长江科学院院报 ›› 2013, Vol. 30 ›› Issue (1): 99-101.DOI: 10.3969/j.issn.1001-5485.2013.01.020

• 安全监测预警专栏 • 上一篇    

Matlab仿真平台下大坝位移BP神经网络模型研究

朱凤林,韩卫    

  1. 辽宁省白石水库管理局,辽宁 朝阳 122000
  • 收稿日期:2012-11-20 出版日期:2013-01-01 发布日期:2013-01-16
  • 通讯作者: 韩 卫(1971-),男,河北保定人,高级工程师,主要从事水库大坝安全监测管理、数值分析等工作
  • 作者简介:朱凤林(1975-),男,辽宁凌源人,工程师,主要从事水利水电工程施工管理工作

BP Neural Network Model to Monitor Dam Deformation in Matlab Simulation Platform

ZHU Feng-lin, HAN Wei   

  1. Baishi Reservoir Management Bureau of Liaoning Province, Chaoyang 122000, China
  • Received:2012-11-20 Online:2013-01-01 Published:2013-01-16

摘要:

基于人工神经网络的非线性映射能力,应用Matlab7.1网络仿真平台,结合辽宁省白石水库多年大坝位移实测数据,建立了3种不同改进BP算法的多层前馈神经网络模型。并通过LM算法、BR算法、GDX算法的BP网络模型的拟合、预报结果,对3种模型的应用效果进行了比较分析,得出了LM算法的BP网络更适合用于建立坝顶位移监控模型的结论,以实现对大坝位移实时、有效的监控。

关键词: Matlab, 大坝位移, BP神经网络, 改进优化, 预报

Abstract:

On the basis of the nonlinear reflection ability of artificial neural network, we established three multi-layer feed-forward neural network models in Matlab 7.1 simulation platform to monitor the Baishi reservoir deformation in Liaoning Province. The three models adopt different modified BP algorithms, i.e. LM algorithm, BR algorithm, and GDX algorithm. According to the fitting and prediction results, we compared the application results of the three models and concluded  that the BP network based on LM algorithm was more suitable for building dam's displacement monitoring model to realize real-time and effective monitoring.

Key words: Matlab, dam displacement, BP neural network, modified algorithm, prediction      ,

中图分类号: