to each module running in the SOC.
The above embodiments are merely preferred embodiments for fully explaining the present invention, and the scope of the present invention is not limited thereto. Equivalent substitutions and modifications will occur to those skilled in the art based on the present invention, and are intended to be within the scope of the present invention.
Claims (10)
1. A remote vehicle diagnostic method based on a knowledge graph and a rules engine, comprising the steps of:
acquiring a sample vehicle running log and screening a sample abnormal log;
establishing a knowledge graph comprising a sample abnormal entity and a path for generating the sample abnormal entity;
constructing a rule base according to the sample abnormal log and the knowledge graph;
collecting a target running log of a vehicle to be diagnosed, and screening out a target abnormal log of the vehicle to be diagnosed;
inputting the target abnormal log of the vehicle to be diagnosed into a rule engine loaded with the rule base, matching the target abnormal entity in the knowledge graph, and then matching a path which leads to the generation of the target abnormal entity to obtain a diagnosis result.
2. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 1, wherein: and establishing a classification model, and screening the sample abnormal log through machine learning of the classification model.
3. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 2, wherein: and inputting the target traveling logs into the classification model, and screening the target abnormal logs through machine learning.
4. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 1, wherein: the knowledge graph entities comprise vehicle faults, fault codes, anomalies and vehicle types.
5. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 1, wherein: and establishing a relation between the sample abnormal log and the knowledge graph to generate the rule base.
6. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 5, wherein: and screening corresponding parameters and corresponding values from the sample abnormal log, wherein the results caused by the parameters and the corresponding values correspond to the sample abnormal entity of the knowledge graph, and storing the relation rule to generate the rule base.
7. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 1, wherein: according to the matched paths which lead to the generation of the target abnormal entity, performing manual fault verification to verify whether the paths are correct, and if so, performing maintenance; and if not, updating the knowledge graph and the rule base.
8. The knowledge-graph and rule engine-based remote vehicle diagnostic method of claim 7, wherein: if the target abnormal entity is matched but the path which causes the generation of the target abnormal entity is not matched, performing manual investigation, and if a fault exists, updating the knowledge graph and the rule base.
9. A remote vehicle diagnostic system based on a knowledge graph and a rules engine, characterized by: the system comprises a cloud system and an automobile terminal system which are in communication connection, wherein the automobile terminal system is used for collecting a driving log of a vehicle to be diagnosed and sending a diagnosis request to the cloud system, and the cloud system is used for constructing a rule base of the relation between the abnormal log and the knowledge graph, receiving the diagnosis request of the automobile terminal system and performing fault diagnosis according to the driving log of the vehicle to be diagnosed by using the rule base.
10. The knowledge-graph and rule engine based remote vehicle diagnostic system of claim 9, wherein: the cloud system comprises a rule building module and a data receiving and processing module, the rule building module is in communication connection with the data receiving and processing module, the automobile terminal system comprises a data acquisition module and a control center module, the data acquisition module is in communication connection with the control center module, and the control center module is in communication connection with the data receiving and processing module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310487489.9A CN116400672A (en) | 2023-04-28 | 2023-04-28 | Remote vehicle diagnosis method and system based on knowledge graph and rule engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310487489.9A CN116400672A (en) | 2023-04-28 | 2023-04-28 | Remote vehicle diagnosis method and system based on knowledge graph and rule engine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116400672A true CN116400672A (en) | 2023-07-07 |
Family
ID=87007566
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310487489.9A Pending CN116400672A (en) | 2023-04-28 | 2023-04-28 | Remote vehicle diagnosis method and system based on knowledge graph and rule engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116400672A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117434925A (en) * | 2023-11-24 | 2024-01-23 | 镁佳(北京)科技有限公司 | Diagnostic sequence processing method, computer equipment and medium |
CN117972416A (en) * | 2023-12-21 | 2024-05-03 | 华能信息技术有限公司 | Model training method, automatic driving vehicle fault pre-judging method and system |
-
2023
- 2023-04-28 CN CN202310487489.9A patent/CN116400672A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117434925A (en) * | 2023-11-24 | 2024-01-23 | 镁佳(北京)科技有限公司 | Diagnostic sequence processing method, computer equipment and medium |
CN117972416A (en) * | 2023-12-21 | 2024-05-03 | 华能信息技术有限公司 | Model training method, automatic driving vehicle fault pre-judging method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116400672A (en) | Remote vehicle diagnosis method and system based on knowledge graph and rule engine | |
EP1674958B1 (en) | A diagnostic method and system | |
CN110674189B (en) | Method for monitoring secondary state and positioning fault of intelligent substation | |
CN113870260B (en) | Welding defect real-time detection method and system based on high-frequency time sequence data | |
CN115718802A (en) | Fault diagnosis method, system, equipment and storage medium | |
CN102765643A (en) | Elevator fault diagnosis and early-warning method based on data drive | |
CN108197812A (en) | One kind is based on the vehicle failure online diagnosing technique of support shaft of " big data " | |
CN109308587A (en) | The reliability analysis system and its intelligent diagnosing method of electric automobile charging pile | |
Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
CN116186270A (en) | Vehicle fault cause diagnosis method, device, equipment and storage medium | |
CN114821856A (en) | Intelligent auxiliary device connected in parallel to automobile traveling computer for rapid automobile maintenance | |
CN113609216A (en) | Block chain-based product quality diagnosis method, device, equipment and storage medium | |
CN112748331A (en) | Circuit breaker mechanical fault identification method and device based on DS evidence fusion | |
CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
CN116719801A (en) | Reasoning generation method and device for automobile fault diagnosis correlation phenomenon | |
EP3451101A1 (en) | Method for determining a cause of a malfunction in a vehicle component | |
CN115373366A (en) | Interactive diagnosis system, diagnosis method and storage medium | |
CN115758561A (en) | Method for generating flight simulation parameter data of airplane | |
CN115203014A (en) | Ecological service abnormity restoration system and restoration method based on deep learning | |
CN105740822B (en) | A kind of mechanical fault diagnosis optimization method and system | |
CN111965995A (en) | Three-in-one aircraft avionics system health assessment and prediction system and method thereof | |
CN114279718B (en) | Configurable fault diagnosis method and system based on real-time vehicle condition | |
CN116627954B (en) | Method and device for extracting big data information of automobile fault diagnosis | |
Feng et al. | Research on Urban Rail Transit Fault Diagnosis Based on Bayesian Network | |
CN112712106B (en) | Mechanical equipment health state identification method based on multi-view confrontation self-encoder |
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 |