CN-122017553-A - Abnormality diagnosis method, device and equipment for vehicle-mounted motor

CN122017553ACN 122017553 ACN122017553 ACN 122017553ACN-122017553-A

Abstract

The application provides an abnormality diagnosis method, device and equipment for a vehicle-mounted motor, which are applied to the technical field of motor control. The method comprises the steps of collecting motor signals of the vehicle-mounted motor in the running process. The motor signals include voltage signals, current signals, and temperature signals. And according to each acquisition time, fusing the voltage state characteristic vector extracted from the voltage signal and the auxiliary state characteristic vector extracted from the current signal and the temperature signal to obtain the comprehensive state characteristic vector of the vehicle-mounted motor at the acquisition time. And determining a time sequence accumulated value corresponding to each fault type in the preset fault types according to the comprehensive state characteristic vectors of the plurality of acquisition moments. According to the time sequence accumulated value corresponding to each fault type, the abnormal diagnosis result of the vehicle-mounted motor is determined, and the problem of low accuracy of the traditional vehicle-mounted motor abnormality diagnosis method can be solved.

Inventors

LI WEN
GUO YUHUI
LIU BO
LIU ZHENXING

Assignees

奇瑞汽车股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260127

Claims (10)

1. An abnormality diagnosis method of an in-vehicle motor, characterized by comprising: Collecting motor signals of the vehicle-mounted motor in the running process, wherein the motor signals comprise voltage signals, current signals and temperature signals; For each acquisition time, according to the voltage state characteristic vector extracted from the voltage signal and the auxiliary state characteristic vector extracted from the current signal and the temperature signal, fusion is carried out to obtain the comprehensive state characteristic vector of the vehicle-mounted motor at the acquisition time; determining a time sequence accumulation value corresponding to each fault type in preset fault types according to the comprehensive state feature vectors at a plurality of acquisition moments; And determining an abnormality diagnosis result of the vehicle-mounted motor according to the time sequence accumulation value corresponding to each fault type.
2. The method according to claim 1, wherein determining a time sequence cumulative value corresponding to each of the preset fault types according to the integrated state feature vectors of the plurality of acquisition moments comprises: Combining the comprehensive state feature vectors at the acquisition time according to the time sequence to obtain a comprehensive state feature time sequence; And determining a time sequence accumulation value of any target fault type in the fault types according to the continuous state of the target fault type in the comprehensive state characteristic time sequence.
3. The method of claim 2, wherein said determining a time series cumulative value for said target fault type based on a sustained state of said target fault type in said integrated state signature time series comprises: and under the condition that the target fault type continuously appears in the comprehensive state characteristic time sequence, determining a time sequence accumulated value of the target fault type according to the initial value of the configuration of the target fault type and the duration time of the target fault type.
4. A method according to claim 3, characterized in that the method further comprises: When the comprehensive state characteristic time sequence is determined to have the abrupt fault characteristic at any acquisition time, adding a time sequence increment based on the time sequence accumulated value of the target fault type with the abrupt fault characteristic as the matching, and obtaining the time sequence accumulated value after increment updating.
5. The method according to claim 1, wherein the determining the abnormality diagnosis result of the in-vehicle motor according to the time-series accumulated value corresponding to each of the fault types includes: determining the confidence level of the vehicle-mounted motor in each fault type according to the time sequence accumulated value corresponding to each fault type; And determining an abnormality diagnosis result of the vehicle-mounted motor according to the confidence coefficient of each fault type.
6. The method of claim 5, wherein determining an abnormality diagnosis result of the in-vehicle motor according to the confidence level of each of the fault types, comprises: Determining the highest confidence coefficient in the confidence coefficient, the candidate fault type to which the highest confidence coefficient belongs and the next highest confidence coefficient in the confidence coefficient according to the confidence coefficient of each fault type; and determining that the abnormal diagnosis result is the candidate fault type under the condition that the highest confidence coefficient is larger than a first threshold value and the difference value between the highest confidence coefficient and the second highest confidence coefficient is larger than a second threshold value.
7. The method according to claim 1, wherein the fusing the voltage state feature vector extracted from the voltage signal and the auxiliary state feature vector extracted from the current signal and the temperature signal to obtain the comprehensive state feature vector of the vehicle-mounted motor at the acquisition time includes: converting the voltage signal to obtain two-dimensional voltage data containing a first voltage component and a second voltage component; determining the voltage state feature vector according to the two-dimensional voltage data; extracting a current fundamental wave amplitude of the current signal according to the current signal; determining an actual measurement temperature value of the vehicle-mounted motor according to the temperature signal and a temperature compensation coefficient matched with the environment where the current vehicle-mounted motor is positioned; determining the auxiliary state characteristic vector according to the current fundamental wave amplitude and the actually measured temperature value; and splicing according to the voltage state characteristic vector and the auxiliary state characteristic vector to obtain the comprehensive state characteristic vector.
8. An abnormality diagnosis device for an in-vehicle motor, the device comprising: the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring motor signals of the vehicle-mounted motor in the operation process, and the motor signals comprise voltage signals, current signals and temperature signals; The fusion module is used for fusing the voltage state characteristic vector extracted from the voltage signal and the auxiliary state characteristic vector extracted from the current signal and the temperature signal according to each acquisition time to obtain the comprehensive state characteristic vector of the vehicle-mounted motor at the acquisition time; The determining module is used for determining a time sequence accumulated value corresponding to each fault type in the preset fault types according to the comprehensive state feature vectors at a plurality of acquisition moments; The determining module is further used for determining an abnormality diagnosis result of the vehicle-mounted motor according to the time sequence accumulated value corresponding to each fault type.
9. An abnormality diagnosis apparatus of an in-vehicle motor, characterized in that it includes a processor and a memory storing machine-executable instructions executable by the processor to implement the abnormality diagnosis method of an in-vehicle motor according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that the computer program, when executed by a processor, realizes the abnormality diagnosis method of the in-vehicle motor according to any one of claims 1 to 7.

Description

Abnormality diagnosis method, device and equipment for vehicle-mounted motor Technical Field The present application relates to the field of motor control technologies, and in particular, to a method, an apparatus, and a device for diagnosing an abnormality of a vehicle-mounted motor. Background With the rapid development of new energy automobiles, the vehicle-mounted motor has become a core component for influencing the safety and performance of the whole automobile. The traditional motor abnormality diagnosis method mainly depends on an AI model operated by a high-performance computing platform, has the problems of high delay, high power consumption and high cost, and is difficult to be deployed in real time in a vehicle-mounted embedded system with limited resources. Meanwhile, the related technology is mostly based on single signal source for analysis, and has insufficient adaptability to complex and changeable motor working conditions and unknown fault modes, so that the diagnosis accuracy and the robustness are low. In addition, the traditional diagnosis model lacks on-line learning and self-adaptive updating capabilities, can not effectively cope with characteristic drift caused by factors such as motor aging, environmental change and the like, and limits the reliability of long-term application of the model. Therefore, there is a need for an abnormality diagnosis method, apparatus and device for an in-vehicle motor, which solve the problem of low accuracy in the abnormality diagnosis method of the conventional in-vehicle motor. Disclosure of Invention The application aims to provide an abnormality diagnosis method, device and equipment for a vehicle-mounted motor, and solves the problem of low accuracy in the conventional abnormality diagnosis method for the vehicle-mounted motor. In a first aspect, an embodiment of the present application provides a method for diagnosing an abnormality of a vehicle-mounted motor, where the method includes collecting a motor signal of the vehicle-mounted motor during an operation process. The motor signals include voltage signals, current signals, and temperature signals. And according to each acquisition time, fusing the voltage state characteristic vector extracted from the voltage signal and the auxiliary state characteristic vector extracted from the current signal and the temperature signal to obtain the comprehensive state characteristic vector of the vehicle-mounted motor at the acquisition time. And determining a time sequence accumulated value corresponding to each fault type in the preset fault types according to the comprehensive state characteristic vectors of the plurality of acquisition moments. And determining an abnormal diagnosis result of the vehicle-mounted motor according to the time sequence accumulated value corresponding to each fault type. According to the abnormality diagnosis method for the vehicle-mounted motor, provided by the embodiment of the application, the motor signals of the vehicle-mounted motor in the running process are collected, and fusion is carried out according to the voltage state characteristic vector extracted from the voltage signal and the auxiliary state characteristic vector extracted from the current signal and the temperature signal at each collection time, so that the comprehensive state characteristic vector of the vehicle-mounted motor at the collection time is obtained. And then, accumulating the comprehensive state characteristics of the plurality of acquisition moments in a time dimension to obtain a time sequence accumulated value corresponding to each fault type in the preset fault types. Finally, confidence calculation and dual threshold judgment are carried out based on the accumulated value One possible implementation manner of determining a time sequence accumulation value corresponding to each fault type in the preset fault types according to the comprehensive state feature vectors at a plurality of acquisition moments comprises the steps of combining the comprehensive state feature vectors at the plurality of acquisition moments according to time sequences to obtain a comprehensive state feature time sequence. And determining a time sequence accumulated value of the target fault type according to the continuous state of the target fault type in the comprehensive state characteristic time sequence aiming at any target fault type in the fault types. One possible implementation manner of determining the time sequence accumulated value of the target fault type according to the continuous state of the target fault type in the comprehensive state characteristic time sequence includes determining the time sequence accumulated value of the target fault type according to the initial value of the configuration of the target fault type and the duration of the target fault type under the condition that the target fault type continuously appears in the comprehensive state characteristic time sequence. When the com