摘要
对于模拟电路故障诊断问题,传统的故障诊断方法计算复杂,存在明显缺陷。运用小波包变换(WPT)提取故障特征信号,建立故障识别的神经网络模型,采取果蝇-粒子群算法优化RBF神经网络的结构参数,提出一种基于小波包变换和RBF神经网络的模拟电路故障识别方法。仿真结果表明,该方法具有识别速度快、准确性高等优点。
An analog circuit fault identification method based on wavelet packet transform and RBF neural network is proposed in view of the characteristics of analog circuit fault.Wavelet packet transform(WAT)is applied to extract fault feature signals,and a neural network model for fault identification is established.Fruit fly particle swarm optimization algorithm is adopted to optimize the structural parameters of RBF neural network.The simulation results show that the method has the advantages of fast recognition speed and high accuracy.
作者
乔维德
QIAO Weide(Scientific Research and Quality Control Department,Wuxi Open University,Wuxi,214011,China)
出处
《温州职业技术学院学报》
2018年第1期47-51,共5页
Journal of Wenzhou Polytechnic
基金
无锡市社会事业领军人才资助项目(WX530/2017037)
