摘要
RBF神经网络在故障诊断中广泛应用,但其依赖于隐含层数据中心的选取是否合适,故引入模糊—C均值聚类(Fuzzy C-means Clustering Algorithm,FCM)算法对其进行优化。其网络结构参数中网络宽度以及隐含层到输出层的权值都是影响RBF网络性能的关键,运用改进粒子优化算法(Particle Swarm Optimization,PSO)对网络参数中宽度和权值进行优化。
RBF neural network has been widely used in fault diagnosis. It depends too much on whether the selection of the hidden layer data center is appropriate, so the Fuzzy C-means Clustering Algorithm(FCM) was introduced to optimize it. And the network width and the weight from the hidden layer to the output layer in the network structure parameters were the keys to the performance of the RBF network. The improved particle swarm optimization(PSO)algorithm was used to optimize the width and weight of network parameters.
作者
刘斌
吴伟
卫涵典
洪诗益
Liu Bin;Wu Wei;Wei Handian;Hong Shiyi(School of Mechanical Engineering,Xi′an Shiyou University,Shanxi 710065,China)
出处
《机电工程技术》
2021年第1期166-169,共4页
Mechanical & Electrical Engineering Technology
