基于小波和经验模态分解的风力发电机组主轴承故障自动识别  

Automatic Identification of Main Bearing Faults in Wind Turbine Based on Wavelet and Empirical Mode Decomposition

作　　者：高一文 GAO Yiwen(State Grid Shandong Comprehensive Energy Service Co.,Ltd.,Jinan,Shandong 250000,China)

机构地区：[1]国网山东综合能源服务有限公司,山东济南250000

出　　处：《自动化应用》2024年第12期197-199,共3页Automation Application

摘　　要：常规的风力发电机组主轴承故障自动识别节点多设定为独立形式,自动识别范围受限制,导致误识率增加,为此,提出对基于小波和经验模态分解的风力发电机组主轴承故障自动识别方法的设计。根据目前的测试,采用多目标的方式,打破自动识别范围的限制,部署多目标故障监测节点,在此基础上提取主轴承故障振动信号特征,并构建小波+经验模态分解发电机组主轴承故障自动识别模型,采用交互标记实现故障自动识别处理。结果表明,此次设计的小波和经验模态分解风力发电机组主轴承故障自动识别测试组最终得出的误识率被较好地控制在10%以下,说明在小波和经验模态分解技术的辅助下,设计的主轴承故障自动识别方法更高效,针对性较强,具有实际的应用价值。The automatic identification nodes of main bearing fault of conventional wind turbine are mostly set as independent forms,and the automatic identification range is limited,resulting to the increase of misidentification rate.Therefore,the design of automatic identification method of main bearing fault of wind turbine based on wavelet and empirical mode decomposition is proposed.According to the current test,adopt the way of multi-target,break the limit of automatic identification range,multi-target fault monitoring node deployment,based on this,extract the main bearing fault vibration signal characteristics,and build the wavelet+experience mode decomposition generator set main bearing fault automatic identification model,using the interactive mark to realize automatic fault identification processing.The results show that the misidentification rate obtained by the designed wavelet and empirical mode decomposition wind turbine main bearing fault automatic identification test group is well controlled below 10%,indicating that with the assistance of wavelet and empirical mode decomposition technology,the designed main bearing fault automatic identification method is more efficient,targeted,and has practical application value.

关 键 词：小波技术 经验模态分解 风力发电机组 主轴承 故障识别 自动识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]