Whole vehicle level fault diagnosis method and system for new energy vehicle

Abstract

The invention relates to the technical field of fault monitoring, in particular to a new energy vehicle whole vehicle level fault diagnosis method and system. Obtaining fault phenomenon information of a to-be-diagnosed vehicle, and extracting a first keyword and a second keyword from the fault phenomenon information; determining a target secondary automobile component according to the first keyword and the second keyword on the basis of the whole automobile structure map; acquiring state information of the target secondary automobile component by using a corresponding abnormity monitoring unit, and determining whether the target secondary automobile component is abnormal or not according to the state information; if it is determined that abnormity exists, all fault types associated with the target secondary automobile component are determined according to a diagnosis map, and all the fault types are sequentially judged to obtain a fault diagnosis result of the to-be-diagnosed vehicle; and if it is determined that there is no abnormality, re-extracting the first keyword and the second keyword from the fault phenomenon information, and re-determining the target secondary automobile component. According to the invention, the efficiency and accuracy of fault diagnosis can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and in particular to a whole vehicle level fault diagnosis method and system for new energy vehicles. Background Art

[0002] Vehicles often have faults that affect the functions of the entire vehicle. After a fault occurs, it is necessary to diagnose the fault to determine the cause of the fault. The fault diagnosis mechanism of existing vehicles focuses more on monitoring the fuel consumption and emissions of the entire vehicle and diagnosing the status of the corresponding components, and the entire vehicle has relatively few parts. Compared with traditional vehicles, new energy vehicles have added component systems such as vehicle controllers, power battery systems, and DCDC. New energy vehicles have more component systems, and the failure conditions that occur are more complex and changeable, making the work of ensuring vehicle driving safety particularly complex. Therefore, it is necessary to provide a new energy vehicle whole vehicle level fault diagnosis method and system to improve the fault diagnosis efficiency of new energy vehicles. Summary of the invention

[0003] The present invention provides a whole vehicle level fault diagnosis method and system for new energy vehicles. The present invention extracts a first keyword and a second keyword as keyword features from fault phenomenon information to determine a target secondary automobile component associated with the fault phenomenon information in conjunction with a whole vehicle structure map, and then determines whether the target secondary automobile component has an abnormality through an abnormality monitoring unit corresponding to the target secondary automobile component to avoid misjudgment. Finally, the fault types associated with the target secondary automobile component are diagnosed in turn through a fault judgment process, and a final fault diagnosis result is obtained, thereby achieving the purpose of improving the efficiency and accuracy of fault diagnosis.

[0004] In a first aspect, the present invention provides a new energy vehicle whole vehicle level fault diagnosis method, which comprises: Acquire fault phenomenon information of a vehicle to be diagnosed, and extract a first keyword and a second keyword from the fault phenomenon information; Based on the pre-constructed vehicle structure map, according to the first keyword, a target first-level automobile component associated with the fault phenomenon is determined, and according to the second keyword, a target second-level automobile component is determined from all second-level automobile components included in the target first-level automobile component; Using an abnormality monitoring unit corresponding to a target secondary automobile component to collect status information of the target secondary automobile component, and determining whether the target secondary automobile component has an abnormality according to the status information; If it is determined that the target secondary vehicle component is abnormal, all fault types associated with the target secondary vehicle component are determined according to a pre-constructed diagnostic map, and all fault types are judged in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; If it is determined that there is no abnormality in the target secondary automobile component, the first keyword and the second keyword are re-extracted from the fault phenomenon information and the above steps are repeated.

[0005] Optionally, the first-level automobile components include a body system, a chassis system, an electrical system and a power system.

[0006] Optionally, the abnormality monitoring unit includes a sound sensor, a temperature sensor and a vibration sensor.

[0007] Optionally, the status information includes sound data, temperature data and vibration data; if at least one of the sound data, temperature data and vibration data is outside a preset normal range, it is determined that the target secondary automobile component is abnormal.

[0008] Optionally, the method for determining each abnormal monitoring unit corresponding to the target secondary automobile component includes: Initial abnormality monitoring units are respectively arranged at various preset positions of the vehicle; Based on the plurality of initial abnormality monitoring units, obtaining first test data; For each of the initial abnormality monitoring units, determining, based on the first test data, an association parameter between the initial abnormality monitoring unit and each of the secondary automobile components; Determining an associated discrete parameter of each initial abnormality monitoring unit according to an associated parameter between the initial abnormality monitoring unit and each of the secondary vehicle components; Taking the associated discrete parameter as greater than a preset associated discrete parameter threshold as a criterion, selecting an abnormal monitoring unit from a plurality of initial abnormal monitoring units; For each secondary automobile component, the abnormal monitoring unit whose associated parameter is higher than a preset threshold is determined as the abnormal monitoring unit corresponding to the target secondary automobile component.

[0009] Optionally, the calculation formula of the association parameter is: ;in, is the association parameter between the jth initial abnormal monitoring unit and the ith secondary automotive component, is the total number of tests performed with the i-th secondary vehicle component failure as the test condition, It is the number of times the jth initial abnormality monitoring unit detects an abnormality in the total number of tests performed with the i-th secondary automobile component failure as the test condition.

[0010] Optionally, the calculation formula of the associated discrete parameter corresponding to each initial abnormal monitoring unit is: ;in, is the associated discrete parameter corresponding to the jth initial abnormal monitoring unit, is the total number of initial abnormal monitoring units.

[0011] Optionally, determining all fault types in sequence to obtain a fault diagnosis result of the vehicle to be diagnosed includes: Obtain historical fault information of vehicles of the same model as the vehicle to be diagnosed; Determine the frequency of occurrence of each fault type associated with the target secondary vehicle component based on historical fault information of vehicles of the same model; Determine the order of determination of each fault type in the fault determination process according to the occurrence frequency of each fault type associated with the target secondary automotive component; The feedback information of the vehicle to be diagnosed is obtained according to the fault judgment process to generate a fault diagnosis result.

[0012] Optionally, according to the occurrence frequency of each fault type associated with the target secondary automobile component, the determination order of each fault type in the fault determination process is determined, and the fault type with a higher occurrence frequency is ranked higher in the determination order.

[0013] In a second aspect, the present invention provides a new energy vehicle whole vehicle level fault diagnosis system, which comprises: An acquisition module, used to acquire fault phenomenon information of a vehicle to be diagnosed, and extract a first keyword and a second keyword from the fault phenomenon information; a determination module, configured to determine a target primary automobile component associated with the fault phenomenon based on a pre-constructed vehicle structure map and according to the first keyword, and to determine a target secondary automobile component from among all secondary automobile components included in the target primary automobile component and according to the second keyword; A judgment module, used for collecting status information of the target second-level automobile component by using an abnormality monitoring unit corresponding to the target second-level automobile component, and determining whether the target second-level automobile component has an abnormality according to the status information; A diagnosis module, for determining all fault types associated with the target secondary automobile component according to a pre-constructed diagnosis map if it is determined that the target secondary automobile component is abnormal, and determining all fault types in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; The repeating module is used to re-extract the first keyword and the second keyword from the fault phenomenon information and re-determine the target second-level automobile component if it is determined that the target second-level automobile component does not have an abnormality.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention utilizes keyword features extracted from fault phenomenon information to cooperate with the whole vehicle structure map to quickly and accurately determine target secondary automobile components that may have abnormalities, and determines whether the target secondary automobile components do have abnormalities through an abnormality monitoring unit corresponding to the target secondary automobile component. Finally, each fault type is checked and determined according to the fault judgment process, and finally the fault diagnosis result is determined according to the feedback information in the troubleshooting process, so that the target secondary automobile component associated with the fault can be quickly and accurately determined, and targeted diagnosis and troubleshooting can be carried out, and the diagnostic efficiency and accuracy are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein: Figure 1 is a schematic flow chart of a whole vehicle level fault diagnosis method for a new energy vehicle in Example 1; Figure 2 It is a partial schematic diagram of the vehicle structure diagram in Example 1; Figure 3 is a partial schematic diagram of the diagnostic spectrum in Example 1; Figure 4 is a partial schematic diagram of the first diagnostic knowledge graph in Example 1; Figure 5 This is a partial schematic diagram of the second diagnostic knowledge graph in Example 1. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. Example 1

[0017] Combination Figure 1 This embodiment provides a new energy vehicle whole vehicle level fault diagnosis method, the method comprising: Step S1, obtaining fault phenomenon information of a vehicle to be diagnosed; extracting a first keyword and a second keyword from the fault phenomenon information; Specifically, the fault phenomenon information may be description information of the vehicle fault uploaded by a user or maintenance personnel, for example, "the engine idle speed of the vehicle is unstable with slight shaking during cold start, and the vehicle feels insufficient power during acceleration." The first keyword and the second keyword are used to describe the primary vehicle component and the secondary vehicle component, respectively.

[0018] Step S2: based on the pre-constructed vehicle structure map, according to the first keyword, determine the target primary automobile component associated with the fault phenomenon, and according to the second keyword, determine the target secondary automobile component from all secondary automobile components included in the target primary automobile component; In a specific embodiment, the vehicle structure map is used to record the associated schematic diagrams of multiple first-level automobile components and multiple second-level automobile components. As an example only, multiple first-level automobile components may include a body system, a chassis system, an electrical system, and a powertrain integrated system. Each first-level automobile component may include at least one second-level automobile component. For example, the chassis system may include a front suspension assembly, a rear suspension assembly, a wheel device, a steering system, etc. Based on at least one first keyword, at least one first-level automobile component associated with the fault phenomenon information can be determined.

[0019] All second-level automobile components included in the target first-level automobile components can be understood as candidate second-level automobile components. This embodiment extracts a second keyword for describing at least one candidate second-level automobile component from the fault phenomenon information, and uses the candidate second-level automobile component associated with the extracted second keyword as the target second-level automobile component.

[0020] To explain specifically with examples, for example, "the vehicle's engine idle speed is unstable during cold start, accompanied by slight shaking, and it feels lack of power during acceleration." The first keyword "power" is first extracted to determine that the first-level automobile components associated with the fault phenomenon information include a powertrain integrated system. The second-level automobile components included in the powertrain integrated system, such as the engine, motor, and battery pack, are taken as candidate second-level automobile components. Based on the candidate second-level automobile components, the second keyword "engine" is extracted from the fault phenomenon information to determine that the target second-level automobile component is the engine.

[0021] Step S3, using an abnormality monitoring unit corresponding to a target secondary automobile component to collect status information of the target secondary automobile component, and determining whether the target secondary automobile component has an abnormality according to the status information; It is understandable that when a secondary automobile component fails, the abnormality monitoring unit that can detect the abnormality can be used as the abnormality monitoring unit corresponding to the secondary automobile component. In a specific embodiment, the abnormality monitoring unit includes a sound sensor, a temperature sensor, a vibration sensor, etc. The state information includes sound data, temperature data, and vibration data; if at least one of the sound data, temperature data, and vibration data is outside the preset normal range, it is determined that the target secondary automobile component has an abnormality.

[0022] Since not every abnormality monitoring unit can accurately collect the real-time status information of the secondary automobile component, this embodiment screens a plurality of pre-arranged initial abnormality monitoring units and finally determines the abnormality monitoring unit corresponding to the target secondary automobile component.

[0023] The method for determining each abnormal monitoring unit corresponding to the target secondary automobile component includes: Initial abnormality monitoring units are respectively set at various preset positions of the vehicle; usually, the initial abnormality monitoring units are arranged at positions close to each secondary automobile component to monitor whether there are abnormalities in the secondary automobile component as much as possible.

[0024] Based on the multiple initial abnormality monitoring units, first test data is obtained; wherein the first test data may include sound, temperature, vibration and other data collected by the multiple initial abnormality monitoring units under different faults; For each of the initial abnormality monitoring units, based on the first test data, the association parameter between the initial abnormality monitoring unit and each of the secondary automobile components is determined; in a specific embodiment, the association parameter between the initial abnormality monitoring unit and each of the secondary automobile components can be calculated based on the following formula: ;in, is the association parameter between the jth initial abnormal monitoring unit and the ith secondary automotive component, is the total number of tests performed with the i-th secondary vehicle component failure as the test condition, It is the number of times the jth initial abnormality monitoring unit detects an abnormality in the total number of tests performed with the i-th secondary automobile component failure as the test condition.

[0025] According to the association parameters between the initial abnormality monitoring unit and each of the secondary automobile components, the associated discrete parameters of each initial abnormality monitoring unit are determined; in a specific embodiment, the associated discrete parameters corresponding to the initial abnormality monitoring unit are calculated based on the following formula: ;in, is the associated discrete parameter corresponding to the jth initial abnormal monitoring unit, is the total number of initial abnormal monitoring units.

[0026] Taking the associated discrete parameter being greater than a preset associated discrete parameter threshold as a criterion, an abnormal monitoring unit is screened out from a plurality of initial abnormal monitoring units; it can be understood that this embodiment screens the abnormal monitoring unit by associated discrete parameters to ensure the accuracy of the monitoring result.

[0027] For each secondary automobile component, the abnormal monitoring unit whose associated parameter is higher than a preset threshold is determined as the abnormal monitoring unit corresponding to the target secondary automobile component.

[0028] Among the screened abnormal monitoring units, the abnormal monitoring unit corresponding to each secondary automobile component is determined based on the associated parameters. During the diagnosis process, targeted monitoring can be performed through the abnormal monitoring unit corresponding to the target secondary automobile component to determine whether the target secondary automobile component is definitely abnormal.

[0029] Step S4: if it is determined that the target secondary automobile component is abnormal, all fault types associated with the target secondary automobile component are determined according to a pre-constructed diagnostic map, and all fault types are judged in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; if it is determined that the target secondary automobile component is not abnormal, the first keyword and the second keyword are re-extracted from the fault phenomenon information and the target secondary automobile component is re-determined.

[0030] The diagnostic map is used to record the fault type associated with each secondary automobile component. As an example, the fault types associated with the steering system include motor fault, sensor fault and power supply fault, etc., wherein the fault type can be further refined, for example, the fault type of motor fault is refined into steering force becoming larger or smaller, the fault type of sensor fault is refined into steering insensitivity, and the fault type of power supply fault is refined into steering power system not working properly.

[0031] The fault diagnosis results of the vehicle to be diagnosed are obtained by sequentially judging all fault types, including: Obtain historical fault information of vehicles of the same model as the vehicle to be diagnosed; determine the frequency of occurrence of each fault type associated with the target secondary vehicle component based on the historical fault information of the same model; determine the determination order of each fault type in the fault determination process according to the frequency of occurrence of each fault type associated with the target secondary vehicle component; wherein, the higher the frequency of occurrence of the fault type, the higher the determination order. Obtain feedback information of the vehicle to be diagnosed based on the fault determination process to generate a fault diagnosis result.

[0032] As an example only, the fault determination process includes: Step 1: Check the air filter and intake pipe; The feedback information of the vehicle to be diagnosed corresponding to step 1 may include whether the air filter is dirty or blocked, and whether the air intake duct is cracked or detached.

[0033] Step 2: Check the air flow sensor quality The feedback information of the vehicle to be diagnosed corresponding to step 2 may include whether the voltage and resistance of the air flow sensor are normal.

[0034] Step 3: Check the fuel system.

[0035] The feedback information of the vehicle to be diagnosed corresponding to step 3 may include whether the fuel pressure is normal and whether the fuel injection nozzle is blocked or damaged.

[0036] In another specific embodiment, the target secondary automobile component is determined by an abnormality monitoring unit and a pre-constructed first diagnostic knowledge graph and a second diagnostic knowledge graph. like Figure 4 As shown, the first diagnostic knowledge graph is used to record the abnormal monitoring unit and the first abnormal feature corresponding to each first-level automobile component. When a first-level automobile component fails, the abnormal monitoring unit that can detect the abnormality can be used as the abnormal monitoring unit corresponding to the first-level automobile component. Just as an example, the first-level automobile component 1 corresponds to abnormal monitoring unit 1, abnormal monitoring unit 2, abnormal monitoring unit 3, abnormal monitoring unit 4, and abnormal monitoring unit 5. The first abnormal feature may include abnormal monitoring unit 1, abnormal monitoring unit 2, abnormal monitoring unit 3, abnormal monitoring unit 4, and abnormal monitoring unit 5 detecting sound and / or vibration abnormalities under vehicle operating parameters 1, vehicle operating parameters 2, and vehicle operating parameters 3.

[0037] like Figure 5 As shown, the second diagnostic knowledge graph is used to record the abnormal monitoring unit and the second abnormal feature corresponding to each secondary automobile component. As an example only, the secondary automobile component 1 included in the primary automobile component 1 corresponds to the abnormal monitoring unit 1, the abnormal monitoring unit 2, and the abnormal monitoring unit 3, and the second abnormal feature corresponding to the secondary automobile component may include the abnormal monitoring unit 1, the abnormal monitoring unit 2, and the abnormal monitoring unit 3 detecting the abnormal sound and / or vibration under the vehicle operating parameter 1.

[0038] The method for determining the target secondary automobile component based on the abnormal monitoring unit and the pre-constructed first diagnostic knowledge graph and second diagnostic knowledge graph includes: Based on the information collected by the multiple abnormality monitoring units, a target abnormality monitoring unit is determined; the target abnormality monitoring unit may be an abnormality monitoring unit that detects an abnormality (eg, abnormal sound, abnormal vibration, and / or abnormal temperature).

[0039] Based on the target abnormality monitoring unit and the first diagnostic knowledge graph, at least one candidate second-level automobile component is determined; all second-level automobile components included in each first-level automobile component corresponding to each target abnormality monitoring unit are taken as candidate second-level automobile components; For each candidate second-level automobile component, based on the information collected by multiple abnormal monitoring units, the real-time status characteristics corresponding to the candidate second-level automobile component are determined, and based on the real-time status characteristics corresponding to the candidate second-level automobile component and the second diagnostic knowledge graph, it is judged whether the candidate second-level automobile component is the target second-level automobile component.

[0040] For each abnormal monitoring unit corresponding to the candidate secondary automobile component, perform empirical mode decomposition on the information collected by the abnormal monitoring unit, determine the characteristic components and characteristic residuals, extract the frequency domain characteristics and time domain characteristics of each characteristic component, and extract the frequency domain characteristics and time domain characteristics of the characteristic residuals; wherein the real-time state characteristics corresponding to the candidate secondary automobile component include the frequency domain characteristics and time domain characteristics of each characteristic component of each abnormal monitoring unit corresponding to the candidate secondary automobile component and the frequency domain characteristics and time domain characteristics of the characteristic residuals. The second abnormal characteristics corresponding to the secondary automobile component may include the frequency domain characteristics and time domain characteristics of each characteristic component of each abnormal monitoring unit associated with the secondary automobile component and the frequency domain characteristics and time domain characteristics of the characteristic residuals; Specifically, for each candidate second-level automobile component, the abnormality score of the candidate second-level automobile component can be determined based on the real-time status feature corresponding to the candidate second-level automobile component and the second abnormal feature corresponding to the candidate second-level automobile component, and the candidate second-level automobile component with an abnormality score greater than a preset abnormality score threshold is used as the target second-level automobile component.

[0041] In a specific embodiment, the abnormality score of each candidate secondary automobile component is calculated based on the following formula:

[0042] Among them, A k is the abnormality score of the kth candidate secondary automobile component, is the feature difference corresponding to the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component, E is the total number of abnormal monitoring units corresponding to the k-th candidate secondary automobile component, is the characteristic difference of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the f-th characteristic component, F is the total number of characteristic components of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component, is the characteristic difference of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the characteristic residual, a1 and a2 are preset weights, and a1 and a2 are both greater than 0, a 1+ a2=1, is the frequency domain feature of the fth feature component of the eth abnormal monitoring unit corresponding to the kth candidate secondary automobile component in the real-time state feature, is the frequency domain feature of the fth feature component of the eth abnormal monitoring unit corresponding to the kth candidate secondary automobile component in the second abnormal feature, is the time domain feature of the fth feature component of the eth abnormal monitoring unit corresponding to the kth candidate secondary automobile component in the real-time state feature, is the time domain feature of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the second abnormal feature in the f-th feature component, a3 and a4 are preset weights, and a3 and a4 are both greater than 0, a 3+ a4=1, is the frequency domain feature of the feature residual of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the real-time state feature, is the frequency domain feature of the feature residual of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the second abnormal feature, is the time domain feature of the feature residual of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the real-time state feature, is the time domain feature of the feature residual of the e-th abnormal monitoring unit corresponding to the k-th candidate secondary automobile component in the second abnormal feature, a5 and a6 have preset weights, and a5 and a6 are both greater than 0, a 5+ a6=1.

[0043] Based on the same inventive concept as in Example 1, this embodiment provides a whole vehicle level fault diagnosis system for new energy vehicles, which includes: An acquisition module, used to acquire fault phenomenon information of a vehicle to be diagnosed, and extract a first keyword and a second keyword from the fault phenomenon information; a determination module, configured to determine a target primary automobile component associated with the fault phenomenon based on a pre-constructed vehicle structure map and according to the first keyword, and to determine a target secondary automobile component from among all secondary automobile components included in the target primary automobile component and according to the second keyword; A judgment module, used for collecting status information of the target second-level automobile component by using an abnormality monitoring unit corresponding to the target second-level automobile component, and determining whether the target second-level automobile component has an abnormality according to the status information; A diagnosis module, for determining all fault types associated with the target secondary automobile component according to a pre-constructed diagnosis map if it is determined that the target secondary automobile component is abnormal, and determining all fault types in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; The repeating module is used to re-extract the first keyword and the second keyword from the fault phenomenon information and re-determine the target second-level automobile component if it is determined that the target second-level automobile component does not have an abnormality.

[0044] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A vehicle-level fault diagnosis method for new energy vehicles, characterized in that: include: Acquire fault phenomenon information of a vehicle to be diagnosed, and extract a first keyword and a second keyword from the fault phenomenon information; Based on the pre-constructed vehicle structure map, according to the first keyword, a target first-level automobile component associated with the fault phenomenon is determined, and according to the second keyword, a target second-level automobile component is determined from all second-level automobile components included in the target first-level automobile component; Using an abnormality monitoring unit corresponding to a target secondary automobile component to collect status information of the target secondary automobile component, and determining whether the target secondary automobile component has an abnormality according to the status information; If it is determined that the target secondary vehicle component is abnormal, all fault types associated with the target secondary vehicle component are determined according to a pre-constructed diagnostic map, and all fault types are judged in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; If it is determined that there is no abnormality in the target secondary automobile component, the first keyword and the second keyword are re-extracted from the fault phenomenon information and the target secondary automobile component is re-determined.

2. A vehicle-level fault diagnosis method for new energy vehicles according to claim 1, characterized in that: The first-level automobile components include body system, chassis system, electrical system and power system.

3. A vehicle-level fault diagnosis method for new energy vehicles according to claim 1, characterized in that: The abnormality monitoring unit includes a sound sensor, a temperature sensor and a vibration sensor.

4. A new energy vehicle whole vehicle level fault diagnosis method according to claim 3, characterized in that: The state information includes sound data, temperature data and vibration data; if at least one of the sound data, temperature data and vibration data is outside a preset normal range, it is determined that the target secondary automobile component is abnormal.

5. A new energy vehicle whole vehicle level fault diagnosis method according to claim 1, characterized in that: The method for determining each abnormal monitoring unit corresponding to the target secondary automobile component includes: Initial abnormality monitoring units are respectively arranged at various preset positions of the vehicle; Based on the plurality of initial abnormality monitoring units, obtaining first test data; For each of the initial abnormality monitoring units, determining, based on the first test data, an association parameter between the initial abnormality monitoring unit and each of the secondary automobile components; Determining an associated discrete parameter of each initial abnormality monitoring unit according to an associated parameter between the initial abnormality monitoring unit and each of the secondary vehicle components; Taking the associated discrete parameter as greater than a preset associated discrete parameter threshold as a criterion, selecting an abnormal monitoring unit from a plurality of initial abnormal monitoring units; For each secondary automobile component, the abnormal monitoring unit whose associated parameter is higher than a preset threshold is determined as the abnormal monitoring unit corresponding to the target secondary automobile component.

6. A vehicle-level fault diagnosis method for new energy vehicles according to claim 5, characterized in that: The calculation formula of the associated parameter is: ;in, is the association parameter between the jth initial abnormal monitoring unit and the ith secondary automotive component, is the total number of tests performed with the i-th secondary vehicle component failure as the test condition, It is the number of times the jth initial abnormality monitoring unit detects an abnormality in the total number of tests performed with the i-th secondary automobile component failure as the test condition.

7. A vehicle-level fault diagnosis method for new energy vehicles according to claim 6, characterized in that: The calculation formula of the associated discrete parameters corresponding to each initial abnormal monitoring unit is: ;in, is the associated discrete parameter corresponding to the jth initial abnormal monitoring unit, is the total number of initial abnormal monitoring units.

8. A new energy vehicle whole vehicle level fault diagnosis method according to claim 1, characterized in that: The method of sequentially determining all fault types to obtain the fault diagnosis result of the vehicle to be diagnosed includes: Obtain historical fault information of vehicles of the same model as the vehicle to be diagnosed; Determine the frequency of occurrence of each fault type associated with the target secondary vehicle component based on historical fault information of vehicles of the same model; Determine the order of determination of each fault type in the fault determination process according to the occurrence frequency of each fault type associated with the target secondary automotive component; The feedback information of the vehicle to be diagnosed is obtained according to the fault judgment process to generate a fault diagnosis result.

9. A vehicle-level fault diagnosis method for new energy vehicles according to claim 8, characterized in that: According to the occurrence frequency of each fault type associated with the target secondary automobile component, the judgment order of each fault type in the fault judgment process is determined, and the fault type with a higher occurrence frequency is ranked higher in the judgment order.

10. A new energy vehicle whole vehicle fault diagnosis system, characterized in that: include: An acquisition module, used to acquire fault phenomenon information of a vehicle to be diagnosed, and extract a first keyword and a second keyword from the fault phenomenon information; a determination module, configured to determine a target primary automobile component associated with the fault phenomenon based on a pre-built vehicle structure map and according to the first keyword, and to determine a target secondary automobile component from among all secondary automobile components included in the target primary automobile component and according to the second keyword; A judgment module, used for collecting status information of the target second-level automobile component by using an abnormality monitoring unit corresponding to the target second-level automobile component, and determining whether the target second-level automobile component has an abnormality according to the status information; A diagnosis module, for determining, if it is determined that the target secondary automobile component is abnormal, all fault types associated with the target secondary automobile component according to a pre-constructed diagnosis map, and determining all fault types in turn to obtain a fault diagnosis result of the vehicle to be diagnosed; The repeating module is used to re-extract the first keyword and the second keyword from the fault phenomenon information and re-determine the target second-level automobile component if it is determined that the target second-level automobile component does not have an abnormality.

Images