摘要
为了诊断风电齿轮箱已知类别和未知类别的故障,提出了基于模糊核聚类和引力搜索的故障诊断方法。首先建立以训练样本分类错误率为目标的聚类模型,利用模糊核聚类对训练样本进行分类;然后利用引力搜索算法求解聚类模型,获得最优分类结果下每个类的类心;最后根据新样本与各类心之间的核空间样本相似度判断属于已知故障或者未知故障。结果表明,该方法准确度高,可有效用于风电齿轮箱故障诊断。
In order to diagnose known faults and unknown faults of wind turbine gearbox, a meth- od was proposed based on kernel fuzzy c-means clustering and gravitational search. Firstly, the cluste- ring model was built based on wrong classification rate of training samples. The training samples were classified by kernel fuzzy c-means clustering. Then the gravitational search method was introduced for solving the clustering model. The class centers of optimal clustering result were acquired. Finally, the similarity parameters in kernel space between new data samples and the class centers were calculated for diagnosing whether the new data sample belonged to the known faults. The results show that the proposed method has higher precision, which can be applied to diagnose fault of wind turbine gearbox
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2015年第19期2667-2671,2676,共6页
China Mechanical Engineering
基金
国家自然科学基金资助项目(51305135)
中央高校基本科研业务费专项资金资助项目(2014XS15)
中国华能集团科技项目(HNKJ13-H20-05)
关键词
模糊核聚类
引力搜索
风电机组齿轮箱
故障诊断
kernel fuzzy c-means clustering
gravitational search
wind turbine gearbox
fault diagnosis
作者简介
李状，男，1987年生。华北电力大学能源动力与机械工程学院博士研究生。主要研究方向为旋转机械设备故障诊断。发表论文6篇。
马志勇，男，1974年生。华北电力大学能源动力与机械工程学院副教授。
胡亮，男，1988年生。华北电力大学能源动力与机械工程学院博士研究生。
柳亦兵，男，1961年生。华北电力大学能源动力与机械工程学院教授、博士研究生导师。
