Fault Diagnosis for Embedded System Based on Neural Network

In the paper, Radial Basis Function (RBF) neural network optimized by particle swarm optimization algorithm is proposed to fault diagnosis for embedded system. The parameters of Radial Basis Function (RBF) neural network are selected by particle swarm optimization algorithm to solve the problem of the parameters selection of Radial Basis Function (RBF) neural network. In order to testify the superiority of Radial Basis Function (RBF) neural network optimized by particle swarm optimization algorithm in fault diagnosis for embedded system, traditional Radial Basis Function (RBF) neural network and Back Propagation (BP) neural network are applied to compare with the proposed Radial Basis Function (RBF) neural network optimized by particle swarm optimization algorithm. The comparison results show that the diagnosis accuracy of Radial Basis Function (RBF) neural network optimized by particle swarm optimization algorithm is the best methods among traditional Radial Basis Function (RBF) neural network, Back Propagation (BP) neural network and Radial Basis Function (RBF) neural network optimized by particle swarm optimization algorithm.