Application of Improved RBF Network to Analog Circuit Fault Isolation
Xiao Mingqing · Ceshi jishu xuebao · 2010
One kind of steepest descent incremental projection learning algorithm for improving the training of radial basis function(RBF) neural network was proposed here,and was applied to analog circuit fault isolation.The algorithm simplified the structure of network for optimum output layer coefficient with incremental projection learning(IPL) algorithm,and adjusted the operator A of IPL algorithm for optimum center and standard deviation of optimum RBF function.Compared to the traditional algorithm,the improved algorithm has quicker convergence rate and higher precision.Simulation results show that this improved RBF network has much better performance,which can be used in analog circuit fault isolation field.