基于BAS-BP大坝变形预测模型研究  

The Deformation Prediction Model to Dam Body Based on BAS-BP

作　　者：刘江川[1,2] 李燕 陈旭尧 LIU Jiang-chuan(School of Water Resources&Environmental Engineering,Changchun Institute of Technology,Changchun 130012,China)

机构地区：[1]长春工程学院水利与环境工程学院,长春130012 [2]吉林省水利电力工程物理级仿真与安全创新中心,长春130012

出　　处：《长春工程学院学报（自然科学版）》2020年第3期78-81,共4页Journal of Changchun Institute of Technology：Natural Sciences Edition

基　　金：吉林省教育厅科学技术研究项目(吉教科合字[2015]第301号)。

摘　　要：提高大坝变形预测的精度是大坝安全监测的重要内容之一。将BAS算法应用到BP神经网络模型中,通过对BP神经网络模型的权值和阈值进行优化,训练BP神经网络预测模型求得最优解,构建了一种基于改进BAS算法的优化BP神经网络的大坝变形预测模型。将该模型运用到坝体的变形预测中,预测结果表明,改进的BAS-BP的模型相较于BP神经模型有效地避免了陷入局部最优问题,并且具有更高的预测精度。Improving the accuracy of dam prediction deformation is one of the important contents of dam safety monitoring.The BAS algorithm is applied to the BP neural network model in this paper.By optimizing the weight and threshold of the BP neural network model,the BP neural network prediction model is trained to obtain the optimal solution,and a dam deformation prediction model based on improved BAS algorithm for BP neural network is constructed.This model is applied to the deformation prediction to the dam.The prediction results show that the improved BAS-BP model effectively avoids the local optimization problem and has higher prediction accuracy than the BP neural model.

关 键 词：大坝变形预测 BP神经网络 BAS算法 

分 类 号：TV698.1[水利工程—水利水电工程]