负载波动下感应电动机转子断条故障诊断  

Broken Rotor Bar Fault Diagnosis for Induction Motors under Oscillating Load Torque

作　　者：吴文军 张晋瑞 尚仪 WU Wen-jun;ZHANG Jin-rui;SHANG Yi(Tianfu New Area Power Supply Company,State Grid Sichuan Electric Power Company,Chengdu 610041,China;Northeast Normal University,Changchun 130024,China)

机构地区：[1]国网四川省电力公司天府新区供电公司,成都610041 [2]东北师范大学,长春130024

出　　处：《微特电机》2019年第6期31-36,41,共7页Small & Special Electrical Machines

摘　　要：针对波动负载下感应电动机转子断条故障特征提取与状态识别问题,研究一种基于瞬时功率与离散小波的波动负载下感应电动机转子断条故障提取方法,并给出了明确有效的检测判据。该方法计算电动机瞬时功率,进行离散小波分解并提取特征频段能量,并通过比较瞬时无功功率中特征频段的小波能量幅值Eq与瞬时有功功率中相应频段的能量幅值Ep的大小形成诊断判断。创建了以随机森林为基分类器的集成分类器,提高负载波动下感应电动机转子断条故障识别的精确性。通过实验验证了该方法及其新判据的有效性。To solve the problem of broken rotor bar fault feature extraction and state recognition for induction motors under oscillating load torque,a novel fault feature extraction method of broken rotor bar fault for induction motors with oscillating load torque was proposed on the basis of combining instantaneous power and discrete wavelet transformation(DWT),and a definite diagnosis criteria was established.The core of the method is to perform discrete wavelet transform to the instantaneous power signal of induction motors.Diagnosis criteria was constructed via comparing the wavelet energy amplitude of characteristic frequency-band in instantaneous reactive power(IRP)with that in instantaneous active power(IAP).An ensemble classifier based on random forests was constructed,which improves the accuracy of broken rotor bar fault identification for induction motors under oscillating load torque.The experimental results prove the effectiveness of the method.

关 键 词：感应电动机 转子断条故障 负载波动 集成分类器 故障诊断 

分 类 号：TM346[电气工程—电机]