通过改进自适应PSO优化BP网络预测大坝变形  

Prediction of Dam Deformation Based on the Improved BP Neural Network with Adaptive Particle Swarm Optimization

作　　者：刘忠豹 LIU Zhongbao(College of Geomatics,Shandong University of Science and Technology,579 Qianwangang Road,Qingdao266590,China)

机构地区：[1]山东科技大学测绘科学与工程学院,青岛市前湾港路579号266590

出　　处：《大地测量与地球动力学》2019年第5期528-532,共5页Journal of Geodesy and Geodynamics

摘　　要：提出自适应粒子群神经网络(ADPPSO-BP)算法,并加入自适应变异算子,提高粒子跳出局部搜索的能力,实现对坝体位移的精准预测。以丰满大坝为例进行验证,建立PSO-BP(粒子群神经网络)、LPSO-BP(线性粒子群神经网络)、改进ADPPSO-BP(改进自适应粒子群神经网络)3种模型,对大坝进行变形预测。结果表明,ADPPSO-BP预测误差最小。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.

关 键 词：水平位移 预测精度 PSO-BP LPSO-BP ADPPSO-BP 

分 类 号：P258[天文地球—测绘科学与技术]