Abstract:
A hybrid algorithm of DEA and PSO is proposed, in which the DEA is utilized to improve the bad subswarms of PSO. By resolving the optimization problems of several widely used test functions, it is showed that the proposed algorithm has better optimization performance than the standard PSO. Finally, the hybrid algorithm is employed to train the artificial neural network that is applied to softsensing of acrylonitrile yield. The results show that the hybrid algorithm is feasible and effective in softsensing of acrylonitrile yield.