Stability classification of mine roadways surrounding rock using genetic algorithm neural network
In order to obtain reasonable layout and support parameter, a mine roadways stability classifi-cation model based on BP neural network was established. After trainings using a large number of measured samples, a mathematic relationship between stability category and factors affecting it was established. Genetic algorithms were used to optimize the initial weights of BP neural network which can select the initial weights work effectively, and improved the generalization performance of BP neural network, to avoid training from falling into local minimum. Test results show that mine roadway surrounding rock stability can be classified correctly and validly. Through this model factors affecting the stability of surrounding rock can be considered comprehensively and a high-dimensional nonlinear mathematical model which matches the reality can be estab-lished with accurate and reliable results, it can meet the requirements of coal mine roadway support. The research provides a scientific basis for roadways selection of support parameters.
P.X. Li Z.X. Tan L.L. Yan K.Z. Deng
China University of Mining and Technology, Key Laboratory for Land Environment and Disaster Monitoring of SBSM, Xuzhou, China China University of Mining and Technology, Jiangsu Key Laboratory of Resources and Environmental Information Engineering, Xuzhou, China
国际会议
The 2nd ISRM International Young ScholarsSymposium on Rock Mechanics(第二届国际岩石力学青年学者研讨会)
北京
英文
499-504
2011-10-14（万方平台首次上网日期，不代表论文的发表时间）