Cultural Particle Swarm Optimization Neural Network and Its Application in Soft-Sensing Modeling

Combining particle swarm optimization algorithm (PSO) with cultural algorithm (CA), a new cultural particle swarm optimization algorithm (CPSO) is proposed by this paper. Then, Both CPSO and PSO are used to resolve the optimization problems of five widely used test functions, and the results show that CPSO has better optimization performance than PSO. Next, CPSO is applied to train artificial neural network (NN) to construct a neural network based on cultural particle swarm optimization algorithm (CPSONN). Finally, CPSONN is applied in soft-sensing modeling of acrylonitrile yield and simulation results show that the method proposed by this paper is feasible and effective in soft-sensing modeling of acrylonitrile yield.