摘要
提出了一种基于GA-PSO混合优化BP神经网络的大坝变形监测模型,将遗传算法(GA)和粒子群算法(PSO)的寻优过程进行融合,利用GA算法的全局性和PSO算法收敛速度快的特点,通过迭代选取最优的粒子作为BP神经网络的连接权值和阈值,以减小网络输出误差,提高其收敛速度和加强网络泛化能力。运用GA-PSO-BP模型对大坝自动监测数据进行预测分析,实验结果表明GA-PSO-BP模型优化了BP神经网络的连接权值和阈值,能有效提高网络训练精度与收敛速度,有效避免早熟收敛,使模型的整体预测效果得到提高。
A kind of monitoring model for dam deformation based on GA-PSO to optimize BP neural network to merge the optimization of genetic algorithm(GA)and particle swarm optimization(PSO)algorithm is put forward,by decreasing the deviation in network output and improving the speed of convergence.The optimal particle is selected iteratively as the connection weight and threshold of BP neural network.The experimental result shows that GA-PSO-BP model can improve the precision in network training and avoid premature convergence effectively,with more excellent forecast value.It can provide a kind of prediction model with excellent performance and high precision for the monitoring of dam deformation.
作者
卢献健
罗乐
胡应剑
周斌
王雷
LU Xian-jian;LUO Le;HU Ying-jian;ZHOU Bin;WANG Lei(College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541006,China;Guangxi Key Laboratory of Spatial Information and Geomatics,Guilin University of Technology,Guilin 541006,China;Guangxi Institute of Geographic Information Surveying and Mapping,Liuzhou 545006,China)
出处
《桂林理工大学学报》
CAS
北大核心
2020年第2期384-389,共6页
Journal of Guilin University of Technology
基金
国家自然科学基金项目(41461089)。
作者简介
卢献健(1982-),男,硕士,副教授,研究方向:建筑变形监测数据处理与应用,2008056@glut.edu.cn。
