摘要
为了提高异步电动机振动故障诊断的准确性,提出了基于邻域粒子群优化神经网络的异步电动机振动故障诊断方法.首先对实验室异步电动机各类常见故障进行测试,然后选择异步电动机不同位置振动信号的特征频率作为神经网络的输入,最终利用邻域粒子群优化后的神经网络进行异步电动机振动的故障诊断.实验结果表明:与其他诊断方法相比,该方法具有较高的诊断精度.此方法适合应用在异步电动机振动故障诊断中,具有推广应用价值.
In order to improve the accuracy of the vibration fault diagnosis of induction motors,a vibration fault diagnosis method of induction motors by using neural network based on particle swarm optimization(PSO) with neighborhood operator is put forward.Firstly,the common faults of a test induction motor are measured in laboratory,and then the characteristic frequencies of the vibration signals of the motor in different positions are used as the input of neural network.Finally,the vibration fault diagnosis of the induction motor is accomplished by the neural network based on PSO with neighborhood operator.The experimental results show that this method has a higher fault diagnosis accuracy compared with other methods.
出处
《西安石油大学学报（自然科学版）》
CAS
北大核心
2010年第2期73-75,共3页
Journal of Xi’an Shiyou University（Natural Science Edition）
基金
陕西省工业攻关计划"基于DSP的水轮发电机组气隙监测与跟踪系统"(编号:2007k05-15)
关键词
异步电动机
振动
故障诊断
邻域粒子群算法
神经网络
induction motor
vibration
fault diagnosis
particle swarm optimization with neighborhood operator
neural network
