长江科学院院报 ›› 2009, Vol. 26 ›› Issue (6): 24-27.

• 岩土工程 • 上一篇    下一篇

基于VB与Matlab的BP神经网络在地应力场分析中的应用

 李永松, 艾凯, 尹健民   

  • 出版日期:2009-06-01 发布日期:2012-07-02

Application of BP Network Based on VB and Matlab in Analysis of In-situ Stress Field

 LI  Yong-Song, AI  Kai, YIN  Jian-Min   

  • Online:2009-06-01 Published:2012-07-02

摘要: 将通用程序Matlab的强大计算功能和VB开发界面友好的特点有机结合,利用ActiveX技术实现可视化神经网络模型并应用于初始地应力场的计算。根据线性回归分析的结果,应用均匀设计来确定计算参数不同水平的组合,通过有限元计算来构造神经网络的训练样本分析工程区应力场。实际工程中往往需要了解某一重要工程部位的应力状态,利用神经网络将整个工程区的初始地应力场智能化,所开发的人机交互界面使用方便。

Abstract: By making use of strong capability in computing of Matlab and features of friendly interface of VB, the visual neural network by using ActiveX technology is realized and used to analyze in-situ stress field in this paper. On the basis of the calculated results of multivariate linear regression analysis, the uniform design method is carried out to settle parameters with different combinations of factor levels. Training samples are gained by FEM analysis. The rock mass is in elastic state when the linear regression method is carried out, and with the ANN method, the training samples are difficult to generate. Combining the linear regression method with ANN method can solve these problems perfectly. Infact, one needs to know the status of the in-situ stress field at some important location in the engineering. By using neural network method, intelligent expression method of the in-situ stress field is presented in this paper. The developed man-computer interface has the property of easy use in the actual engineering.