基于风电故障机组筛选的齿轮箱故障诊断研究  

Gearbox Fault Diagnosis Based on Wind Turbine Fault Unit Selection

作　　者：石慧 赵巧娥 SHI hui;ZHAO Qiao-e(Taiyuan City Kangpei Garden Greenery Engineering Limited Company,Taiyuan 030025,China;Department of Electric Power Engineering,Shanxi University,Taiyuan 030006,China)

机构地区：[1]太原市康培园林绿化工程有限公司,山西太原030025 [2]山西大学电力工程系,山西太原030006

出　　处：《电工电气》2019年第9期7-11,共5页Electrotechnics Electric

摘　　要：利用改进粒子群优化模糊C均值聚类算法对双馈风力发电机组群进行故障机组分类,并提出基于改进粒子群优化的模糊核聚类算法对双馈风力发电机组齿轮箱的已知以及未知故障进行诊断分类。通过分析实际风电场采集得来的齿轮箱振动数据,验证所提方法不仅可以准确快速地判断出故障机组,而且还可以进一步对发生的已知故障以及未知故障进行一个很好的诊断。This paper used the improved particle swarm optimization fuzzy C means clustering algorithm to classify the fault units of doubly fed wind turbines,and presented a fuzzy kernel clustering algorithm based on the improved particle swarm optimization(PSO)for the diagnosis and classification of the known and unknown faults of the gear box of the doubly fed wind turbine.By analyzing the vibration data of the gear box collected by the actual wind farm,it is proved that the proposed method can not only judge the fault unit accurately and quickly,but also further diagnose the known fault and the unknown fault.

关 键 词：双馈风力发电机组 模糊C均值聚类算法 模糊核聚类算法 改进粒子群优化算法 故障诊断 

分 类 号：TM614[电气工程—电力系统及自动化]