基于SDP和SURF特征提取的异步电机故障诊断方法  

A Fault Diagnosis Method of Asynchronous Motor Based on SDP and SURF Feature Extraction

作　　者：蒋亦悦 刘莺 王玺帏 龙卓 张晓飞 JIANG Yiyue;LIU Ying;WANG Xiwei;LONG Zhuo;ZHANG Xiaofei(China Shipbuilding and Ocean Engineering Design and Research,Shanghai 200011,China;College of Electrical and Information Engineering,Hunan University,Changsha 410082,China)

机构地区：[1]中国船舶及海洋工程设计研究院,上海200011 [2]湖南大学电气与信息工程学院,长沙410082

出　　处：《微电机》2022年第9期12-16,99,共6页Micromotors

摘　　要：在工业方面,电机长期运行中,电机的健康状态会下降,需对其进行故障诊断。传统检测方法在不同负载条件下对于电机故障诊断的准确率较低,本文提出了一种图像特征提取的新型故障诊断方法。通过对称点模式(SDP)和加速鲁棒特征算法(SURF),建立电机故障与图像特征之间的映射关系,通过字典模板统计匹配点来判断电机故障的状态,通过对比其他图像特征识别算法,该方法数据训练量和学习量较小,且准确率较高,获得了不错的故障诊断效果。In industrial field,the health of the motor will decline during long-term operation of the motor,and fault diagnosis is required.Traditional detection methods have low accuracy for motor fault diagnosis under different load conditions.This paper proposed a new fault diagnosis method based on image feature extraction.Through Symmetric Point Mode(SDP)and Accelerated Robust Feature Algorithm(SURF),the mapping relationship between motor faults and image features was established,and the status of motor faults could be judged through the dictionary template statistics matching points.By comparing other image feature recognition algorithms,the amount of data training and learning of this method is small,and the accuracy rate is high,and a good fault diagnosis effect is obtained.

关 键 词：感应电机 电机故障诊断 对称点模式 加速鲁棒特征 

分 类 号：TM346[电气工程—电机]