摘要
基于经验模态分解(EMD)和遗传算法优化的神经网络,研究了一种风力发电机组齿轮箱的故障诊断方法。使用EMD将齿轮箱振动信号序列分解成一系列内蕴模式函数分量(IMF);然后提取各分量的特征参数,对特征参数采用主成分分析法进行降维处理;使用降维后的特征参数集训练神经网络,建立故障诊断模型;在训练过程中,采用了遗传算法优化神经网络的权值和阈值。仿真实验表明,该模型能有效提取振动信号的主要特征,完成对风力发电机组齿轮箱故障的诊断,效果良好。
An EMD-GANN fault diagnosis model of wind turbine gearbox is proposed based on empirical mode decomposition(EMD)and genetic algorithm neural network(GANN).EMD is used to decompose the vibration signal sequence into a series of intrinsic mode functions(IMF).Feature parameters of each component are extracted.The dimension of the feature parameters set is reduced with principal component analysis.A training neural network for the feature parameters set is used to establish a fault diagnosis model.In the training process,genetic algorithm is used to optimize weights and thresholds of the BP neural network.Experimental results show that the above mentioned model can effectively extract main features of the vibration signal and identify faults of the gearbox.The model is effective.
出处
《上海电机学院学报》
2016年第2期99-104,共6页
Journal of Shanghai Dianji University
基金
国家自然科学基金资助项目(61374136)
上海市自然科学基金项目资助(12ZR1411800)
上海市教育委员会创新项目资助(12YZ186
14YZ157
13YZ139)
闵行科委区校合作项目资助(2014MH157)
关键词
齿轮箱
经验模态分解
遗传算法
神经网络
故障诊断
gearbox
empirical mode decomposition(EMD)
genetic algorithm
neural network
fault diagnosis
