Automobile power loss problem diagnosis method and device and medium
By building a diagnostic priority scoring model, the diagnostic priority of the cause of failure is automatically calculated, and the problem of low diagnostic efficiency of hybrid vehicle power loss problems is solved, and fast and accurate troubleshooting is achieved, reducing costs and human errors.
Patent Information
- Application Number
- CN202411787544.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2025-04-25
AI Technical Summary
In the case of power loss, the prior art is difficult to quickly and accurately analyze the causes of failures, resulting in low diagnostic efficiency, high cost, and limited by differences in personnel experience and skills.
By constructing a diagnostic priority scoring model, including comparing the scoring model, network scoring model and SVIP scoring model, the diagnostic priority of the cause of the fault is automatically calculated based on historical fault diagnosis information and whether there is fuel injection, and then the troubleshooting is guided.
It significantly improves the diagnostic efficiency of power loss problems, reduces the range and time of problem locking, reduces costs, and avoids errors caused by personnel experience or skills differences.
Smart Images
Figure CN119882662A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of automobile fault diagnosis, and in particular to a method, device and medium for diagnosing automobile power loss problems. Background Art
[0002] For hybrid vehicles, it is particularly important to output power stably as expected. However, the controllers and control logic involved in their power architecture are highly complex. When power loss problems occur, the analysis process will take up a lot of manpower time and cost investment. The analysis process and time will vary depending on different project management and the experience and ability of engineers, making it difficult to quickly sort out ideas and obtain the key path. Summary of the invention
[0003] The invention discloses a method, a device and a medium for diagnosing a power loss problem of an automobile, which can improve the diagnostic efficiency of power loss problems.
[0004] In order to achieve the above purpose, on the one hand, a method for diagnosing the problem of automobile power loss is provided, and the specific method is as follows:
[0005] Based on historical fault diagnosis information, a diagnostic priority scoring model is constructed;
[0006] Determine if there was fuel injection when the vehicle lost power;
[0007] According to whether fuel injection is performed, the diagnosis priority scoring model is queried to obtain the diagnosis priority score;
[0008] According to the fault diagnosis priority score, diagnose and troubleshoot the fault causes in sequence.
[0009] Furthermore, the diagnosis priority scoring model includes: a comparison scoring model, a network scoring model and a SVIP scoring model.
[0010] Preferably, the comparison scoring model includes a comparison scoring sub-model for starting without fuel injection and a comparison scoring sub-model for starting with fuel injection, and the comparison scoring sub-model for starting without fuel injection and the comparison scoring sub-model for starting with fuel injection are selected according to whether there is fuel injection when the vehicle loses power;
[0011] The specific construction methods of the starting without fuel injection comparison scoring sub-model and the starting with fuel injection comparison scoring sub-model are as follows:
[0012] Arrange all the causes of vehicle power loss in rows and columns;
[0013] According to the number of vehicle power loss causes in the historical fault diagnosis information, the number of vehicle power loss causes in the row is divided by the number of vehicle power loss causes in the column to obtain the comparison model score of the vehicle power loss causes corresponding to the row;
[0014] Calculate the average score of the comparison model scores for all rows corresponding to the causes of vehicle power loss as the benchmark average score.
[0015] Furthermore, the network scoring model is specifically constructed as follows:
[0016] List all causes of vehicle power loss as a separate unit;
[0017] Determine the correlation between various causes of vehicle power loss based on the experience database;
[0018] Use directional arrows to connect all related causes of vehicle power loss;
[0019] For each cause of vehicle power loss, there is a directional arrow pointing to another unit, 1 point is scored;
[0020] Count the network model scores of all causes of vehicle power loss.
[0021] Furthermore, the SVIP scoring model includes a starting without fuel injection SVIP scoring sub-model and a starting with fuel injection SVIP scoring sub-model, and the starting without fuel injection SVIP scoring sub-model and the starting with fuel injection SVIP scoring sub-model are selected according to whether there is fuel injection when the vehicle loses power;
[0022] The construction methods of the SVIP scoring sub-model for starting without fuel injection and starting with fuel injection are as follows:
[0023] For all causes of vehicle power loss, impact scores and likelihood scores are performed respectively, and then the impact score is multiplied by the likelihood score to obtain the IP value scores of the causes of vehicle power loss.
[0024] Furthermore, the reasons for the failure to inject fuel at start that cause the vehicle to lose power include: fuel failure, cylinder clearing function, CAN communication problems, and fuel failure due to collision;
[0025] Causes of fuel injection during starting that cause vehicle power loss include: air flow meter failure, exhaust back pressure failure, correction circuit failure and carbon deposits.
[0026] Furthermore, the diagnostic priority score is obtained as follows:
[0027] Normalize the comparison model scores, network model scores and IP value scores of each cause of vehicle power loss;
[0028] The diagnostic priority score for each cause of vehicle power loss is calculated by using the comparison model score, network model score and IP value score after weighted normalization with preset weights.
[0029] Optionally, the diagnosis priority scoring model includes: a comparison scoring model, a network scoring model or a SVIP scoring model.
[0030] Optionally, the diagnosis priority scoring model includes: a comparison scoring model and a network scoring model, or a comparison scoring model and an SVIP scoring model, or a network scoring model and an SVIP scoring model.
[0031] To achieve the above-mentioned purpose, on the other hand, a vehicle power loss problem diagnosis device is provided, comprising a model building module, a fuel injection determination module, a diagnosis scoring module and a diagnosis troubleshooting module;
[0032] The model building module builds a diagnosis priority scoring model based on historical fault diagnosis information;
[0033] The fuel injection determination module determines whether fuel injection occurs when the vehicle loses power;
[0034] The diagnosis scoring module queries the diagnosis priority scoring model according to whether fuel injection is performed to obtain the diagnosis priority score;
[0035] The diagnosis and troubleshooting module diagnoses and troubleshoots the causes of the faults in sequence according to the fault diagnosis priority scores.
[0036] In order to achieve the above-mentioned purpose, on the other hand, a storage medium is provided, which stores a plurality of instructions, and a processor loads the instructions to execute the above-mentioned automobile power loss problem diagnosis method.
[0037] In order to achieve the above-mentioned purpose, on the other hand, a vehicle controller is provided, which is installed in a hybrid vehicle and includes the above-mentioned vehicle power loss problem diagnosis device and / or the above-mentioned storage medium.
[0038] Due to the adoption of the above technical solution, the present invention has the following beneficial effects:
[0039] 1. The present invention has a complete automatic problem analysis and processing method, which selects different priority scores from different models, calculates the final score, and finally organizes the diagnostic logic according to the final score to avoid problems such as lack of ideas or directional errors caused by differences in personnel experience or skills.
[0040] 2. The present invention adopts automatic calculation of the model, through which the probability, importance and impact of possible causes are obtained, which significantly reduces the scope and time of problem locking.
[0041] 3. After the present invention constructs a model based on historical data, the operator can obtain the diagnosis priority. It is user-friendly, highly feasible, and widely applicable. It can be applied to solve various controller problems and significantly reduce costs.
[0042] It should be noted that the terms "first", "second" and similar terms used in this article are only for describing the various components in the technical solution, and do not constitute a limitation of the technical solution, nor can they be understood as an indication or suggestion of the importance of the corresponding elements; elements with "first", "second" and similar terms indicate that the corresponding technical solution contains at least one of the element. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the technical solution of the present invention and facilitate further understanding of the technical effects, technical features and purposes of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings. The accompanying drawings constitute an essential part of the specification and are used together with the embodiments of the present invention to illustrate the technical solution of the present invention, but do not constitute a limitation to the present invention.
[0044] The same reference numerals in the accompanying drawings represent the same components, specifically:
[0045] Figure 1 Schematic diagram of the comparative scoring model in Example 1.
[0046] Figure 2 Schematic diagram of the network scoring model in Example 1.
[0047] Figure 3 Schematic diagram of the SVIP scoring model in Example 1.
[0048] Figure 4 This is a schematic diagram of the process of Example 1. DETAILED DESCRIPTION
[0049] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. Of course, the specific embodiments described below are only for explaining the technical solutions of the present invention, rather than for limiting the present invention. In addition, the parts described in the embodiments or the accompanying drawings are only examples of the relevant parts of the present invention, rather than the whole of the present invention.
[0050] Embodiment 1:
[0051] A method for diagnosing a vehicle power loss problem, such as Figure 4 As shown, the specific steps are as follows:
[0052] S1. Obtain historical fault diagnosis information.
[0053] In this embodiment, the historical fault diagnosis information is 21 cases of power loss caused by engine start failure during operation of the hybrid vehicle. The specific situations of the 21 cases are distributed as follows:
[0054] The engines are all pulled up to 1000rpm normally by the ISG motor;
[0055] There were 15 cases where oil was not sprayed at start-up, and 6 cases where oil was sprayed;
[0056] In 13 cases, EMS failure was reported, and in 8 cases, no EMS failure was reported;
[0057] In 3 cases, the fault was reported during the starting process, and in 10 cases, the fault was reported after the start was successful;
[0058] In 10 cases, the system was normal after repeated restart, and in 11 cases, the system was normal after power off and restart.
[0059] After troubleshooting, the above cases can be divided into two types: engine start without fuel injection and engine start with fuel injection.
[0060] The reasons for the engine starting without fuel injection are: fuel cut-off due to fault, abnormal cylinder cleaning function, CAN communication problem and fuel cut-off due to collision.
[0061] The causes of engine starting and fuel injection failure are: air flow meter failure, exhaust back pressure failure, correction circuit failure and carbon deposits.
[0062] S2. Construct a diagnostic priority scoring model.
[0063] In this embodiment, the diagnostic priority scoring model includes: a comparison scoring model, a network scoring model and an SVIP scoring model, which are constructed as follows:
[0064] S21, the comparative scoring model, such as Figure 1 As shown, it includes a starting without fuel injection comparison scoring sub-model and a starting with fuel injection comparison scoring sub-model, and the starting without fuel injection comparison scoring sub-model and the starting with fuel injection comparison scoring sub-model are selected according to whether there is fuel injection when the vehicle loses power;
[0065] The specific construction methods of the starting without fuel injection comparison scoring sub-model and the starting with fuel injection comparison scoring sub-model are as follows:
[0066] Arrange all the causes of vehicle power loss in rows and columns;
[0067] According to the number of reasons causing vehicle power loss in the historical fault diagnosis information, the number of reasons causing vehicle power loss in the row is divided by the number of reasons causing vehicle power loss in the column to obtain the comparative model score of the reasons causing vehicle power loss corresponding to the row, that is, the sum score in the figure;
[0068] Calculate the average score of the comparative model scores of all rows corresponding to the causes of vehicle power loss as the benchmark average score. Scores above the benchmark average score are high-probability causes. The higher the score, the higher the probability, and the higher the priority item for investigation.
[0069] like Figure 1Statistical results show that for engine starting failure and no fuel injection, the most likely cause is a CAN communication problem, followed by a fault that inhibits fuel injection, so these two problem directions should be checked first; for starting fuel injection, the most likely cause is an air flow meter failure or carbon deposits, so these two problem directions should be checked first.
[0070] S22, the network scoring model, such as Figure 2 As shown, the specific construction method is as follows:
[0071] List all causes of vehicle power loss as a separate unit;
[0072] Determine the correlation between various causes of vehicle power loss based on the experience database;
[0073] Use directional arrows to connect all related causes of vehicle power loss;
[0074] For each cause of vehicle power loss, there is a directional arrow pointing to another unit, 1 point is scored;
[0075] Count the network model scores of all causes of vehicle power loss.
[0076] from Figure 2 It can be seen that after the network relationship logic analysis, the scores above 0 are considered to be the most likely root causes or the most important factors, namely CAN communication failure, injection correction circuit failure, and exhaust back pressure failure. Therefore, it is necessary to start the inspection from these three aspects.
[0077] S23, the SVIP scoring model, such as Figure 3 As shown, it includes the SVIP scoring sub-model for starting without fuel injection and the SVIP scoring sub-model for starting with fuel injection. The SVIP scoring sub-model for starting without fuel injection and the SVIP scoring sub-model for starting with fuel injection are selected according to whether there is fuel injection when the vehicle loses power;
[0078] The construction methods of the SVIP scoring sub-model for starting without fuel injection and starting with fuel injection are as follows:
[0079] For all causes of vehicle power loss, impact scores and likelihood scores are performed respectively, and then the impact score is multiplied by the likelihood score to obtain the IP value scores of the causes of vehicle power loss.
[0080] The SVIP scoring model first distinguishes the causes of starting failure in the primary dimension, then fills in the specific possible causes in the secondary variables, and then fills in the impact and possible factors for each cause. The higher the score, the greater the impact, and finally multiplies the values to get the IP value. From the calculation of this model, it can be seen that the first thing to be checked is the oil failure and CAN communication problems, followed by air flow meter failure and carbon deposit problems.
[0081] S3. Query the diagnosis priority scoring model according to whether fuel injection is performed to obtain the diagnosis priority score.
[0082] In this embodiment, the comparison scoring model, the network scoring model and the SVIP scoring model are queried to obtain the model scores of fault oil shut-off, cylinder cleaning function, CAN communication problem, collision oil shut-off, air flow meter fault, exhaust back pressure fault, correction circuit fault and carbon deposits respectively.
[0083] According to the scores of each model, the diagnostic priority score is obtained. The specific method is as follows:
[0084] The comparative model scores, network model scores and IP value scores of each cause of vehicle power loss are normalized; the diagnostic priority score of each cause of vehicle power loss is calculated by weighting the comparative model scores, network model scores and IP value scores after normalization with preset weights.
[0085] In this embodiment, one model or three models are selected based on the expert experience library and a comprehensive judgment is made after assigning weights. The possibility, importance, impact and other aspects of the output solutions are ranked and output, and the problems with scores higher than 0 or higher than the average are focused on and are prioritized for investigation and resolution.
[0086] Through the comparison model, it is found that CAN communication failure, air flow failure, carbon deposition, and fuel failure are important inspection items with decreasing priority; through the network model, it is found that CAN communication failure, fuel injection correction circuit failure, and exhaust back pressure failure are important inspection items with decreasing priority; through the SVIP model, it is found that CAN communication failure, fuel failure, air flow failure, and carbon deposition are important inspection items with decreasing priority;
[0087] It can be seen that the CAN communication fault score is the highest among all the three models, so this fault is the first one that needs to be checked and eliminated. It is preset that the three models are considered at the same time and the weights are all 1. Then, the faults that need to be checked are air flow fault, fuel cut-off fault, carbon deposits, injection correction circuit fault, and exhaust back pressure fault.
[0088] S4. According to the fault diagnosis priority score, diagnose and troubleshoot the fault causes in turn.
[0089] In this embodiment, the problems are checked according to the order of the above judgments, and the possible causes with high probability and high impact calculated by the model can be verified first. First, the CAN communication fault is checked. If the system is indeed found to have a CAN communication problem, such as a short circuit, open circuit, virtual connection, software problem, etc., the closed loop of the problem is solved. Otherwise, the lower priority problems are eliminated until the cause is finally found and the problem is solved, and the cycle can be ended.
[0090] Embodiment 2:
[0091] A vehicle power loss problem diagnosis device comprises a model building module, an injection determination module, a diagnosis scoring module and a diagnosis troubleshooting module;
[0092] The model building module builds a diagnosis priority scoring model based on historical fault diagnosis information;
[0093] The fuel injection determination module determines whether fuel injection occurs when the vehicle loses power;
[0094] The diagnosis scoring module queries the diagnosis priority scoring model according to whether fuel injection is performed to obtain the diagnosis priority score;
[0095] The diagnosis and troubleshooting module diagnoses and troubleshoots the causes of the faults in sequence according to the fault diagnosis priority scores.
[0096] It should be noted that the above embodiments are only for more clearly illustrating the technical solutions of the present invention. Those skilled in the art will understand that the implementation methods of the present invention are not limited to the above contents, and obvious changes, replacements or substitutions based on the above contents do not exceed the scope of the technical solutions of the present invention; other implementation methods will also fall within the scope of the present invention without departing from the concept of the present invention.
Claims
1. A method for diagnosing a vehicle power loss problem, characterized in that: The specific method is as follows: Based on historical fault diagnosis information, a diagnostic priority scoring model is constructed; Determine if there was fuel injection when the vehicle lost power; According to whether fuel injection is performed, the diagnosis priority scoring model is queried to obtain the diagnosis priority score; According to the fault diagnosis priority score, diagnose and troubleshoot the fault causes in sequence.
2. The method for diagnosing a vehicle power loss problem as claimed in claim 1, characterized in that: The diagnostic priority scoring model includes: a comparison scoring model, a network scoring model and a SVIP scoring model.
3. The method for diagnosing a vehicle power loss problem as claimed in claim 2, characterized in that: The comparison scoring model includes a start-up without fuel injection comparison scoring sub-model and a start-up with fuel injection comparison scoring sub-model, and the start-up without fuel injection comparison scoring sub-model and the start-up with fuel injection comparison scoring sub-model are selected according to whether there is fuel injection when the vehicle loses power; The specific construction methods of the starting without fuel injection comparison scoring sub-model and the starting with fuel injection comparison scoring sub-model are as follows: Arrange all the causes of vehicle power loss in rows and columns; According to the number of vehicle power loss causes in the historical fault diagnosis information, the number of vehicle power loss causes in the row is divided by the number of vehicle power loss causes in the column to obtain the comparison model score of the vehicle power loss causes corresponding to the row; Calculate the average score of the comparison model scores for all rows corresponding to the causes of vehicle power loss as the benchmark average score.
4. The method for diagnosing a vehicle power loss problem as claimed in claim 2, characterized in that: The network scoring model is specifically constructed as follows: List all causes of vehicle power loss as a separate unit; Determine the correlation between various causes of vehicle power loss based on the experience database; Use directional arrows to connect all related causes of vehicle power loss; For each cause of vehicle power loss, there is a directional arrow pointing to another unit, 1 point is scored; Count the network model scores of all causes of vehicle power loss.
5. The method for diagnosing a vehicle power loss problem as claimed in claim 2, characterized in that: The SVIP scoring model includes a starting without fuel injection SVIP scoring sub-model and a starting with fuel injection SVIP scoring sub-model, and the starting without fuel injection SVIP scoring sub-model and the starting with fuel injection SVIP scoring sub-model are selected according to whether there is fuel injection when the vehicle loses power; The construction methods of the SVIP scoring sub-model for starting without fuel injection and starting with fuel injection are as follows: For all causes of vehicle power loss, impact scores and likelihood scores are performed respectively, and then the impact score is multiplied by the likelihood score to obtain the IP value scores of the causes of vehicle power loss.
6. The method for diagnosing a vehicle power loss problem as claimed in claim 3, 4 or 5, characterized in that: The reasons for the loss of power during starting without fuel injection include: fuel failure, cylinder cleaning function, CAN communication problems and fuel failure due to collision; Causes of fuel injection during starting that cause vehicle power loss include: air flow meter failure, exhaust back pressure failure, correction circuit failure and carbon deposits.
7. The method for diagnosing a vehicle power loss problem as claimed in claim 2, characterized in that: Get the diagnostic priority score as follows: Normalize the comparison model scores, network model scores and IP value scores of each cause of vehicle power loss; The diagnostic priority score for each cause of vehicle power loss is calculated by using the comparison model score, network model score and IP value score after weighted normalization with preset weights.
8. The method for diagnosing a vehicle power loss problem as claimed in claim 1, characterized in that: The diagnostic priority scoring model includes: a comparative scoring model, a network scoring model or a SVIP scoring model.
9. The method for diagnosing a vehicle power loss problem as claimed in claim 1, characterized in that: The diagnostic priority scoring model includes: a comparison scoring model and a network scoring model, or a comparison scoring model and an SVIP scoring model, or a network scoring model and an SVIP scoring model.
10. A vehicle power loss problem diagnosis device, characterized in that: It includes a model building module, a fuel injection determination module, a diagnostic scoring module and a diagnostic troubleshooting module; The model building module builds a diagnosis priority scoring model based on historical fault diagnosis information; The fuel injection determination module determines whether fuel injection occurs when the vehicle loses power; The diagnosis scoring module queries the diagnosis priority scoring model according to whether fuel injection is performed to obtain the diagnosis priority score; The diagnosis and troubleshooting module diagnoses and troubleshoots the causes of the faults in sequence according to the fault diagnosis priority scores.
11. A storage medium, characterized in that: A plurality of instructions are stored, and a processor loads the instructions to execute the automobile power loss problem diagnosis method as described in any one of claims 1 to 9.
12. A vehicle controller installed in a hybrid vehicle, characterized in that: It includes the vehicle power loss problem diagnosis device as described in claim 10, and / or the storage medium as described in claim 11.