徐开,郑小霞
XU Kai,ZHENG Xiaoxia

• 1:上海电力学院自动化工程学院

摘要(Abstract)：

提出了综合考虑风电机组转速及输入/输出轴水平和垂直方向振动信号,对故障数据依照转动周期分组后分别对每个周期的时域指标进行提取,而后基于SVM(支持向量机)对提取后的数据进行4种状态下故障分类的方法。测试结果表明,该方法简单有效,具有很好的故障识别能力,适合风电机组齿轮箱故障诊断。
The paper introduce a fault classification method. In this method, rotation speed of wind turbine and vibration signal in horizontal and vertical direction of input and output shafts are taken into consideration;in accordance with rotation period, the fault data is grouped and time-domain indexes in each period are extracted, after which faults in four conditions are classified on the basis of extracted data of SVM(support vector machine). The test result show that the method is simple and effective, and it can identify faults and is suitable for diagnosis of faults in gear boxes of wind turbine generating units.

关键词(KeyWords)： 多分类;支持向量机;风电机组;故障诊断
multi-classification;support vector machine(SVM);wind turbine generating units;fault diagnosis

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 徐开,郑小霞
XU Kai,ZHENG Xiaoxia

DOI: 10.19585/j.zjdl.2015.04.015

参考文献(References)：

• [1]HAMEED Z,HONG Y,CHO Y,et al.Condition monitoring and faultdetection of wind turbines and related algorithms:a review[J].Renewable and Sustainable Energy Reviews,2009,13(1):1-39.
• [2]AMIRAT Y,BENBOUZID M,AL-AHMAR E,et al.A brief status oncondition monitoring and fault diagnosis in wind energy conversionsystems[J].Renewable and Sustainable Energy Reviews,2009,13(9):2629-2636.
• [3]梁伟宸,许湘莲,庞可,等.风电机组故障诊断实现方法探讨[J].高压电器,2011,47(8):57-62.
• [4]苏勋文,米增强,王毅.风电场常用等值方法的适用性及其改进研究[J].电网技术,2010,34(6):175-180.
• [5]方瑞明.支持向量机理论及其应用分析[M].北京:中国电力出版社,2007.
• [6]魏于凡.支持向量机在智能故障诊断中的应用研究[D].保定:华北电力大学,2007.
• [7]安学利,蒋东翔.风力发电机组运行状态的混沌特性识别及其趋势预测[J].电力自动化设备,2010,30(3):15-19.
• [8]张周锁,李凌均,何正嘉.基于支持向量机的机械故障诊断方法研究[J].西安交通大学学报,2002,36(12):1303-1306.