Abstract:We propose an ADPPSO-BP neural network for adaptive particle swarm optimization, and an adaptive mutation operator is added into the algorithm, improving the ability of particles to jump out of local search, realizing the accurate prediction of the dam’s displacement. PSO-BP, LPSO-BP (BP neural network with line particle swarm optimization) and ADPPSO-BP algorithms are modeled to predict dam deformation. The results show that ADPPSO-BP has the highest precision and the ADPPSO-BP model is most suitable for the deformation prediction of dams.
LIU Zhongbao. Prediction of Dam Deformation Based on the Improved BP Neural Network with Adaptive Particle Swarm Optimization[J]. jgg, 2019, 39(5): 528-532.