Vehicle fault detection method and device, electronic equipment and storage medium
By building a vehicle knowledge graph for fault detection and safety analysis, the problem of low fault detection efficiency and accuracy in autonomous vehicles is solved, and the safety of the car is significantly improved.
Patent Information
- Application Number
- CN202411065284.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-29
AI Technical Summary
The prior art has low vehicle fault detection efficiency and accuracy in autonomous vehicles, affecting vehicle safety.
By obtaining vehicle attribute information and health detection information, building a vehicle knowledge graph, conducting fault diagnosis and safety analysis, screening out faulty vehicles and determining their health status.
It improves the efficiency and accuracy of vehicle fault detection and improves the safety of car autonomous driving.
Smart Images

Figure CN119049151A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle detection technology, and in particular to a vehicle fault detection method and device, electronic equipment and storage medium. Background Art
[0002] At present, the safety of self-driving cars is mainly addressed by detecting faults that occur during the operation of the car based on expert knowledge. However, this method is based on manually collected vehicle data and only performs simple detection of vehicle faults, which makes the efficiency and accuracy of vehicle safety detection low, thus affecting the safety of self-driving cars. How to improve the safety of self-driving cars has become an urgent problem to be solved. Summary of the invention
[0003] The main purpose of the embodiments of the present application is to propose a vehicle fault detection method and device, an electronic device and a storage medium, aiming to improve the safety of automatic driving of a vehicle.
[0004] To achieve the above object, a first aspect of an embodiment of the present application provides a vehicle fault detection method, the method comprising:
[0005] Obtain vehicle attribute information and vehicle health detection information of the target vehicle;
[0006] Constructing a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information;
[0007] Performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether the target vehicle has a fault or not;
[0008] Screening out a faulty vehicle from the target vehicles according to the fault diagnosis result;
[0009] A vehicle safety analysis is performed on the faulty vehicle to obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle.
[0010] In some embodiments, constructing a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information includes:
[0011] Extracting a vehicle attribute entity set of the vehicle attribute information and a vehicle detection entity set of the vehicle health detection information;
[0012] Extracting relationships between the vehicle attribute entity set and the vehicle detection entity set to obtain a vehicle entity relationship set;
[0013] Performing entity detection on the vehicle attribute entity set and the vehicle detection entity set to obtain an entity detection result; wherein the entity detection result indicates that the same entity exists between the vehicle attribute entity set and the vehicle detection entity set or the same entity does not exist;
[0014] If the entity detection result indicates that there are identical entities between the vehicle attribute entity set and the vehicle detection entity set, the identical entities are fused to obtain a fused attribute entity set corresponding to the vehicle attribute entity set and a fused detection entity set corresponding to the vehicle detection entity set, and the vehicle knowledge graph is constructed based on the fused attribute entity set, the fused detection entity set and the vehicle entity relationship set;
[0015] If the entity detection result indicates that the same entity does not exist between the vehicle attribute entity set and the vehicle detection entity set, the vehicle knowledge graph is constructed based on the vehicle attribute entity set, the vehicle detection entity set and the vehicle entity relationship set.
[0016] In some embodiments, the method further includes updating the vehicle knowledge graph, specifically including:
[0017] Acquire vehicle attribute entities inconsistent with the vehicle attribute information from the vehicle knowledge graph to obtain a first vehicle attribute entity set, acquire vehicle detection entities inconsistent with the vehicle health detection information from the vehicle knowledge graph to obtain a first vehicle detection entity set, and perform a first update on the first vehicle attribute entity set and the first vehicle detection entity set to obtain a first vehicle knowledge graph;
[0018] Acquire a first vehicle attribute entity that is changed compared with the vehicle attribute entity set from the first vehicle knowledge graph to obtain a second vehicle attribute entity set, acquire a first vehicle detection entity that is changed compared with the vehicle detection entity set from the first vehicle knowledge graph to obtain a second vehicle detection entity set, and perform a second update on the second vehicle attribute entity set and the second vehicle detection entity set to obtain a second vehicle knowledge graph;
[0019] A second vehicle attribute entity that is logically inconsistent with the first vehicle attribute entity set is obtained from the second vehicle knowledge graph to obtain an updated vehicle attribute entity set; a second vehicle detection entity that is logically inconsistent with the first vehicle detection entity set is obtained from the second vehicle knowledge graph to obtain an updated vehicle detection entity set; and a third update is performed on the updated vehicle attribute entity set and the updated vehicle detection entity set to obtain an updated vehicle knowledge graph.
[0020] In some embodiments, the performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph includes:
[0021] Obtaining standard parameters of the target vehicle during normal operation;
[0022] Setting a fault threshold according to the standard parameter; wherein the fault threshold includes a lower fault threshold and / or an upper fault threshold;
[0023] Acquire attribute values of vehicle detection entities in the vehicle detection entity set according to the vehicle knowledge graph;
[0024] When the vehicle detection entity attribute value is greater than the upper fault threshold or the vehicle detection entity attribute value is less than the lower fault threshold, the fault detection result indicates that a fault exists in the target vehicle.
[0025] In some embodiments, performing vehicle safety analysis on the faulty vehicle to obtain vehicle fault information includes:
[0026] Obtaining the fault location and fault identification of the faulty vehicle;
[0027] Based on the fault location and the fault identifier, searching for the fault type and fault cause of the faulty vehicle from the vehicle attribute entity set of the vehicle knowledge graph and the vehicle detection entity set;
[0028] Analyzing the degree of vehicle failure of the faulty vehicle according to the vehicle entity relationship set of the vehicle knowledge graph;
[0029] Determining a fault risk level of the faulty vehicle according to the fault type, the fault cause and the degree of vehicle fault;
[0030] The fault location, the fault identifier, the fault type, the fault cause, the vehicle fault degree and the fault risk level are used as the vehicle fault information.
[0031] In some embodiments, the method further includes performing a fault maintenance operation on the vehicle fault information, including:
[0032] Acquire the vehicle fault degree of the vehicle fault information;
[0033] Performing a vehicle risk detection on the target vehicle according to the degree of the vehicle fault to obtain a vehicle risk detection result; the vehicle risk detection result is used to indicate whether the driving safety of the target vehicle is affected or the driving safety of the target vehicle is not affected;
[0034] If the vehicle risk detection result indicates that the driving safety of the target vehicle is affected, a target redundancy strategy matching the vehicle fault information is obtained from the vehicle detection entity set of the vehicle knowledge graph, and a redundant switching decision is executed on the vehicle fault information based on the target redundancy strategy to perform fault maintenance on the faulty vehicle.
[0035] In some embodiments, acquiring a target redundancy strategy matching the vehicle fault information from a vehicle detection entity set of the vehicle knowledge graph includes:
[0036] Acquire all redundant strategies and strategy types corresponding to all redundant strategies from the vehicle detection entity set of the vehicle knowledge graph;
[0037] The strategy type is matched with the vehicle fault type of the vehicle fault based on a preset matching rule to select a target redundancy strategy that matches the vehicle fault information.
[0038] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a vehicle fault detection device, the device comprising:
[0039] An information acquisition module is used to obtain vehicle attribute information and vehicle health detection information of the target vehicle;
[0040] A knowledge graph construction module, used to construct a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information;
[0041] A fault detection module, used to perform fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether the target vehicle has a fault or not;
[0042] A vehicle screening module, used for screening out faulty vehicles from the target vehicles according to the fault diagnosis result;
[0043] A fault analysis module is used to perform a vehicle safety analysis on the faulty vehicle to obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle. To achieve the above purpose, a third aspect of an embodiment of the present application proposes an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.
[0044] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.
[0045] The vehicle fault detection method and device, electronic device and storage medium proposed in this application obtain the vehicle attribute information and vehicle health detection information of the target vehicle; construct a vehicle knowledge graph based on the vehicle attribute information and vehicle health detection information; perform fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph; screen out the faulty vehicle from the target vehicle according to the fault detection result obtained by the fault diagnosis; perform vehicle safety analysis on the faulty vehicle to obtain vehicle fault information. This application performs fault detection on the vehicle through the constructed vehicle knowledge graph, and can automatically detect vehicle faults in combination with the vehicle knowledge graph, thereby improving the efficiency of vehicle fault detection, and further conducts safety analysis on the faulty vehicle in combination with the vehicle knowledge graph to determine the vehicle fault information, thereby improving the efficiency and accuracy of vehicle fault detection, thereby improving the safety of the vehicle's autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 is a flow chart of a vehicle fault detection method provided by an embodiment of the present application;
[0047] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.
[0048] Figure 3 yes Figure 1 Flow chart of step S103 in FIG.
[0049] Figure 4 yes Figure 1 Flow chart of step S104 in FIG.
[0050] Figure 5 yes Figure 1 Flow chart of step S105 in FIG.
[0051] Figure 6 is another flow chart of the vehicle fault detection method provided by an embodiment of the present application;
[0052] Figure 7 yes Figure 6 Flow chart of step S603 in FIG.
[0053] Figure 8 is a structural schematic diagram of a vehicle fault detection device provided in an embodiment of the present application;
[0054] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0056] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0058] The embodiments of the present application provide a vehicle fault detection method and device, an electronic device and a storage medium, aiming to improve the safety of autonomous driving of a vehicle.
[0059] The vehicle fault detection method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the vehicle fault detection method in the embodiments of the present application is described.
[0060] The vehicle fault detection method provided in the embodiment of the present application relates to the field of vehicle detection technology. The vehicle fault detection method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the vehicle fault detection method, etc., but is not limited to the above forms.
[0061] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0062] Figure 1 is an optional flow chart of the vehicle fault detection method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.
[0063] Step S101, obtaining vehicle attribute information and vehicle health detection information of the target vehicle.
[0064] Step S102, constructing a vehicle knowledge graph based on vehicle attribute information and vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information.
[0065] Step S103, performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether a fault exists or not in the target vehicle.
[0066] Step S104, screening out faulty vehicles from target vehicles according to the fault diagnosis result.
[0067] Step S105, performing a vehicle safety analysis on the faulty vehicle to obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle.
[0068] Steps S101 to S105 shown in the embodiment of the present application are performed by obtaining the vehicle attribute information and vehicle health detection information of the target vehicle; constructing a vehicle knowledge graph based on the vehicle attribute information and vehicle health detection information; performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph; screening out faulty vehicles from the target vehicles according to the fault detection results obtained by the fault diagnosis; and performing vehicle safety analysis on the faulty vehicles to obtain vehicle fault information. The present application performs fault detection on the vehicle through the constructed vehicle knowledge graph, and can automatically detect vehicle faults in combination with the vehicle knowledge graph, thereby improving the efficiency of vehicle fault detection, and further performs safety analysis on the faulty vehicle in combination with the vehicle knowledge graph to determine the vehicle fault information, thereby improving the efficiency and accuracy of vehicle fault detection, thereby improving the safety of autonomous driving of the vehicle.
[0069] In step S101 of some embodiments, the vehicle attribute information includes basic vehicle body information and vehicle component information; the vehicle health detection information includes vehicle fault information and vehicle fault maintenance information.
[0070] Specifically, the basic vehicle body information includes but is not limited to vehicle brand, vehicle identification code, manufacturer, trademark, license plate, vehicle product model, vehicle overall dimensions, transmission ratio, wheelbase, track width and number of tires, etc.
[0071] Vehicle parts information includes but is not limited to engine parts, transmission system parts, brake system parts, steering system parts, electrical instrument parts and redundant components (such as redundant main steering units, redundant standby steering units, redundant sensors), etc.
[0072] Vehicle fault information includes, but is not limited to, fault codes and phenomenon descriptions (such as airbag fault codes and internal fault descriptions, etc.), fault types (such as sensor faults, processor faults, actuator faults, configuration faults, and mechanical faults, etc.), fault locations (such as left front wheel speed sensor faults, engine coolant temperature sensor faults, etc.) and fault history (such as the time of occurrence of historical vehicle faults, handling status, and whether they recur, etc.).
[0073] Vehicle maintenance information includes but is not limited to maintenance records, repair records, and vehicle redundancy strategies.
[0074] Furthermore, the vehicle attribute information and vehicle health detection information of the target vehicle can be collected through the attention mechanism in the Transformer model. The relevant information of the target vehicle can also be collected through other methods, such as a combination of radio frequency identification technology and video recognition technology, but is not limited thereto.
[0075] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S205:
[0076] Step S201, extracting a vehicle attribute entity set of vehicle attribute information and a vehicle detection entity set of vehicle health detection information.
[0077] Step S202: extract the relationship between the vehicle attribute entity set and the vehicle detection entity set to obtain a vehicle entity relationship set.
[0078] Step S203, performing entity detection on the vehicle attribute entity set and the vehicle detection entity set to obtain an entity detection result; wherein the entity detection result indicates that the same entity exists or does not exist between the vehicle attribute entity set and the vehicle detection entity set.
[0079] Step S204, if the entity detection result indicates that there are identical entities between the vehicle attribute entity set and the vehicle detection entity set, the identical entities are fused to obtain a fused attribute entity set corresponding to the vehicle attribute entity set and a fused detection entity set corresponding to the vehicle detection entity set, and a vehicle knowledge graph is constructed based on the fused attribute entity set, the fused detection entity set and the vehicle entity relationship set.
[0080] Step S205, if the entity detection result indicates that there are no identical entities between the vehicle attribute entity set and the vehicle detection entity set, a vehicle knowledge graph is constructed based on the vehicle attribute entity set, the vehicle detection entity set and the vehicle entity relationship set.
[0081] In step S201 of some embodiments, the vehicle attribute entity set refers to a set of entities that describe vehicle attribute information, such as vehicle model, engine, and sensor entities; the vehicle detection attribute entity set refers to a set of entities that describe vehicle health detection information, such as motor short circuit, torque sensor failure, angle sensor failure, motor sensor failure, backup angle sensor, and backup actuator.
[0082] Specifically, the vehicle attribute information and the vehicle detection health information are matched by character strings using a preset regular expression to determine the character strings of characteristic patterns in the vehicle attribute information and the vehicle detection health information.
[0083] Furthermore, the vehicle attribute information and the vehicle health detection module are tagged with parts of speech, and the tagged words are matched with a preset vocabulary list to identify the entity information corresponding to each word, thereby obtaining a vehicle attribute entity set corresponding to the vehicle attribute information and a vehicle health entity set corresponding to the vehicle health detection information.
[0084] In step S202 of some embodiments, the vehicle entity relationship set refers to a collection of connections and interactions between different entities; wherein the vehicle entity relationships include but are not limited to attribute relationships, part-whole relationships, cause-effect relationships, etc.
[0085] For example, the association between an engine and an engine model is an attribute relationship; the association between an engine temperature sensor and a sensor is a type relationship; and the association between an engine model and fuel consumption is a causal relationship.
[0086] Specifically, possible semantic role candidates are generated for each entity according to a predefined set of semantic roles, and the dependency relationship between different parts of speech is obtained according to the semantic role candidates, thereby extracting the entity relationship between different roles.
[0087] For example, the semantic role set is S = {A, B, C, D}, where A represents the vehicle-based information entity label in the vehicle entity attribute set, B represents the vehicle parts information entity label in the vehicle entity attribute set, C represents the vehicle fault information label in the vehicle detection entity set, and D represents the vehicle maintenance information label in the vehicle detection entity set. By obtaining the dependency relationship between the semantic role sets, the entity relationship between different semantic roles is extracted.
[0088] In step S203 of some embodiments, specifically, the entity detection result indicates that the same entity exists or does not exist between the vehicle attribute entity set and the vehicle detection entity set.
[0089] Specifically, the vehicle attribute entity set and the vehicle detection entity set are mapped into a continuous vector space for representation through a trained word vector model (such as a Word2Vec model), and the entities are represented as the same entity or not based on the vector space distance between the entities.
[0090] Specifically, the vector space distance can be expressed by the following cosine similarity formula:
[0091]
[0092] Among them, Sim(e1,e2) represents the vector space distance between vehicle attribute entity sets or vehicle detection entity sets; e1 represents a vehicle attribute entity or a vehicle detection entity; e2 represents another vehicle attribute entity that belongs to the vehicle attribute entity set at the same time as e1 or another vehicle detection entity that belongs to the vehicle detection entity set at the same time as e1.
[0093] Specifically, the vector space distance is compared with a preset distance threshold e; if the vector space distance is less than the distance threshold e, it means that there are no identical entities between the vehicle attribute entity set and the vehicle detection entity set; if the vector space distance is greater than or equal to the distance threshold e, it means that there are identical entities between the vehicle attribute entity set and the vehicle detection entity set.
[0094] In step S204 of some embodiments, if the entity detection result indicates that the same entity exists between the vehicle attribute entity set and the vehicle detection entity set, it means that the same entity exists between the vehicle attribute entity sets or between the vehicle detection entities.
[0095] Specifically, the fused attribute entity set and the fused detection entity set are used as nodes, and the vehicle entity relationship set is used as edges to construct a vehicle knowledge graph.
[0096] In this embodiment, by fusing the same entities to obtain a fused attribute entity set corresponding to the vehicle attribute entity set and a fused detection entity set corresponding to the vehicle detection entity set, entity ambiguity can be eliminated and the accuracy of entity extraction can be improved. A vehicle knowledge graph is constructed based on the fused attribute entity set, the fused detection entity set and the vehicle entity relationship set, which can reduce the redundancy of constructing the vehicle knowledge graph structure and enhance the correlation between different vehicle entities, thereby constructing a vehicle knowledge graph with a clear structure.
[0097] In step S205 of some embodiments, specifically, if the entity detection result indicates that there are no identical entities between the vehicle attribute entity set and the vehicle detection entity set, it means that there are no identical entities between the vehicle attribute entity sets or between the vehicle detection entities.
[0098] Specifically, a vehicle knowledge graph is constructed by taking the vehicle attribute entity set and the vehicle detection entity set as nodes and the vehicle entity relationship set as edges.
[0099] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S303:
[0100] Step S301, obtain vehicle attribute entities inconsistent with vehicle attribute information from the vehicle knowledge graph to obtain a first vehicle attribute entity set, obtain vehicle detection entities inconsistent with vehicle health detection information from the vehicle knowledge graph to obtain a first vehicle detection entity set, and perform a first update on the first vehicle attribute entity set and the first vehicle detection entity set to obtain a first vehicle knowledge graph.
[0101] Step S302: obtain the first vehicle attribute entity that has changed compared with the vehicle attribute entity set from the first vehicle knowledge graph to obtain the second vehicle attribute entity set; obtain the first vehicle detection entity that has changed compared with the vehicle detection entity set from the first vehicle knowledge graph to obtain the second vehicle detection entity set; and perform a second update on the second vehicle attribute entity set and the second vehicle detection entity set to obtain the second vehicle knowledge graph.
[0102] Step S303, obtain the second vehicle attribute entity that is logically inconsistent with the first vehicle attribute entity set from the second vehicle knowledge graph to obtain an updated vehicle attribute entity set, obtain the second vehicle detection entity that is logically inconsistent with the first vehicle detection entity set from the second vehicle knowledge graph to obtain an updated vehicle detection entity set, and perform a third update on the updated vehicle attribute entity set and the updated vehicle detection entity set to obtain an updated vehicle knowledge graph.
[0103] In step S301 of some embodiments, the first vehicle knowledge graph is a knowledge graph obtained by modifying vehicle attribute entities in the vehicle knowledge graph that are inconsistent with vehicle attribute information or vehicle detection entities that are inconsistent with vehicle health detection information.
[0104] Specifically, the first vehicle knowledge graph can be obtained by the following formula:
[0105]
[0106] Among them, G1 represents the first vehicle knowledge graph; G0 represents the vehicle knowledge graph; F1 represents the first vehicle attribute entity set or the first vehicle detection entity set; F0 represents the vehicle attribute entity set inconsistent with the vehicle attribute information or the vehicle detection entity set inconsistent with the vehicle health detection information.
[0107] In this embodiment, by performing a first update on the first vehicle attribute entity and the first vehicle detection entity set, entities that are inconsistent with the facts in the vehicle knowledge graph and the facts represented by the vehicle attribute information or the vehicle health detection information are modified to obtain the first vehicle knowledge graph, which can significantly reduce information recognition errors and improve the data quality of the vehicle knowledge graph.
[0108] In step S302 of some embodiments, the second vehicle knowledge graph is a knowledge graph obtained by updating the first vehicle attribute entity that is inconsistent with the vehicle attribute entity or the first vehicle detection entity that is inconsistent with the vehicle detection entity in the first vehicle knowledge graph.
[0109] Specifically, the second vehicle knowledge graph can be obtained by the following formula:
[0110] G2=G1+F2
[0111] Among them, G2 represents the second vehicle knowledge graph; G1 represents the first vehicle knowledge graph; F2 represents the second vehicle attribute entity set that has changed compared with the first vehicle attribute entity or the second vehicle detection entity set that has changed compared with the first vehicle detection entity.
[0112] Specifically, by performing a second update on the second vehicle attribute entity and the second vehicle detection entity set, the vehicle knowledge graph will be automatically updated in real time based on changes in driving scenarios, and vehicle attribute information and vehicle health detection will also change accordingly. The content in the vehicle knowledge graph can be continuously expanded, thereby ensuring the timeliness and completeness of the vehicle knowledge graph.
[0113] In step S303 of some embodiments, the updated vehicle knowledge graph is a knowledge graph after updating the second vehicle attribute entity that is inconsistent with the first vehicle attribute entity or the second vehicle detection entity that is inconsistent with the first vehicle detection entity in the second vehicle knowledge graph.
[0114] Specifically, the updated vehicle knowledge graph can be obtained through the following formula:
[0115] G3=G2-F3
[0116] Among them, G3 represents the updated vehicle knowledge graph; G2 represents the second vehicle knowledge graph; F3 represents the updated vehicle attribute entity set that has changed compared with the second vehicle attribute entity or the updated vehicle detection entity set that has changed compared with the second vehicle detection entity.
[0117] Specifically, by performing a third update on the updated vehicle attribute entity set and the updated vehicle detection entity set, an updated vehicle knowledge graph is obtained, which means that the contradictions in the second vehicle knowledge graph are checked through logical reasoning, and the facts related to the contradictions are removed. It is possible to avoid redundancy and contradictions in the vehicle knowledge graph by identifying and correcting information with logical contradictions, thereby ensuring the accuracy and consistency of the information stored in the vehicle knowledge graph, and enhancing the reliability of the vehicle knowledge graph, thereby constructing a more complete and accurate vehicle knowledge graph, which is convenient for subsequent improvement of the accuracy of vehicle fault detection, thereby ensuring the safety of vehicle autonomous driving.
[0118] See also Figure 4 In some embodiments, step S104 may include but is not limited to steps S401 to S404:
[0119] Step S401, obtaining standard parameters of the target vehicle during normal operation.
[0120] Step S402, setting a fault threshold according to standard parameters; wherein the fault threshold includes a lower fault threshold and / or an upper fault threshold.
[0121] Step S403, obtaining the attribute values of the vehicle detection entities in the vehicle detection entity set according to the vehicle knowledge graph.
[0122] Step S404: When the vehicle detection entity attribute value is greater than the upper fault threshold or the vehicle detection entity attribute value is less than the lower fault threshold, the fault detection result indicates that the target vehicle has a fault.
[0123] In step S401 of some embodiments, the standard parameter refers to the parameter range of the vehicle attribute entity defined in the vehicle knowledge graph when it is working normally, including the normal working parameter range of each vehicle component entity. For example, the normal working temperature of the engine is between 85°C and 105°C.
[0124] In step S402 of some embodiments, the fault threshold is a threshold that characterizes that the vehicle attribute entity exceeds the normal operating parameter range, and the fault threshold is set based on standard parameters; wherein the fault threshold includes a lower fault threshold and an upper fault threshold, an upper fault threshold or a lower fault threshold.
[0125] For example, if the standard parameters of the engine are between 85°C and 105°C, the fault threshold includes the engine temperature lower threshold of 85°C and the engine temperature upper threshold of 105°C; if the standard parameters of the transmission oil temperature are not more than 120°C, the fault threshold is the transmission upper threshold of 120°C.
[0126] In step S403 of some embodiments, the vehicle detection entity attribute value refers to the entity attribute value corresponding to the vehicle detection entity. For example, if the vehicle detection entity is engine temperature abnormality, the attribute value of engine temperature abnormality is 120°C.
[0127] Specifically, the vehicle conditional statement can be obtained by querying the vehicle detection entity attribute value corresponding to the vehicle conditional statement from the vehicle knowledge graph.
[0128] Among them, the vehicle conditional statement can be a query statement based on the vehicle attribute entity, vehicle detection entity, vehicle entity relationship, the combination of vehicle attribute entity and vehicle entity relationship, the combination of vehicle detection entity and vehicle entity relationship, or the combination of vehicle attribute entity, vehicle detection entity and vehicle entity relationship input based on actual application needs.
[0129] For example, the vehicle conditional statement is to query the parked vehicle attribute entity, which is the vehicle detection entity between the vehicle sensor and the vehicle entity relationship, and the abnormal temperature of the engine temperature sensor is detected by the vehicle sensor. The query result can be obtained as the connected vehicle detection entity is the abnormal temperature of the engine temperature sensor.
[0130] In this embodiment, by obtaining the vehicle detection entity attribute values in the vehicle detection entity set according to the vehicle knowledge graph, various entity attribute values or entity relationships can be directly queried from the vehicle knowledge graph, thereby improving the efficiency of obtaining the vehicle detection entity attribute values in the vehicle detection entity set.
[0131] In step S404 of some embodiments, the fault diagnosis result is used to characterize whether a fault exists or not in the target vehicle.
[0132] Specifically, by comparing the vehicle detection entity attribute value with the fault threshold, if the vehicle detection entity attribute value is greater than the upper fault threshold or the vehicle detection entity attribute value is less than the lower fault threshold, the fault detection result indicates that the target vehicle has a fault.
[0133] In the embodiment of the present application, for a fault threshold value including an upper threshold value and a lower threshold value range, when the vehicle detection entity attribute value is less than the lower threshold value or greater than the upper threshold value, the fault detection result indicates that a fault exists in the target vehicle.
[0134] In this embodiment, when the vehicle detection entity attribute value is greater than the upper fault threshold or the vehicle detection entity attribute value is less than the lower fault threshold, the fault detection result indicates that there is a fault in the target vehicle, and a preliminarily diagnosis can be made that a fault has occurred in the target vehicle, but the cause and degree of the fault still require further analysis.
[0135] See also Figure 5 In some embodiments, step S105 may also include but is not limited to steps S501 to S505:
[0136] Step S501, obtaining the fault location and fault identification of the faulty vehicle.
[0137] Step S502, based on the fault location and fault identification, search for the fault type and fault cause of the faulty vehicle from the vehicle attribute entity set and the vehicle detection entity set of the vehicle knowledge graph.
[0138] Step S503, analyzing the degree of vehicle failure of the faulty vehicle according to the vehicle entity relationship set of the vehicle knowledge graph.
[0139] Step S504, determining the fault risk level of the faulty vehicle according to the fault type, fault cause and vehicle fault degree.
[0140] Step S505, taking the fault location, fault identification, fault type, fault cause, vehicle fault degree and fault risk level as vehicle fault information.
[0141] In step S501 of some embodiments, the fault location refers to a specific component or system in the vehicle where the fault occurs. For example, if a sensor fails, the fault location is an engine temperature sensor failure, a torque sensor failure, an angle sensor failure, or a motor sensor failure; and the fault identifier is an identification code used to characterize a faulty component of the vehicle.
[0142] In step S502 of some embodiments, the fault type includes but is not limited to engine fault, transmission system fault, electrical system fault, safety system fault, sensor fault, actuator fault, processor fault, etc.
[0143] The fault cause describes the specific reason why the fault occurred. For example, a sensor fault may be caused by excessive temperature, humidity, vibration or impact, and an electrical system fault may be caused by a short circuit, open circuit, blown fuse or poor electrical connection.
[0144] Specifically, a vehicle fault conditional statement can be generated based on the fault location and fault identification, and the fault type and fault cause of the faulty vehicle can be found from the vehicle knowledge graph according to the vehicle fault statement.
[0145] For example, based on the vehicle fault conditional statement of engine temperature sensor fault and fault code P0118, find out the faulty vehicle whose fault type is sensor fault and fault cause is engine coolant temperature sensor short circuit to positive pole from the vehicle knowledge graph.
[0146] In this embodiment, by searching the fault type and fault cause of the faulty vehicle from the vehicle attribute entity set and the vehicle detection entity set of the vehicle knowledge graph based on the fault location and fault identification, the fault type and fault cause of the faulty vehicle can be directly queried from the vehicle knowledge graph, thereby improving the efficiency of vehicle safety analysis.
[0147] In step S503 of some embodiments, the degree of vehicle failure is used to characterize whether the failure generated by the vehicle affects the driving safety of the vehicle, and the degree of vehicle failure is determined based on the failure records in the vehicle detection entity set in the vehicle knowledge graph.
[0148] In step S504 of some embodiments, specifically, the fault risk level can be determined by calculating the risk score of the fault type and the fault cause, and combining the risk score with the degree of vehicle fault; wherein the fault risk level includes a low risk level, a medium risk level and a high risk level, and scores 1-10 can be used to represent different risk levels, scores 1-3 represent a low risk level, scores 4-6 represent a medium risk level, and scores 7-10 represent a high risk level.
[0149] Specifically, the risk score range of historical faults based on the vehicle knowledge graph is set to 1-10, the weights of vehicle fault types and fault causes are both 0.1-1, and the degree of fault types and fault causes are divided into three risk impact levels, among which the first risk impact level has a score of 1-3 points and a weight of 0.1-0.3; the second risk impact level has a score of 4-6 points and a weight of 0.4-0.6; the third risk impact level has a score of 7-10 points and a weight of 0.7-1.
[0150] For example, if the fault type is engine failure, it means that the degree of impact on vehicle risk is large, the risk level is the third level, the score is 8, and the weight value is 0.8; if the fault cause is engine wear, it means that the degree of impact on vehicle risk is average, the score is 5, the weight value is 0.5, and the risk score is (8x0.8)+(6x0.6)=8.9.
[0151] Furthermore, in this embodiment, the fault risk level can be determined by multiplying the risk score by the degree of vehicle fault.
[0152] For example, if the vehicle failure degree is 90%, the failure risk level is 0.9x8.9=8.01. Since 8.01 is within the range of scores 7-10, the failure risk level is a high failure risk level.
[0153] In step S505 of some embodiments, the vehicle fault information is used to characterize the health status of the target vehicle, wherein the vehicle fault information includes the fault location, fault identification, fault type, fault cause, vehicle fault degree and fault risk.
[0154] For example, the vehicle fault information of the target vehicle is that the fault location is engine temperature sensor fault, the fault identifier is fault code P0118, the fault type is sensor fault, the fault cause is engine coolant temperature sensor short circuit to the positive pole, the vehicle fault degree is 90%, and the fault risk is a high risk level.
[0155] See also Figure 6 In some embodiments, after step S105, the vehicle fault detection method further includes steps S601 to S603:
[0156] Step S601, obtaining the vehicle fault degree of the vehicle fault information.
[0157] Step S602, performing a vehicle risk detection on the target vehicle according to the degree of vehicle failure to obtain a vehicle risk detection result; the vehicle risk detection result is used to indicate whether the driving safety of the target vehicle is affected or the driving safety of the target vehicle is not affected.
[0158] Step S603: If the vehicle risk detection result indicates that the driving safety of the target vehicle is affected, a target redundancy strategy matching the vehicle fault information is obtained from the vehicle detection entity set of the vehicle knowledge graph, and a redundant switching decision is executed on the vehicle fault information based on the target redundancy strategy to perform fault maintenance on the faulty vehicle.
[0159] In step S601 of some embodiments, the degree of vehicle failure is used to characterize whether the failure generated by the vehicle affects the driving safety of the vehicle, and the degree of vehicle failure is determined based on the failure records in the vehicle detection entity set in the vehicle knowledge graph.
[0160] In step S602 of some embodiments, specifically, vehicle risk detection for the target vehicle may be performed by comparing the degree of vehicle failure and the vehicle driving safety threshold; wherein the vehicle driving safety threshold may be determined based on an actual driving scenario.
[0161] Specifically, if the angle sensor fails, all fault records stored in the vehicle knowledge graph show that the vehicle fault degree is less than or equal to the vehicle driving safety threshold, indicating that the vehicle is still in a drivable state, so although the vehicle fault exists, it does not affect the vehicle's driving safety; if in addition to the angle sensor failure, the steering angle actuator is also faulty as read from the knowledge graph, indicating that the vehicle fault degree is greater than the vehicle driving safety threshold, and the steering angle actuator failure affects the judgment of the steering wheel angle, making the direction of the vehicle during driving impossible to guarantee, indicating that the vehicle fault degree has affected the vehicle's driving safety.
[0162] For example, the vehicle driving safety threshold is 60%, and the vehicle knowledge graph records that the power supply voltage of vehicle components has experienced three under-voltage failures within 7 days. At this time, the vehicle failure degree is 10%, and the vehicle driving safety is 90%, indicating that the vehicle driving safety is not affected; the vehicle knowledge graph records that the power supply voltage of vehicle components has experienced three under-voltage failures within one day. At this time, the vehicle failure degree is 65%, and the vehicle driving safety is 35%, indicating that the vehicle driving safety is affected.
[0163] In step S603 of some embodiments, the target redundancy strategy refers to a strategy for performing corresponding maintenance for vehicle fault information, including but not limited to backup angle sensors, backup torque sensors, backup motor sensors, and backup actuators.
[0164] Specifically, after identifying vehicle fault information based on the knowledge graph, an abnormal signal can be issued, the fault location of the target vehicle can be determined based on the abnormal signal, and a redundant switching decision can be made for the fault location.
[0165] For example, when an angle sensor fails and the driving safety of the vehicle is affected, a backup angle sensor corresponding to the angle sensor failure is obtained and automatically switched to the corresponding backup sensor.
[0166] In an optional embodiment of the present application, after the fault is maintained through redundant switching decision, the record of fault maintenance (including replaced parts, maintenance time and maintenance type, etc.) is integrated into the vehicle knowledge graph, and the redundant switching event log and audit information are recorded, including switching events and fault events, etc. The vehicle fault occurrence and maintenance information completed through the knowledge graph can be recorded to improve the accuracy of vehicle fault detection. Real-time alarms and notifications are also generated through the vehicle knowledge graph. When a vehicle fault is detected or a redundant decision switching is required, the vehicle control center or driver is notified in time to further ensure the safety of the car's autonomous driving.
[0167] In an embodiment of the present application, if the vehicle risk detection result indicates that the driving safety of the target vehicle is affected, it means that the driving of the vehicle is not safe. By acquiring a target redundancy strategy that matches the vehicle fault information from the vehicle detection entity set of the vehicle knowledge graph, and executing a redundant switching decision on the vehicle fault information based on the target redundancy strategy, timely fault maintenance can be performed on the faulty vehicle to ensure the safety of the vehicle during automatic driving.
[0168] See also Figure 7 In some embodiments, step S603 may include but is not limited to steps S701 to S702:
[0169] Step S701, obtain all redundant strategies and the strategy types corresponding to all redundant strategies from the vehicle detection entity set of the vehicle knowledge graph.
[0170] Step S702 : matching the strategy type with the vehicle fault type of the vehicle fault based on a preset matching rule to select a target redundancy strategy that matches the vehicle fault information.
[0171] In step S701 of some embodiments, the strategy types include but are not limited to backup vehicle parts, data redundancy strategy, communication redundancy strategy, and control redundancy strategy.
[0172] In step S702 of some embodiments, the matching rule is determined based on an actual application scenario. For example, the target redundancy strategy for angle sensor failure matching is a backup angle sensor strategy.
[0173] In this embodiment, by matching the strategy type with the vehicle fault type of the vehicle fault based on a preset matching rule, a target redundant strategy that matches the vehicle fault information can be selected to ensure that when a target vehicle fails, a matching redundant strategy can be selected in time for maintenance, thereby ensuring the safety of the vehicle's autonomous driving.
[0174] The embodiment of the present application obtains the vehicle attribute information and vehicle health detection information of the target vehicle; constructs a vehicle knowledge graph based on the vehicle attribute information and vehicle health detection information; performs fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph; screens out the faulty vehicle from the target vehicle according to the fault detection results obtained by the fault diagnosis; and performs vehicle safety analysis on the faulty vehicle to obtain vehicle fault information. The present application performs fault detection on the vehicle through the constructed vehicle knowledge graph, and can automatically detect vehicle faults in combination with the vehicle knowledge graph, thereby improving the efficiency of vehicle fault detection, and further performs safety analysis on the faulty vehicle in combination with the vehicle knowledge graph to determine the vehicle fault information, thereby improving the efficiency and accuracy of vehicle fault detection, thereby improving the safety of autonomous driving.
[0175] See also Figure 8 The embodiment of the present application also provides a vehicle fault detection device, which can implement the above-mentioned vehicle fault detection method, and the device includes:
[0176] An information acquisition module is used to obtain vehicle attribute information and vehicle health detection information of the target vehicle;
[0177] A knowledge graph construction module is used to construct a vehicle knowledge graph based on vehicle attribute information and vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information;
[0178] A fault detection module is used to perform fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether the target vehicle has a fault or not;
[0179] A vehicle screening module, used to screen out faulty vehicles from target vehicles according to the fault diagnosis result;
[0180] The fault analysis module is used to perform vehicle safety analysis on the faulty vehicle and obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle.
[0181] The specific implementation of the vehicle fault detection device is basically the same as the specific implementation of the above-mentioned vehicle fault detection method, and will not be repeated here.
[0182] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above vehicle fault detection method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.
[0183] See also Fig. 9 , Fig. 9The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0184] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.
[0185] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the vehicle fault detection method of the embodiment of this application;
[0186] Input / output interface 903, used to implement information input and output;
[0187] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);
[0188] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);
[0189] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .
[0190] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned vehicle fault detection method is implemented.
[0191] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0192] The vehicle fault detection method, vehicle fault detection device, electronic device and storage medium provided in the embodiments of the present application obtain vehicle attribute information and vehicle health detection information of the target vehicle; construct a vehicle knowledge graph based on the vehicle attribute information and vehicle health detection information; perform fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph; screen out faulty vehicles from the target vehicles according to the fault detection results obtained by the fault diagnosis; perform vehicle safety analysis on the faulty vehicles to obtain vehicle fault information. The present application performs fault detection on the vehicle through the constructed vehicle knowledge graph, and can automatically detect vehicle faults in combination with the vehicle knowledge graph, thereby improving the efficiency of vehicle fault detection, and further conducts safety analysis on the faulty vehicle in combination with the vehicle knowledge graph to determine the vehicle fault information, thereby improving the efficiency and accuracy of vehicle fault detection, thereby improving the safety of the vehicle's autonomous driving.
[0193] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0194] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0195] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0196] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0197] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0198] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0199] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0200] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0201] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0202] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0203] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A vehicle fault detection method, characterized in that: The method comprises: Obtain vehicle attribute information and vehicle health detection information of the target vehicle; Constructing a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information; Performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether the target vehicle has a fault or not; Screening out a faulty vehicle from the target vehicles according to the fault diagnosis result; A vehicle safety analysis is performed on the faulty vehicle to obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle.
2. The method according to claim 1, characterized in that The constructing a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information includes: Extracting a vehicle attribute entity set of the vehicle attribute information and a vehicle detection entity set of the vehicle health detection information; Extracting relationships between the vehicle attribute entity set and the vehicle detection entity set to obtain a vehicle entity relationship set; Performing entity detection on the vehicle attribute entity set and the vehicle detection entity set to obtain an entity detection result; wherein the entity detection result indicates that the same entity exists between the vehicle attribute entity set and the vehicle detection entity set or the same entity does not exist; If the entity detection result indicates that there are identical entities between the vehicle attribute entity set and the vehicle detection entity set, the identical entities are fused to obtain a fused attribute entity set corresponding to the vehicle attribute entity set and a fused detection entity set corresponding to the vehicle detection entity set, and the vehicle knowledge graph is constructed based on the fused attribute entity set, the fused detection entity set and the vehicle entity relationship set; If the entity detection result indicates that the same entity does not exist between the vehicle attribute entity set and the vehicle detection entity set, the vehicle knowledge graph is constructed based on the vehicle attribute entity set, the vehicle detection entity set and the vehicle entity relationship set.
3. The method according to claim 1, characterized in that The method further includes updating the vehicle knowledge graph, specifically including: Acquire vehicle attribute entities inconsistent with the vehicle attribute information from the vehicle knowledge graph to obtain a first vehicle attribute entity set, acquire vehicle detection entities inconsistent with the vehicle health detection information from the vehicle knowledge graph to obtain a first vehicle detection entity set, and perform a first update on the first vehicle attribute entity set and the first vehicle detection entity set to obtain a first vehicle knowledge graph; Acquire a first vehicle attribute entity that is changed compared with the vehicle attribute entity set from the first vehicle knowledge graph to obtain a second vehicle attribute entity set, acquire a first vehicle detection entity that is changed compared with the vehicle detection entity set from the first vehicle knowledge graph to obtain a second vehicle detection entity set, and perform a second update on the second vehicle attribute entity set and the second vehicle detection entity set to obtain a second vehicle knowledge graph; A second vehicle attribute entity that is logically inconsistent with the first vehicle attribute entity set is obtained from the second vehicle knowledge graph to obtain an updated vehicle attribute entity set; a second vehicle detection entity that is logically inconsistent with the first vehicle detection entity set is obtained from the second vehicle knowledge graph to obtain an updated vehicle detection entity set; and a third update is performed on the updated vehicle attribute entity set and the updated vehicle detection entity set to obtain an updated vehicle knowledge graph.
4. The method according to claim 1, characterized in that: The performing fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph includes: Obtaining standard parameters of the target vehicle during normal operation; Setting a fault threshold according to the standard parameter; wherein the fault threshold includes a lower fault threshold and / or an upper fault threshold; Acquire attribute values of vehicle detection entities in the vehicle detection entity set according to the vehicle knowledge graph; When the vehicle detection entity attribute value is greater than the upper fault threshold or the vehicle detection entity attribute value is less than the lower fault threshold, the fault detection result indicates that a fault exists in the target vehicle.
5. The method according to claim 1, characterized in that The performing of a vehicle safety analysis on the faulty vehicle to obtain vehicle fault information includes: Obtaining the fault location and fault identification of the faulty vehicle; Based on the fault location and the fault identifier, searching for the fault type and fault cause of the faulty vehicle from the vehicle attribute entity set of the vehicle knowledge graph and the vehicle detection entity set; Analyzing the degree of vehicle failure of the faulty vehicle according to the vehicle entity relationship set of the vehicle knowledge graph; Determining a fault risk level of the faulty vehicle according to the fault type, the fault cause and the degree of vehicle fault; The fault location, the fault identifier, the fault type, the fault cause, the vehicle fault degree and the fault risk level are used as the vehicle fault information.
6. The method according to claim 5, characterized in that The method further includes performing a fault maintenance operation on the vehicle fault information, including: Acquire the vehicle fault degree of the vehicle fault information; Performing a vehicle risk detection on the target vehicle according to the degree of the vehicle fault to obtain a vehicle risk detection result; the vehicle risk detection result is used to indicate whether the driving safety of the target vehicle is affected or the driving safety of the target vehicle is not affected; If the vehicle risk detection result indicates that the driving safety of the target vehicle is affected, a target redundancy strategy matching the vehicle fault information is obtained from the vehicle detection entity set of the vehicle knowledge graph, and a redundant switching decision is executed on the vehicle fault information based on the target redundancy strategy to perform fault maintenance on the faulty vehicle.
7. The method according to claim 6, characterized in that The acquiring a target redundancy strategy matching the vehicle fault information from the vehicle detection entity set of the vehicle knowledge graph includes: Acquire all redundant strategies and strategy types corresponding to all redundant strategies from the vehicle detection entity set of the vehicle knowledge graph; The strategy type is matched with the vehicle fault type of the vehicle fault based on a preset matching rule to select a target redundancy strategy that matches the vehicle fault information.
8. A vehicle fault detection device, characterized in that: The device comprises: An information acquisition module is used to obtain vehicle attribute information and vehicle health detection information of the target vehicle; A knowledge graph construction module, used to construct a vehicle knowledge graph based on the vehicle attribute information and the vehicle health detection information; wherein the vehicle knowledge graph includes a vehicle detection entity set, and the vehicle detection entity set is used to represent the vehicle health detection information; A fault detection module, used to perform fault diagnosis on the vehicle detection entity set according to the vehicle knowledge graph to obtain a fault diagnosis result; wherein the fault diagnosis result is used to characterize whether the target vehicle has a fault or not; A vehicle screening module, used for screening out faulty vehicles from the target vehicles according to the fault diagnosis result; The fault analysis module is used to perform a vehicle safety analysis on the faulty vehicle to obtain vehicle fault information; wherein the vehicle fault information is used to characterize the health status of the target vehicle.
9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the vehicle fault detection method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle fault detection method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Fault analysis method and device of power battery, vehicle and medium
CN119644156A
Electric power product potential safety hazard troubleshooting intelligent management system based on industrial internet
CN119903307A
