CN-122008766-A - Air spring fault early warning method and device, electronic equipment and storage medium

CN122008766ACN 122008766 ACN122008766 ACN 122008766ACN-122008766-A

Abstract

The embodiment of the application provides a fault early warning method, device, electronic equipment and storage medium for an air spring, which comprise the steps of obtaining running state data, air spring control data and driving condition data of a vehicle, respectively carrying out feature extraction on the running state data and the air spring control data to obtain a plurality of feature data, wherein the plurality of feature data comprise time domain feature data, frequency domain feature data, vehicle asymmetry feature data, attitude stability feature data and control signal feature data, determining weight parameters corresponding to the feature data according to the driving condition data, carrying out weighted fusion on the plurality of feature data based on the weight parameters corresponding to the feature data to obtain fusion feature data, and determining the health state and fault type of the air spring according to the fusion feature data. The application can effectively reduce false recognition and improve the accuracy of the determination of the health state and the fault type.

Inventors

LIANG RUNQIU
HUANG ZONGYUAN
LI ZUQING
QIAO BIN
GUO QUANDONG

Assignees

重庆长安汽车股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260409

Claims (10)

1. A fault early warning method for an air spring, the method comprising: Acquiring running state data, air spring control data and driving condition data of a vehicle; respectively carrying out feature extraction on the driving state data and the air spring control data to obtain a plurality of feature data, wherein the plurality of feature data comprise time domain feature data, frequency domain feature data, vehicle asymmetry feature data, attitude stability feature data and control signal feature data; according to the driving condition data, determining weight parameters corresponding to the characteristic data; based on weight parameters corresponding to the feature data, weighting and fusing the feature data to obtain fused feature data; and determining the health state and the fault type of the air spring according to the fusion characteristic data.
2. The method according to claim 1, wherein determining the weight parameter corresponding to each feature data according to the driving condition data comprises: according to the driving condition data, initial weight parameters corresponding to the characteristic data are adjusted to obtain target weight parameters corresponding to the characteristic data; The weighting fusion is carried out on the plurality of feature data based on the weight parameters corresponding to the feature data to obtain fusion feature data, and the method comprises the following steps: And carrying out weighted fusion on the plurality of feature data based on the target weight parameters corresponding to the feature data to obtain fused feature data.
3. The method of claim 2, wherein the driving condition data includes a vehicle speed, a steering angle of a steering wheel, and a road surface type, and the adjusting initial weight parameters corresponding to each feature data according to the driving condition data to obtain target weight parameters corresponding to each feature data includes: When the vehicle speed is in a first preset range, the steering angle of the steering wheel is smaller than or equal to the first preset angle, and the road surface type belongs to a flat road surface type, initial weight parameters corresponding to the characteristic data are kept unchanged; And when the vehicle speed is in a second preset range, and/or the steering angle of the steering wheel is larger than the first preset angle, and/or the road surface type does not belong to the flat road surface type, adjusting initial weight parameters corresponding to the characteristic data to obtain target weight parameters corresponding to the characteristic data, wherein the lower limit value of the second preset range is larger than the upper limit value of the first preset range.
4. The method of claim 3, wherein the adjusting the initial weight parameter corresponding to each feature data to obtain the target weight parameter corresponding to each feature data includes: When the vehicle speed is in the second preset range, the steering angle of the steering wheel is smaller than or equal to a first preset angle, and the road surface type belongs to the flat road surface type, the initial weight parameters corresponding to the time domain feature data, the frequency domain feature data and the gesture stability feature data are respectively increased, and the initial weight parameters corresponding to the control signal feature data are reduced, so that the target weight parameters corresponding to the feature data are obtained; Under the condition that the road surface type does not belong to the flat road surface type, the initial weight parameters corresponding to the time domain feature data, the frequency domain feature data and the vehicle asymmetry feature data are enlarged, and the initial weight parameters corresponding to the gesture stability feature data and the control signal feature data are reduced, so that the target weight parameters corresponding to the feature data are obtained; And under the condition that the steering angle of the steering wheel is larger than the first preset angle, the initial weight parameters corresponding to the vehicle asymmetry characteristic data and the gesture stability characteristic data are increased, and the initial weight parameters corresponding to the control signal characteristic data are decreased, so that the target weight parameters corresponding to the characteristic data are obtained.
5. The method of claim 1, wherein the driving state data includes wheel speeds and wheel accelerations of the respective wheels, the driving state data further includes a left side suspension stroke, a right side suspension stroke, a pitch angle speed and a roll angle speed of the vehicle, the feature extracting is performed on the driving state data and the air spring control data, respectively, to obtain a plurality of feature data, including: extracting frequency domain features of the driving state data to obtain frequency domain feature data; extracting time domain features of the driving state data to obtain time domain feature data; Determining the vehicle asymmetry characteristic data according to the left side suspension travel, the right side suspension travel, the wheel speeds and the wheel accelerations of all wheels; determining the attitude stability characteristic data according to the pitch angle speed and the roll angle speed; And carrying out feature extraction on the air spring control data to obtain the control signal feature data.
6. The method according to claim 1, wherein determining the weight parameter corresponding to each feature data according to the driving condition data comprises: Determining weight parameters corresponding to the characteristic data according to the target fault early warning model and the driving condition data; the weighting fusion is carried out on the plurality of feature data based on the weight parameters corresponding to the feature data to obtain fusion feature data, and the health state and the fault type of the air spring are determined according to the fusion feature data, and the method comprises the following steps: and weighting and fusing the plurality of characteristic data based on weight parameters corresponding to the characteristic data by utilizing the target fault early warning model to obtain fused characteristic data, and determining the health state and fault type of the air spring according to the fused characteristic data.
7. The method according to any one of claims 1-6, further comprising: acquiring multiple sets of training sample data, wherein each set of training sample data comprises sample driving state data, sample air spring control data, sample driving condition data, real health state and real fault type; And training the initial fault early-warning model by taking the real health state and the real fault type as training labels and adopting the plurality of groups of training samples to obtain a target fault early-warning model, wherein the target fault early-warning model is used for predicting the health state and the fault type of the air spring based on the running state data, the air spring control data and the driving working condition data of the vehicle.
8. The utility model provides an air spring's trouble early warning device which characterized in that includes: The data acquisition module is used for acquiring running state data, air spring control data and driving condition data of the vehicle; the characteristic extraction module is used for respectively carrying out characteristic extraction on the running state data and the air spring control data to obtain a plurality of characteristic data, wherein the plurality of characteristic data comprise time domain characteristic data, frequency domain characteristic data, vehicle asymmetry characteristic data, attitude stability characteristic data and control signal characteristic data; The weight distribution module is used for determining weight parameters corresponding to the characteristic data according to the driving condition data; The feature fusion module is used for carrying out weighted fusion on the plurality of feature data based on the weight parameters corresponding to the feature data to obtain fusion feature data; And the fault determining module is used for determining the health state and the fault type of the air spring according to the fusion characteristic data.
9. An electronic device is characterized by comprising a memory and a processor; The memory stores computer-executable instructions; The processor executing computer-executable instructions stored in the memory, causing the processor to perform the method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.

Description

Air spring fault early warning method and device, electronic equipment and storage medium Technical Field The present application relates to the field of vehicle technologies, and in particular, to a method and an apparatus for early warning of faults of an air spring, an electronic device, and a storage medium. Background The air spring is used as a core part of an automobile air suspension system, provides elastic support through compressed air, and can dynamically adjust the rigidity and damping of the suspension according to the load of a vehicle, road conditions and driving requirements, so that riding comfort, control stability and trafficability are improved. In the long-term operation process, the air spring is easy to have the problems of rubber aging, curtain fatigue, sealing failure or air bag leakage, and the like, so that the system performance is gradually reduced, and even the safety problems of suspension collapse, vehicle out of control and the like are caused when the system performance is serious. Because the failure of the air spring often has the characteristic of coexistence of progressive and sudden, the failure is difficult to be found in time through routine inspection before the failure occurs, and therefore, the service life evaluation and fault early warning of the air spring are particularly important. In the related art, the operation process of the air spring is simulated by finite element simulation using a digital twin model to estimate the remaining life of the air spring. However, the method has higher calculation complexity, higher construction and maintenance cost of the digital twin model, and difficulty in meeting the requirement of real-time early warning. Disclosure of Invention The embodiment of the application provides a fault early warning method and device for an air spring, electronic equipment and a storage medium, which can effectively reduce false recognition and improve the accuracy of determination of the health state and fault type. In a first aspect, an embodiment of the present application provides a fault early warning method for an air spring, where the method includes acquiring driving state data, air spring control data, and driving condition data of a vehicle, performing feature extraction on the driving state data and the air spring control data to obtain a plurality of feature data, where the plurality of feature data includes time domain feature data, frequency domain feature data, vehicle asymmetry feature data, attitude stability feature data, and control signal feature data, determining weight parameters corresponding to the feature data according to the driving condition data, performing weighted fusion on the plurality of feature data based on the weight parameters corresponding to the feature data to obtain fusion feature data, and determining a health state and a fault type of the air spring according to the fusion feature data. In one possible implementation manner, determining the weight parameter corresponding to each feature data according to the driving condition data includes adjusting an initial weight parameter corresponding to each feature data according to the driving condition data to obtain a target weight parameter corresponding to each feature data, and performing weighted fusion on the feature data based on the weight parameter corresponding to each feature data to obtain fusion feature data, wherein the step of performing weighted fusion on the feature data based on the target weight parameter corresponding to each feature data to obtain fusion feature data. In a possible implementation manner, the driving condition data comprise a vehicle speed, a steering wheel steering angle and a road surface type, the initial weight parameters corresponding to the characteristic data are adjusted according to the driving condition data to obtain target weight parameters corresponding to the characteristic data, the initial weight parameters corresponding to the characteristic data are kept unchanged when the vehicle speed is in a first preset range, the steering wheel steering angle is smaller than or equal to the first preset angle, and the road surface type belongs to a flat road surface type, and the initial weight parameters corresponding to the characteristic data are adjusted when the vehicle speed is in a second preset range, and/or the steering wheel steering angle is larger than the first preset angle, and/or the road surface type does not belong to the flat road surface type, so that the target weight parameters corresponding to the characteristic data are obtained. In one possible implementation, the adjusting the initial weight parameters corresponding to each feature data to obtain the target weight parameters corresponding to each feature data includes that when the vehicle speed is in a second preset range and the steering angle of the steering wheel is smaller than or equal to a first preset angle and the road surface t