A Hybrid Particle Swarm Algorithm for the Structure and Parameters Optimization of Feed-Forward Neural Network

Abstract

A novel and efficient method combining chaos particle swarm optimization (CPSO) and discrete particle swarm optimization (DPSO) is proposed to optimize the topology and connection weights of multilayer feed-forward artificial neural network (ANN) simultaneously. In the proposed algorithm, the topology of neural network is optimized by DPSO and connection weights are trained by CPSO to search the; global optimal ANN structure and connectivity. The proposed algorithm is successfully applied to fault diagnosis, able to eliminate some bad effects on the diagnosis capacity of network introduced by redundant structure of ANN. Compared with genetic algorithm (GA), the proposed method shows its superiority on convergence property and efficiency in training ANN. It is validated by the good diagnosis results of experiments.