摘要
主轴承故障诊断最直接的方法是安装在线振动监测系统,但早期风机并无此系统.时至今日,现场安装的振动传感器的数量也非常少,而最为常见的方法是使用与振动最为接近的数据,即主轴承温度,从侧面推算主轴承是否发生故障.该文选取、设计EPF-BP算法的主轴承温度故障诊断方案,搭建诊断模型.对于诊断出的故障,构建主轴承温度异常故障树模型,使用protégé开放源代码软件,进行主轴承温度异常原因推理探索.添加Web本体语言-OWL的信息规则,实现语义层次上的信息共享、交互和处理.实验针对直驱型2 MW风电机组主轴承进行故障诊断,结果表明:该诊断系统可以更为有效、准确地识别风电机组核心部件主轴承温度异常,以提高主轴承运行的可靠性.
The most direct way to diagnose the main bearing fault is to install the on-line vibration monitoring system,but the early fan does not have this system.Today,the number of vibration sensors installed in the field is very small,and the most common method is to use the data closest to the vibration,that is,the temperature of the main bearing,to calculate whether the main bearing is out of order from the side.A temperature fault diagnosis scheme for main bearing of EPF-BP algorithm is selected and designed in this paper.For the fault diagnosed,the main bearing temperature abnormal fault tree model is constructed,and the protege open source code software is used to explore the reason of the main bearing temperature abnormal.The information rules of Web ontology language OWL are added to realize information sharing,interaction and processing at semantic level.The results show that the diagnosis system can identify the abnormal temperature of the main bearing of the core components of the wind turbine more effectively and accurately,so as to improve the reliability of the main bearing.
作者
常兴邦
段斌
CHANG Xing-bang;DUAN Bin(School of Automation and Electronic Information, Xiangtan University,Xiangtan 411105 China)
出处
《湘潭大学学报（自然科学版）》
CAS
2020年第5期25-34,共10页
Journal of Xiangtan University(Natural Science Edition)
基金
国家自然科学基金资助项目(61379063)。
