新能源汽车驱动电机冷却系统劣化故障预测

打开文本图片集

Deterioration fault prediction of the drive-motor cooling-system fornewenergyvehicles

LIU Chiwei1， HUANG Yundi2

1.InstituteofMechanicalandElectricalEngineering，ZhongshanPolytechnic，Zhongshan528404，China； 2.InstituteofInformationEngineering，ZhongshanPolytechnic，Zhongshan528404，China）

Abstract：Amulti-clasifiermodel of Principal-Component-Analysisand theParticle-Swarm-Optimization Support-Vector-Machine （PCA-GOA-LSSVM）was proposed todetectand predict thedeteriorationofthe cooling systemofthe drive motorof new energy vehiclesas earlyas possbleand reduce the occurrence of motor power limit orshutdowncaused byexcessivecoolant temperature.The Principal Component Analysis （PCA）method was used to reduce the dimensionalityand reconstruct the fault characteristics.The Grasshopper Optimization Algorithm （GOA）was used to optimize parameters of Least Square Support Vector Machine （LSSVM）.The sampledatacollcted from thereal vehicle fault test，were respectivelyinputto the LSSVM prediction model， （PCA-PSO-SVM），andthe PCA-GOA-LSSVM models forcomparison testing.The results show that for the multi-classification prediction model based on PCA-GOA-LSSVM，the accuracy reaches 91.41% with a precision of 86.25% ，which is higher than the compared prediction model.The model can be used in the performance deteriorationpredictionandfaultdiagnosisofthecoolingsystemofthedrivemotorof newenergyvehicles，and canaccuratelyremind tomaintain thevehicle timelyand effectively judge the fault type.

Keywords：new energyvehicles；drive-motorcooling-system；fault prediction；least squares support vector machine （LSSVM）； grasshopper optimization algorithm （GOA）； principal component analysis （PCA）

开展驱动电机冷却系统故障预测研究，实时监控冷却系统散热性能的劣化情况，实现早期故障预警，及时进行相关装置的检查维护，可有效减少车辆故障机率，优化驱动电机冷却系统产品开发和设计。（剩余12629字）