基于遗传算法与BP神经网的风力发电机齿轮箱故障诊断研究  

Study on the Fault Diagnosis of Gear Box for Wind Turbine Generator System Based On Genetic Algorithm and BP Neural Network

作　　者：周培毅[1] 张新燕[1] 张华中[1] 

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830046

出　　处：《华北电力技术》2010年第7期6-11,共6页North China Electric Power

基　　金：国家自然科学基金项目编号:50767003;自治区教育厅科研资助项目编号:XJEDU2007I05

摘　　要：为研究风力发电机组齿轮箱故障的诊断方法,提高其工作的可靠性,将BP算法寻优具有精确性与遗传算法全局寻优的优点相结合,提出一种新的BP神经网训练算法。通过算法比较和实例分析表明,该算法在风力发电机组齿轮箱故障诊断领域具有良好的实用性。To study the fault diagnosis and increase the work reliability of the gear box of wind turbine, a combining algorithm for neural network training is formed by combining BP algorithm and genetic algorithm in the process of fault diagnosis of gear box. According to the characteristics of genetic algorithm and BP algorithm, we have firstly brought forward a new algorithm for fault diagnosis to combine the genetic algorithm with BP neural network. The experiment results prove that this algorithm is practical in the field of faults diagnosis by comparing the two algorithms and analyzing the results of real examples.

关 键 词：风力发电机组 齿轮箱 神经网络 BP算法 遗传算法 故障诊断 

分 类 号：TM315[电气工程—电机]