Abstract：Particle swarm optimization algorithm (PSO) is easy to fall into local extremum and premature convergence. To make up the defect of PSO，put forward a new kind of PSO which based on survival of the fittest and step by step selection(referred to as SSPSO). Then use SSPSO to optimize smoothness value of generalized regression neural network(GRNN). It makes full use the dvantages of optimization ability of SSPSO and fewer parameters of GRNN. Then set up vibration response prediction model which based on research data of crest overflow hydropower station. Predicted results show that search capability of SSPSO has been greatly improved compared with PSO. At the same time，prediction accuracy、convergence performance and generalization ability of SSPSO-GRNN is better than others. Puts forward a new method for vibration response prediction of hydropower stations，and provides guarantee for enhancing intelligent monitoring.
2015, Vol. 34 
