欢迎访问《金属矿山》杂志官方网站,今天是 分享到:
×

扫码分享

金属矿山 ›› 2013, Vol. 42 ›› Issue (03): 9-13.

• 采矿工程 • 上一篇    下一篇

基于GA-BPNN的巷道围岩变形模量预测

王德永1,2,袁艳斌1,陈颖1   

  1. 1.武汉理工大学资源与环境工程学院;2.平顶山工业职业技术学院计算机系
  • 出版日期:2013-03-15 发布日期:2013-04-16
  • 基金资助:

    * 国家高技术研究发展计划(863计划)项目(编号:2009AA12201),平顶山市科技创新人才计划项目(编号:2012061)。

Prediction of Surrounding Rock Deformation Modulus of Roadway Base on GA-BPNN

Wang Deyong1,2,Yuan Yanbin1,Chen Ying1   

  1. 1.School of Resources and Environmental Engineering,Wuhan University of Technology;2.Department of Computing,Pingdingshan Industrial College of Technology
  • Online:2013-03-15 Published:2013-04-16

摘要: 研究了遗传算法(GA)在设计和优化BPNN结构时的效能和它在预测岩体变形模量的应用,利用GA找到隐藏层神经元的最优数量以及隐含与输出层的学习因子和动量因子,然后和试错过程进行比较。采用了来源于实际巷道测量的76组数据集验证该方法。利用MSE,MAE,R等性能标准,证明GA-BPNN模型在岩体变形模量预测方面优于BPNN试错模型。

关键词: 巷道围岩, 变形模量, 预测, GA-BPNN

Abstract: The effectiveness of the genetic algorithm (GA) in the design and BPNN structure optimization and its application in the prediction of rock mass deformation modulus was researched. GA is used to find out the optimal number of neurons in the hidden layer and learning factor and momentum factor of the hidden layer and output layer,and then compared with the trial-and-error process. 76 groups of data sets derived from the actual roadway were used to validate this method. With performance criteria such as MSE,MAE and R,it is proved that GA-BPNN model is better than BPNN trial-and-error model in the prediction of rock mass deformation modulus.

Key words: Surrounding rock, Deformation modulus, Prediction, GA-BPNN