WO2023103984A1

WO2023103984A1 - Vehicle fault diagnosis method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023103984A1
Application number: PCT/CN2022/136651
Authority: WO
Inventors: 汪大涵; 郭健; 张潘
Original assignee: 北京罗克维尔斯科技有限公司
Priority date: 2021-12-09
Filing date: 2022-12-05
Publication date: 2023-06-15
Also published as: CN116257030A

Abstract

Disclosed are a vehicle fault diagnosis method and apparatus, an electronic device, a storage medium, a computer program product, and a computer program. The vehicle fault diagnosis method comprises: according to a fault knowledge graph and a plurality of target fault codes, determining a target diagnosis result set (S101); the target diagnosis result set comprising a plurality of target diagnosis results, and the fault knowledge graph comprises corresponding relationships between a plurality of fault codes and diagnosis results; and according to the relevancy between each target diagnosis result in the target diagnosis result set and the target fault codes, generating a target diagnosis result sequence (S103).

Description

Vehicle fault diagnosis method, device, electronic device and storage medium

Cross References to Related Applications

This application claims priority to Chinese Patent Application No. 202111499806.6 filed in China on December 9, 2021, the entire contents of which are incorporated herein by reference.

technical field

The present disclosure relates to the technical field of automobiles, in particular to a vehicle failure method, device, electronic equipment, storage medium, computer program product and computer program.

Background technique

At present, there are mainly the following methods for diagnosing vehicle faults: one is the manual discrimination method, that is, the maintenance personnel determine the fault of the vehicle by means of seeing, listening, and smelling, and use the maintenance personnel's own maintenance experience and some simple tools to analyze . The other is the simple instrument diagnosis method, that is, on the basis of the manual experience method, the fault type is judged with the help of simple instruments such as multimeters and oscilloscopes. Since these two methods depend to a large extent on the experience and ability of the maintenance personnel, the diagnosis takes more time and the accuracy of the diagnosis is also poor.

Based on this, an intelligent on-board diagnostic system has emerged, which uses the vehicle controller to analyze the data of auto parts, and then displays it on the on-board screen, or displays the location and time of the fault on the handheld diagnostic instrument.

However, although the on-board diagnostic system can obtain some obvious faults in time, it still cannot obtain the most fundamental fault cause and potential fault problems for serious faults of the vehicle.

Contents of the invention

Embodiments of the present disclosure provide a vehicle fault diagnosis method, device, electronic equipment, storage medium, computer program product and computer program, capable of comprehensively diagnosing vehicle faults.

In a first aspect, an embodiment of the present disclosure provides a vehicle fault diagnosis method, the vehicle fault diagnosis method comprising:

Determine a target diagnostic result set according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes correspondences between multiple fault codes and diagnostic results; and

A target diagnosis result sequence is generated according to the correlation between each target diagnosis result in the target diagnosis result set and the target fault code.

In some embodiments, the determination of the target diagnostic result set according to the fault knowledge map and multiple target fault codes includes:

For each target fault code, according to the fault knowledge graph, determine a set of diagnostic results, the set of diagnostic results includes at least one diagnostic result; and

The target diagnosis result set is determined according to the occurrence frequency of each diagnosis result in the plurality of diagnosis result sets of the plurality of target DTCs.

In some embodiments, before generating the target diagnostic result sequence according to the correlation between each target diagnostic result in the target diagnostic result set and the target fault code, the vehicle fault diagnosis method further includes:

According to the frequency corresponding to each target diagnosis result in the target diagnosis result set, the correlation degree between each target diagnosis result and the target DTC is determined.

According to the chronological order of the target DTCs reported, the correlation degree between the target diagnosis results and the target DTCs is determined.

In some embodiments, before determining the correlation between each target diagnosis result and the target DTC according to the time sequence of each target DTC report, the vehicle fault diagnosis method further includes:

According to the frequency of occurrence of each diagnosis result in the plurality of diagnosis result sets, it is determined that the frequency of each diagnosis result does not satisfy a preset condition.

In some embodiments, the determining the target diagnostic result set according to the frequency of each diagnostic result in the multiple diagnostic result sets of the multiple target DTCs includes:

Determining that the union of the plurality of diagnostic result sets is the target diagnostic result set based on the frequency of each diagnostic result meeting a preset condition;

Based on the frequency of each diagnosis result not satisfying the preset condition, the plurality of diagnosis result sets are determined as the target diagnosis result set.

In some embodiments, the preset condition is that at least one of the corresponding frequencies of all the diagnostic results in the plurality of diagnostic result sets is greater than or equal to the preset frequency.

For each target fault code, according to the fault knowledge graph and the priority of the diagnostic results in the fault knowledge graph, determine a diagnostic result set for each target fault code, and the diagnostic result set includes at least one diagnostic result ;and

For each target DTC, determine the diagnosis result set as the target diagnosis result set corresponding to each target DTC.

In some embodiments, according to the correlation between each target diagnostic result in the target diagnostic result set and the target fault code, before generating the target diagnostic result sequence, the vehicle fault diagnosis method further includes:

According to the priority of all target diagnostic results in each target diagnostic result set, the correlation between each target diagnostic result in each target diagnostic result set and the corresponding target DTC is determined.

In some embodiments, the diagnosis results in the fault knowledge graph include: at least one of controllers, fault setting conditions, fault recovery conditions, fault causes, and maintenance suggestions.

In some embodiments, the vehicle fault diagnosis method also includes:

The plurality of target DTCs are input into the trained model, and a sequence of diagnosis results of the plurality of target DTCs is output based on the trained model, and the diagnosis results in the sequence of diagnosis results are sorted according to probability values.

In a second aspect, an embodiment of the present disclosure provides a vehicle fault diagnosis device, the vehicle fault diagnosis device comprising:

A determining module, configured to determine a target diagnosis result set according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes multiple fault codes and diagnostic results corresponding relationship; and

A sequence generating module, configured to generate a target diagnostic result sequence according to the correlation between each target diagnostic result in the target diagnostic result set and the target fault code.

In some embodiments, the method further includes: a result sequence module, configured to input the multiple target DTCs into the trained model, and output the diagnosis result sequence of the multiple target DTCs based on the trained model , the diagnosis results in the diagnosis result sequence are sorted according to the probability value.

In a third aspect, an embodiment of the present disclosure provides an electronic device, the electronic device includes: a processor, the processor is configured to execute a computer program stored in a memory, and when the computer program is executed by the processor, the first aspect is implemented The steps of any method provided in the embodiments.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any method provided in the embodiment of the first aspect are implemented.

In a fifth aspect, an embodiment of the present disclosure provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, any method provided in the embodiment of the first aspect is implemented.

In a sixth aspect, an embodiment of the present disclosure provides a computer program, the computer program includes computer program code, and when the computer program code is run on a computer, the computer executes any one of the methods provided in the embodiment of the first aspect .

In the technical solution provided by the embodiments of the present disclosure, the target diagnostic result set is determined according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes multiple fault codes and The corresponding relationship of diagnosis results; according to the correlation between each target diagnosis result in the target diagnosis result set and the target fault code, the target diagnosis result sequence is generated. In this way, based on multiple fault codes generated by vehicle faults, multiple faults can be quickly obtained The direct diagnosis result and the related diagnosis result corresponding to the code, that is, the direct diagnosis result and the related diagnosis result of the current fault of the vehicle, so that a comprehensive diagnosis of the vehicle fault can be realized.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure.

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or related technologies, the following will briefly introduce the drawings that need to be used in the descriptions of the embodiments or related technologies. Obviously, for those of ordinary skill in the art, Other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present disclosure;

FIG. 2 is a schematic flowchart of a vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a fault knowledge map provided by an embodiment of the present disclosure;

FIG. 4 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 5 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 6 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 7 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 8 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 9 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 10 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

FIG. 11 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure;

Fig. 12 is a schematic structural diagram of a vehicle fault diagnosis device provided by an embodiment of the present disclosure.

Detailed ways

In order to more clearly understand the above objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, in the case of no conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways than described here; obviously, the embodiments in the description are only some of the embodiments of the present disclosure, and Not all examples.

The embodiment of the present disclosure is applied to a vehicle, and FIG. 1 is a schematic diagram of an application scenario provided by the embodiment of the present disclosure. As shown in FIG. 1 , it includes: a vehicle 110 and a cloud server 120. The vehicle 110 communicates with the cloud server 120. The cloud server 120 periodically sends a DTC request to the vehicle 110. Based on the received DTC request, the vehicle 110, in the current When there is a fault, a fault code is returned to the cloud server 120, and the cloud server 120 diagnoses the vehicle fault based on the received fault code.

Continuing as shown in FIG. 1 , the application scenario may also include: the vehicle diagnostic instrument 130, when the vehicle 110 fails, connect the vehicle diagnostic instrument 130 and the vehicle 110, and after the connection, the vehicle diagnostic instrument 130 sends a fault code request to the vehicle 110, Based on the received fault code request, the vehicle 110 returns the fault code generated under the current fault to the vehicle diagnostic instrument 130 , and the vehicle fault diagnostic instrument 130 diagnoses the current fault of the vehicle based on the received fault code.

When a vehicle breaks down, a corresponding fault code will be generated, and each vehicle fault may generate at least one fault code, especially when a serious fault occurs in the vehicle, multiple fault codes will be generated. A fault code is a character string whose first character is a letter and the subsequent characters are a group of numbers. The first letter is used to identify the type of the fault code, and this group of numbers is used to identify the cause of the current fault, maintenance suggestions, and fault recovery conditions. at least one.

The technical solutions of the embodiments of the present disclosure can be applied to the vehicle fault diagnosis instrument 130 and/or the cloud server 120 in the above-mentioned scenarios, by determining the target diagnosis result set according to the fault knowledge map and multiple target fault codes, the target diagnosis result set includes For multiple target diagnostic results, the fault knowledge map includes the correspondence between multiple fault codes and diagnostic results; according to the correlation between each target diagnostic result in the target diagnostic result set and the target fault code, a target diagnostic result sequence is generated. In this way, based on Multiple fault codes generated by vehicle faults can quickly obtain the direct diagnosis results and related diagnostic results corresponding to multiple fault codes, that is, the direct diagnosis results and related diagnostic results of the current fault of the vehicle, so as to realize a comprehensive diagnosis of vehicle faults.

The technical solution of the present disclosure will be explained in detail below through several specific embodiments.

Fig. 2 is a schematic flowchart of a vehicle fault diagnosis method provided by an embodiment of the present disclosure. As shown in Figure 2, the vehicle fault diagnosis method includes S101 and S103.

S101. Determine a target diagnosis result set according to the fault knowledge map and multiple target fault codes.

The set of target diagnostic results includes multiple target diagnostic results, and the fault knowledge graph includes correspondences between multiple fault codes and diagnostic results.

Fig. 3 is a schematic diagram of a fault knowledge map provided by an embodiment of the present disclosure. As shown in Figure 3, the fault knowledge graph includes a variety of different types of nodes, among which, a variety of different types of nodes include fault code node 1, fault cause node 2, maintenance suggestion node 3, fault setting condition node 4, At least one of the failover condition node 5 and the controller node 6 . Nodes can be connected by connection lines, and there is a corresponding relationship between the nodes at both ends of the connection line. For example, as shown in Figure 3, the two ends of the connection line can be fault code node 1 and fault cause node 2, and the two ends of the connection line It can also be fault code node 1 and maintenance suggestion node 3.

In some embodiments, the fault knowledge graph includes 6449 nodes, wherein the total number of controller nodes 6 is 36, the total number of fault cause nodes 2 is 1099, the total number of fault code nodes 1 is 2066, and the fault recovery condition The total number of nodes 5 is 580, the total number of repair suggestion nodes 3 is 839, and the total number of failure setting condition nodes 4 is 1879.

Based on the above-mentioned embodiments, the diagnosis result in the fault knowledge graph may be at least one of fault cause, maintenance suggestion, fault setting condition, fault recovery condition and controller, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results, It should be noted that the same fault code may correspond to multiple diagnostic results, and different fault codes may correspond to one diagnostic result. The correspondence between these diagnostic results and fault codes is determined based on historical investigation results.

When a serious fault occurs to the vehicle, multiple target DTCs may be generated. The target DTC is one of all DTCs in the fault knowledge map. According to the received multiple target DTCs, for each target DTC, from Find the corresponding diagnostic result set in the fault knowledge map. For example, when a serious fault occurs to the vehicle, target DTC B1, target DTC B2, and target DTC B3 are generated, wherein, target DTC B1 in the fault knowledge map corresponds to diagnosis result A1 and diagnosis result A3, and target DTC B2 Corresponding to diagnosis result A1, diagnosis result A2 and diagnosis result A3, target DTC B3 corresponding to diagnosis result A1, then diagnosis result set 1 of target DTC B1 is {diagnosis result A1, diagnosis result A3}, target DTC B2 Diagnosis result set 2 is {diagnosis result A1, diagnosis result A2, diagnosis result A3}, and diagnosis result set 3 of target DTC B3 is {diagnosis result A1}.

The target diagnostic result set is determined according to the diagnostic result set of each target fault code. The target diagnostic result set includes multiple target diagnostic results. The target diagnostic result can be one of the above-mentioned diagnostic result sets, or it can be the above-mentioned A collection of diagnostic results. There may be one target diagnostic result set, that is, one target diagnostic result set is determined for multiple target DTCs, or there may be multiple target diagnostic result sets, that is, one target diagnostic result set is determined for each target DTC. In this embodiment, there is no specific limitation on the number of target diagnostic result sets corresponding to multiple target fault codes, and the type of target diagnostic result in each target diagnostic result set.

S103. Generate a target diagnostic result sequence according to the correlation between each target diagnostic result in the target diagnostic result set and the target DTC.

In some embodiments, based on multiple target fault codes corresponding to a target diagnostic result set, and one target diagnostic result set in the target diagnostic result set is a diagnostic result set, based on the correlation between the diagnostic result set and all target fault codes, the Each diagnostic result set in the target diagnostic result set is arranged in descending order of correlation to generate a target diagnostic result sequence. For example, based on the above-mentioned embodiment, the target diagnostic result set corresponding to the target fault code B1, target fault B2 and target fault code B3 is {diagnostic result set 1, diagnostic result set 2, diagnostic result set 3}, wherein, the diagnostic result set 1 The correlation with all target DTCs is greater than the correlation between diagnosis result set 2 and all target DTCs, and the correlation between diagnosis result set 3 and all target DTCs is greater than the correlation between diagnosis result set 1 and all target DTCs, then generate The target diagnosis result sequence of is {diagnosis result set 3, diagnosis result set 1, diagnosis result set 2}.

In some embodiments, based on a plurality of target fault codes corresponding to a target diagnosis result set, and one target diagnosis result in the target diagnosis result set is a diagnosis result, based on the correlation between the diagnosis result and all target fault codes, the target diagnosis The diagnostic results in the result set are arranged in descending order of correlation to generate a target diagnostic result sequence. For example, based on the above-mentioned embodiment, the set of target diagnostic results corresponding to target fault code B1, target fault B2, and target fault code B3 is {diagnostic result A1, diagnostic result A2, diagnostic result A3}, wherein, diagnostic result A1 and all target faults The correlation degree of the code is greater than the correlation degree of the diagnosis result A3 and all target DTCs, and the correlation degree of the diagnosis result A3 and all target DTCs is greater than the correlation degree of the diagnosis result A2 and all target DTCs, then the generated target diagnosis result sequence is { Diagnosis result A1, diagnosis result A3, diagnosis result A2}.

In some embodiments, based on multiple target DTCs corresponding to multiple target diagnostic result sets, one target diagnostic result set is a diagnostic result set, based on the correlation between the diagnostic results in each diagnostic result set and the corresponding target DTC, Arrange the diagnostic results in the diagnostic result set in descending order of correlation, and generate a target diagnostic result sequence corresponding to each target fault code. For example, based on the above implementation, the target diagnosis result sets corresponding to target DTC B1, target DTC B2 and target DTC B3 are {Diagnostic Result Set 1}, {Diagnostic Result Set 2} and {Diagnostic Result Set 3}, where, The correlation between diagnosis result A1 and target DTC B1 in diagnosis result set 1 is greater than the correlation between diagnosis result A3 and target DTC B1, and the correlation between diagnosis result A1 and target DTC B2 in diagnosis result set 2 is greater than that between diagnosis result A3 and target DTC B1. The correlation degree of the target DTC B2, the correlation degree of the diagnosis result A3 and the target DTC B2 is greater than the correlation degree of the diagnosis result A2 and the target DTC B2, then the target diagnosis result sequence of the generated target DTC B1 is {diagnosis result A1, Diagnosis result A3}, the target diagnosis result sequence of the generated target DTC B2 is {diagnosis result A1, diagnosis result A3, diagnosis result A2}, and the target diagnosis result sequence of the generated target DTC B3 is {diagnosis result A1}.

In this embodiment, the target diagnostic result set is determined according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results ;According to the correlation between each target diagnosis result in the target diagnosis result set and the target DTC, a target diagnosis result sequence is generated, so that based on multiple DTCs generated by vehicle faults, the direct diagnosis corresponding to multiple DTCs can be quickly obtained The results and related diagnosis results, that is, the direct diagnosis results and related diagnosis results of the current fault of the vehicle, so that a comprehensive diagnosis of vehicle faults can be realized.

FIG. 4 is a schematic flowchart of another vehicle fault diagnosis provided by an embodiment of the present disclosure. Fig. 4 is a specific description of a possible implementation of S101 based on the embodiment shown in Fig. 2 . S101 specifically includes S1011 and S1012.

S1011. For each target fault code, determine a diagnosis result set according to the fault knowledge graph.

The diagnosis result set includes at least one diagnosis result.

The target fault code can be a non-circuit target fault code, which is used to indicate the fault of the non-communication bus system. The first letter of the non-circuit target fault code is a fault code with a non-U character, for example, the initial letter of the non-circuit target fault code Can be B, C, P and other characters. The fault knowledge map includes the corresponding relationship between the target fault code and the diagnosis result. According to the received target fault codes, at least one corresponding diagnosis result is found from the fault knowledge map, that is, the diagnosis result set of each target fault code is obtained. And the diagnosis result set includes at least one diagnosis result.

For example, if target DTC C1, target DTC C2 and target DTC C3 are received, target DTC C1 in the fault knowledge map corresponds to diagnosis result A1 and diagnosis result A3, and target DTC C2 corresponds to diagnosis result A1, diagnosis result A2 and diagnosis result Result A3, target DTC C3 corresponds to diagnosis result A1. Accordingly, for the target DTC C1, the determined diagnosis result set is {diagnosis result A1, diagnosis result A3}; for the target DTC C2, the determined diagnosis result set is {diagnosis result A1, diagnosis result A2, diagnosis result A3} ; For the target fault code C3, the determined diagnosis result set is {diagnosis result A1}.

S1012. Determine a target diagnostic result set according to the occurrence frequency of each diagnostic result in the multiple diagnostic result sets of the multiple target DTCs.

According to all diagnostic results in all diagnostic result sets of all target fault codes, the frequency of each diagnostic result appearing in all diagnostic results is determined. For example, based on the above embodiment, all diagnostic result sets include: {diagnostic result A1, diagnostic result A3}, {diagnostic result A1, diagnostic result A2, diagnostic result A3} and {diagnostic result A1}, all diagnostic result sets include three Diagnosis results, that is, diagnosis result A1, diagnosis result A2 and diagnosis result A3, wherein, the frequency of diagnosis result A1 in all diagnosis result sets is 3 times, and the frequency of diagnosis result A2 in all diagnosis result sets is 1 time , the frequency of diagnosis result A3 appearing in all diagnosis result sets is 2 times.

Determine the target diagnostic result set according to whether the frequency of each diagnostic result in all diagnostic results meets the preset conditions. The target diagnostic result in the target diagnostic result set can be a diagnostic result set or a diagnostic result. for detailed analysis.

FIG. 5 is a specific description as a possible implementation manner when executing S1012. S1012 specifically includes S201, S202 and S203.

S201. Determine whether the frequency of each diagnosis result satisfies a preset condition.

Based on yes, perform S202; based on no, perform S203.

In some embodiments, the preset condition may be that at least one of the corresponding frequencies of all the diagnostic results in the plurality of diagnostic result sets is greater than or equal to the preset frequency. Based on meeting the preset conditions, it means that there is at least one diagnosis result whose frequency is greater than or equal to the preset frequency in all diagnostic results, and based on not meeting the preset conditions, it means that there is no diagnosis result in all diagnostic results whose frequency is greater than or equal to the preset frequency Frequency, that is, frequencies corresponding to all diagnostic results are less than a preset frequency.

S202. Determine the union of the plurality of diagnosis result sets as the target diagnosis result set.

Based on the frequency corresponding to at least one diagnosis result among all the diagnosis results being greater than or equal to the preset frequency, it is determined that the union of the plurality of diagnosis result sets is the target diagnosis result set. For example, the preset frequency can be 3. Based on the above-mentioned embodiment, the frequency of diagnosis result A1 in all diagnosis result sets is equal to the preset frequency, that is, the preset condition is met, and the diagnosis result set {diagnosis result A1, diagnosis result A3 can be determined }, the union of diagnosis result set {diagnosis result A1, diagnosis result A2, diagnosis result A3} and diagnosis result set {diagnosis result A1}, that is, {diagnosis result A1, diagnosis result A2, diagnosis result A3} is the target diagnosis result set .

S203. Determine the plurality of diagnosis result sets as the target diagnosis result set.

Based on the frequency corresponding to each of the diagnostic results being less than the preset frequency, each diagnostic result set can be regarded as a target diagnostic result, and all diagnostic result sets form a target diagnostic result set. For example, the preset frequency can be 3, and all diagnostic result sets include: {diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3} and {diagnostic result A2}, all diagnostic result sets include three diagnoses As a result, the frequency of diagnosis result A1 and diagnosis result A2 in all diagnosis result sets is 2 times, and the frequency of diagnosis result A3 in all diagnosis result sets is 1 time, that is, both are less than the preset frequency, that is, not Satisfying the preset conditions, the set of target diagnostic results can be determined based on time series as {{diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}, {diagnostic result A2}}, namely {diagnostic result A1, diagnostic result Result A2} is earlier than {diagnosis result A1, diagnosis result A3}, and {diagnosis result A1, diagnosis result A3} is earlier than {diagnosis result A2}.

FIG. 6 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. FIG. 6 is based on the embodiment shown in FIG. 4 , before performing S103 , the vehicle fault diagnosis method further includes S102 .

S102. Determine the correlation between each target diagnosis result and the target DTC according to the frequency corresponding to each target diagnosis result in the target diagnosis result set.

Based on the target diagnostic result in the target diagnostic result set is the diagnostic result, the higher the frequency of the target diagnostic result in the target diagnostic result set, the higher the correlation between the target diagnostic result and the target DTC. The order of the relevance of the target diagnosis results can be determined.

For example, based on the above embodiment, the set of target diagnosis results is {diagnosis result A1, diagnosis result A2, diagnosis result A3}, the frequency corresponding to diagnosis result A1 is 3 times, the frequency corresponding to diagnosis result A2 is 1 time, and the frequency corresponding to diagnosis result A3 is If the frequency is 2 times, the diagnosis result A1 has the highest correlation with the target DTC, followed by the diagnosis result A3, and finally the diagnosis result A2. Thus, the generated target diagnosis result sequence is {diagnosis result A1, diagnosis result A3, diagnosis Result A2}.

In this embodiment, by determining the correlation between each target diagnostic result and the target DTC according to the frequency corresponding to each target diagnostic result in the target diagnostic result set, the diagnostic results of the current fault of the vehicle can be analyzed based on the frequency corresponding to the target diagnostic result. Sorting, so that the direct diagnosis results and indirect diagnosis results of the vehicle's current faults can be obtained.

FIG. 7 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. Fig. 7 is based on the embodiment shown in Fig. 4, before performing S103, the vehicle fault diagnosis method further includes S102'.

S102', according to the time sequence of each target DTC report, determine the correlation between each target diagnosis result and the target DTC.

Based on the target diagnosis result set in the target diagnosis result set is the diagnosis result set, the time when each target DTC is reported is obtained, and the earlier the time based on the target DTC is reported, the correlation between the diagnosis result set corresponding to the target DTC and the target DTC The higher the degree is, the order of correlation between the diagnosis result set and the target DTC can be determined based on the time sequence of each target DTC report.

For example, based on the above embodiment, the set of target diagnostic results is {{diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}, {diagnostic result A2}}, and the reporting time of target DTC C1 is 13 :21, the target DTC C2 is reported at 13:23, and the target DTC C3 is reported at 13:20, then the target diagnosis result {diagnosis result A2} has the highest correlation with the target DTC, followed by the target diagnosis result {diagnosis result A1, diagnosis result A2}, and finally the target diagnosis result {diagnosis result A1, diagnosis result A3}, thus, the generated target diagnosis result sequence is {{diagnosis result A2}, {diagnosis result A1, diagnosis result A2} , {diagnosis result A1, diagnosis result A3}}.

In this embodiment, by determining the correlation between each target diagnostic result and the target DTC according to the time sequence of each target DTC report, the diagnostic results of the current vehicle fault can be sorted based on the reporting time of the target DTC, so that The direct and indirect diagnosis results of the vehicle's current faults are obtained.

FIG. 8 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. Fig. 8 is based on the embodiment shown in Fig. 7, before executing S102', the vehicle fault diagnosis method further includes S1013.

S1013. According to the frequency of occurrence of each diagnosis result in the plurality of diagnosis result sets, determine that the frequency of each diagnosis result does not satisfy a preset condition.

Based on the fact that the preset conditions are not met, the correlation between each target diagnosis result and the target DTC is determined based on the time sequence reported by each target DTC; based on the satisfaction of the preset condition, based on the corresponding Frequency, to determine the correlation between each target diagnosis result and the target DTC.

FIG. 9 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. FIG. 9 is a specific description of another possible implementation of S101 based on the embodiment shown in FIG. 2 . S101 specifically includes S301 and S302.

S301. For each target DTC, determine a diagnosis result set for each target DTC according to the fault knowledge graph and the priority of the diagnosis results in the fault knowledge graph.

The diagnosis result set includes at least one diagnosis result.

The target fault code can be a circuit target fault code, which is used to indicate a fault in the communication bus system. The first letter of the circuit target fault code is a fault code with a U character. The diagnosis node in the fault knowledge map includes the corresponding relationship between the target fault code and the diagnosis result, wherein the diagnosis result can include: at least one of the first-level diagnosis result, the second-level diagnosis result and the third-level diagnosis result, and the priority of the first-level diagnosis result is The priority of the second-level diagnosis result is higher than that of the second-level diagnosis result, and the priority of the second-level diagnosis result is higher than that of the third-level diagnosis result. For example, the first-level diagnosis result may be a bus diagnosis result, the second-level diagnosis result may be a sub-node diagnosis result, and the third-level diagnosis result may be a leaf node diagnosis result.

According to the prior knowledge of the circuit topology map, determine the priority of the diagnosis results in the fault knowledge map, and according to each target fault code, first determine the first-level diagnosis result corresponding to the target fault code in the fault knowledge map, and then determine the first-level diagnosis result Finally, determine the second-level diagnosis result corresponding to the target fault code in the fault knowledge map. After confirming the second-level diagnosis result, finally determine the third-level diagnosis result corresponding to the target fault code in the fault knowledge map. A diagnosis result set of the target fault code may be generated, and the diagnosis result set may include at least one of the first-level diagnosis result, the second-level diagnosis result and the third-level diagnosis result.

For example, the diagnosis result set of target DTC U1 is {diagnosis result L2, diagnosis result L3}, the diagnosis result set of target DTC U2 is {diagnosis result L1, diagnosis result L2, diagnosis result L3}, and the diagnosis result set of target DTC U3 The result set is {diagnosis result L3}, wherein, diagnosis result L1 is a first-level diagnosis result, diagnosis result L2 is a second-level diagnosis result, and diagnosis result L3 is a third-level diagnosis result.

S302. For each target DTC, determine the diagnosis result set as the target diagnosis result set corresponding to each target DTC.

Each target DTC corresponds to a diagnostic result set, which can be used as the target diagnostic result set of each target DTC, so that multiple target diagnostic result sets can be determined for multiple target DTCs. At least one target diagnosis result is included, and the target diagnosis result is the diagnosis result.

For example, based on the above-mentioned embodiment, the set of target diagnosis results of target DTC U1 is {target diagnosis result L2, target diagnosis result L3}, and the set of target diagnosis results of target DTC U2 is {target diagnosis result L1, target diagnosis result L2, The target diagnosis result L3}, the target diagnosis result set of the target DTC U3 is {target diagnosis result L3}.

In this embodiment, for each target fault code, according to the fault knowledge graph and the priority of the diagnostic results in the fault knowledge graph, the diagnostic result set of each target fault code is determined, and the diagnostic result set includes at least one diagnostic result; for For each target DTC, determine the diagnosis result set as the target diagnosis result set corresponding to each target DTC. In this way, determining the target diagnosis result set of each target DTC based on the priority of the diagnosis result can not only determine the cause of the vehicle failure Direct diagnosis results can also determine related diagnosis results, so that a comprehensive diagnosis of vehicle faults can be realized.

FIG. 10 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. Fig. 10 is based on the embodiment shown in Fig. 9, before performing S103, the vehicle fault diagnosis method further includes S102".

S102", according to the priority of all target diagnostic results in each target diagnostic result set, determine the correlation between each target diagnostic result in each target diagnostic result set and the corresponding target DTC.

The target diagnosis result set is the diagnosis result set, the target diagnosis result in the target diagnosis result set is the diagnosis result in the diagnosis result set, and the priority of the target diagnosis result is the priority of the diagnosis results in the diagnosis result set. According to the order in which the diagnosis results are determined in the diagnosis result set, the correlation degree between each target diagnosis result in the target diagnosis result set and the corresponding target DTC can be determined. The above content shows that the first-level diagnosis result is determined first, and then the second-level diagnosis As a result, the final result is the third-level diagnosis result, then based on the order of the diagnosis results, the correlation ranking of each target diagnosis result in the target diagnosis result set can be determined.

For example, based on the above-mentioned embodiment, in the target diagnostic result set {target diagnostic result L2, target diagnostic result L3}, the target diagnostic result L2 is determined first, and then the target diagnostic result L3 is determined, and the target diagnostic result set {target diagnostic result L1, target diagnostic result In result L2, target diagnosis result L3}, the target diagnosis result L1 is determined first, then the target diagnosis result L2 is determined, and finally the target diagnosis result L3 is determined. The target diagnosis result set {target diagnosis result L3} only determines one target diagnosis result L3. From this, it can be determined that in the target diagnosis result set of the target DTC U1, the correlation between the target diagnosis result L2 and the target DTC U1 is greater than the correlation between the target diagnosis result L3 and the target DTC U1; the target diagnosis result of the target DTC U2 In the set, the correlation between the target diagnosis result L1 and the target DTC U2 is greater than the correlation between the target diagnosis result L2 and the target DTC U2, and the correlation between the target diagnosis result L2 and the target DTC U2 is greater than the target diagnosis result L3 and the target DTC The correlation of U2. In this way, the target diagnosis result sequence corresponding to the determined target DTC U1 is {target diagnosis result L2, target diagnosis result L3}, and the target diagnosis result sequence corresponding to the target DTC U2 is {target diagnosis result L1, target diagnosis result L2, target Diagnosis result L3}, the target diagnosis result sequence corresponding to the target fault code U3 is {target diagnosis result L3}.

In this embodiment, by determining the correlation between each target diagnostic result in each target diagnostic result set and the corresponding target DTC according to the priority of all target diagnostic result sets in each target diagnostic result set, it is possible to The priority sorts the target diagnostic results in all target diagnostic result sets, so that the direct diagnostic results and indirect diagnostic results of the current fault of the vehicle can be obtained.

Fig. 11 is a schematic flowchart of another vehicle fault diagnosis method provided by an embodiment of the present disclosure. FIG. 11 is based on the embodiment shown in FIG. 2 , the vehicle fault diagnosis method further includes S104.

S104. Input the multiple target DTCs into the trained model, and output a diagnosis result sequence of the multiple target DTCs based on the trained model.

The diagnosis results in the diagnosis result sequence are sorted according to the probability value.

The model has three layers, including input layer, hidden layer and output layer. The number of neurons in the input layer is the total number of fault codes, the number of neurons in the output layer is the total number of diagnosis results, and the number of neurons in the hidden layer is 256. Use the diagnosis results in the fault knowledge graph as labels, and use the fault codes in the fault knowledge graph as training features, set the dimension vector L of the number of neurons in the input layer of the model, and initialize all values to 0. Based on the numerical dictionary, input The fault codes and diagnosis results are numerically processed, and the corresponding position in L is changed from 0 to 1, and the final vector L1 is obtained, so as to train the model and obtain the trained model.

Input multiple target fault codes into the trained model, and the trained model can output multiple diagnostic results, wherein the multiple diagnostic results correspond to different probability values, and based on the order of the probability values from large to small, it can be determined A sequence of multiple diagnosis results, the top diagnosis result in the sequence is the direct diagnosis result and related diagnosis results of the current fault of the vehicle.

In this embodiment, by inputting a plurality of target fault codes into the trained model, and outputting a plurality of target fault code diagnosis result sequences based on the trained model, the diagnosis results in the diagnosis result sequence are sorted according to the probability value, which can Obtaining the direct diagnosis result of the vehicle's current fault and related diagnosis results can verify the target diagnosis result sequence obtained in the above-mentioned embodiment.

The embodiment of the present disclosure also provides a vehicle fault diagnosis device. Fig. 12 is a schematic structural diagram of a vehicle fault diagnosis device provided by an embodiment of the present disclosure. As shown in FIG. 12 , the vehicle fault diagnosis device includes: a determination module 210 and a sequence generation module 220 .

The determining module 210 is used to determine a target diagnosis result set according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes multiple fault codes and diagnostic results corresponding relationship.

The sequence generating module 220 is configured to generate a target diagnostic result sequence according to the correlation between each target diagnostic result in the target diagnostic result set and the target DTC.

In some embodiments, the determination module 210 is further configured to determine a diagnostic result set for each target fault code according to the fault knowledge map, and the diagnostic result set includes at least one diagnostic result; according to the multiple target faults The frequency of occurrence of each diagnosis result in the plurality of diagnosis result sets of the code is used to determine the target diagnosis result set.

In some embodiments, the determination module 210 is further configured to determine the correlation between each target diagnosis result and the target DTC according to the frequency corresponding to each target diagnosis result in the target diagnosis result set.

In some embodiments, the determination module 210 is further configured to determine the correlation between the target diagnosis results and the target DTCs according to the time sequence of the target DTCs.

In some embodiments, the determining module 210 is further configured to determine that the frequency of each diagnosis result does not satisfy a preset condition according to the frequency of occurrence of each diagnosis result in the plurality of diagnosis result sets.

In some embodiments, the determination module 210 is further configured to determine that the union of the plurality of diagnostic result sets is the target diagnostic result set based on the frequency of each diagnostic result meeting a preset condition; frequency does not meet the preset condition, and determine the plurality of diagnosis result sets as the target diagnosis result set.

In some embodiments, the determination module 210 is further used for determining the diagnosis result set of each target DTC according to the fault knowledge graph and the priority of the diagnosis results in the fault knowledge graph for each target DTC , the diagnosis result set includes at least one diagnosis result; for each target DTC, determine the diagnosis result set as the target diagnosis result set corresponding to each target DTC.

In some embodiments, the determining module 210 is further configured to determine the target diagnostic results in each target diagnostic result set and the corresponding target fault codes according to the priorities of all target diagnostic result sets in each target diagnostic result set relevance.

In some embodiments, the vehicle fault diagnosis device further includes: a result sequence module, configured to input the multiple target fault codes into the trained model, and output the diagnosis of the multiple target fault codes based on the trained model A result sequence, the diagnosis results in the diagnosis result sequence are sorted according to the probability value.

The vehicle fault diagnosis device provided by the embodiments of the present disclosure can be used to execute the steps of the above-mentioned method embodiments, and its implementation principles and technical effects are similar, and will not be repeated here.

An embodiment of the present disclosure further provides an electronic device, including: a processor, the processor is configured to execute a computer program stored in a memory, and when the computer program is executed by the processor, the steps of the foregoing method embodiments are implemented.

Embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the foregoing method embodiments are implemented.

An embodiment of the present disclosure further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, any one of the methods provided in the foregoing embodiments is implemented.

An embodiment of the present disclosure provides a computer program, where the computer program includes computer program code, and when the computer program code is run on a computer, it causes the computer to execute any one of the methods provided in the above embodiments.

It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only specific implementation manners of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

All the embodiments of the present disclosure can be implemented independently or in combination with other embodiments, which are all regarded as the scope of protection required by the present disclosure.

Claims

A vehicle fault diagnosis method, characterized in that, comprising:

Determine a target diagnostic result set according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes correspondences between multiple fault codes and diagnostic results; and

A target diagnosis result sequence is generated according to the correlation between each target diagnosis result in the target diagnosis result set and the target fault code.
The method according to claim 1, wherein said determining the target diagnosis result set according to the fault knowledge map and multiple target fault codes includes:

For each target fault code, according to the fault knowledge graph, determine a set of diagnostic results, the set of diagnostic results includes at least one diagnostic result; and

The target diagnosis result set is determined according to the occurrence frequency of each diagnosis result in the plurality of diagnosis result sets of the plurality of target DTCs.
The method according to claim 2, wherein, before generating the sequence of target diagnostic results according to the correlation between each target diagnostic result in the target diagnostic result set and the target DTC, the method further comprises:

According to the frequency corresponding to each target diagnosis result in the target diagnosis result set, the correlation degree between each target diagnosis result and the target DTC is determined.
The method according to claim 2, wherein, before generating the sequence of target diagnostic results according to the correlation between each target diagnostic result in the target diagnostic result set and the target DTC, the method further comprises:

According to the chronological order of the target DTCs reported, the correlation degree between the target diagnosis results and the target DTCs is determined.
The method according to claim 4, characterized in that, before determining the correlation between the target diagnosis results and the target DTCs according to the time sequence reported by each target DTC, the method further comprises:

According to the frequency of occurrence of each diagnosis result in the plurality of diagnosis result sets, it is determined that the frequency of each diagnosis result does not satisfy a preset condition.
The method according to claim 2, wherein the determining the target diagnostic result set according to the frequency of each diagnostic result in the multiple diagnostic result sets of the multiple target DTCs includes:

Determining that the union of the plurality of diagnostic result sets is the target diagnostic result set based on the frequency of each diagnostic result meeting a preset condition;

Based on the frequency of each diagnosis result not satisfying the preset condition, the plurality of diagnosis result sets are determined as the target diagnosis result set.
The method according to claim 5 or 6, wherein the preset condition is that at least one of the corresponding frequencies of all the diagnostic results in the plurality of diagnostic result sets is greater than or equal to the preset frequency.
The method according to any one of claims 1 to 7, wherein said determining the target diagnosis result set according to the fault knowledge graph and multiple target fault codes includes:

For each target fault code, according to the fault knowledge graph and the priority of the diagnostic results in the fault knowledge graph, determine a diagnostic result set for each target fault code, and the diagnostic result set includes at least one diagnostic result ;and

For each target DTC, determine the diagnosis result set as the target diagnosis result set corresponding to each target DTC.
The method according to claim 8, wherein, according to the correlation between each target diagnostic result in the target diagnostic result set and the target DTC, before generating the target diagnostic result sequence, the method further comprises:

According to the priority of all target diagnostic results in each target diagnostic result set, the correlation between each target diagnostic result in each target diagnostic result set and the corresponding target DTC is determined.
The method according to any one of claims 1 to 9, wherein the diagnosis results in the fault knowledge map include: controller, fault setting conditions, fault recovery conditions, fault causes, maintenance suggestions at least one.
The method according to any one of claims 1 to 10, further comprising:

The plurality of target DTCs are input into the trained model, and a sequence of diagnosis results of the plurality of target DTCs is output based on the trained model, and the diagnosis results in the sequence of diagnosis results are sorted according to probability values.
A vehicle fault diagnosis device, characterized in that it comprises:

A determining module, configured to determine a target diagnosis result set according to the fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes multiple fault codes and diagnostic results corresponding relationship; and

A sequence generating module, configured to generate a target diagnostic result sequence according to the correlation between each target diagnostic result in the target diagnostic result set and the target fault code.
The vehicle fault diagnosis device according to claim 12, further comprising:

The result sequence module is used to input the multiple target fault codes into the trained model, and output the diagnostic result sequence of the multiple target fault codes based on the trained model, and the diagnostic results in the diagnostic result sequence are according to Probability values are sorted.
An electronic device, characterized in that the electronic device comprises: a processor, the processor is configured to execute a computer program stored in a memory, and when the computer program is executed by the processor, the computer program according to any one of claims 1 to 11 can be implemented. steps of the method described above.
A computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are realized.
A computer program product, characterized by comprising a computer program, the computer program implements the method according to any one of claims 1 to 11 when executed by a processor.
A computer program, comprising computer program codes, when the computer program codes are run on a computer, the computer is made to execute the method according to any one of claims 1 to 11.