电动汽车永磁同步电机BP神经网络故障诊断模型研究  

Research of Fault Diagnosis Model for Electric Vehicle Permanent Magnet Synchronous Motor on BP Neural Network

作　　者：乔维德 QIAO Wei-de(Research and Quality Control Division,Wuxi Open University,Wuxi,Jiangsu 214011,China)

机构地区：[1]无锡开放大学科研与发展规划处,江苏无锡214011

出　　处：《石家庄学院学报》2024年第6期50-55,共6页Journal of Shijiazhuang University

摘　　要：永磁同步电机作为电动汽车应用较为广泛的驱动电机,其故障诊断技术关乎电动汽车的安全可靠运行.为实现永磁同步电机故障的精准诊断,提出一种基于改进遗传算法优化反向传播(BP)神经网络的永磁同步电机故障诊断模型,该模型将通过小波包分解提取电机定子绕组电流故障特征信号作为BP神经网络输入,利用改进遗传算法优化训练BP神经网络.仿真实验分析表明:相比于BP算法、遗传算法,改进遗传算法优化BP神经网络模型的电机故障诊断速度快、精度高,为电动汽车驱动电机故障诊断提供一种新的技术方案和应用手段.As widely used driving motor in electric vehicles,the fault diagnosis technology of permanent magnet synchronous motors is crucial for the safe and reliable operation of electric vehicles.To achieve accurate diagnosis of permanent magnet synchronous motor faults,a fault diagnosis model for permanent magnet synchronous motors based on improved genetic algorithm optimized back propagation(BP)neural network is constructed.The model extracts the fault characteristic signal of the motor stator winding current through wavelet packet decomposition as the input of the BP neural network,and uses the improved genetic algorithm to optimize the training of the BP neural network.Simulation experiment analysis shows that compared with BP algorithm and genetic algorithm,the improved genetic algorithm optimizing the BP neural network model for motor fault diagnosis with fast speed,high precision,provides a new technical solution and application tool for fault diagnosis of electric vehicle drive motor.

关 键 词：永磁同步电机 小波包分解 改进遗传算法 故障诊断 

分 类 号：TM341[电气工程—电机]