The application of intelligence information management system in predicting mining subsidence
Surface subsidence in mining is influenced by lots of factors,such as geological condition and mining condition.These factors have hardly been described by a numerical model because of their non-linear characters.In view of the characters of mining subsidence,a new method for training the artificial neural network is presented.In this method,the genetic algorithm(GA),a general-purpose global search algorithm is used to train the network with updating the weights to minimize the errors between the network output and the desired output.The measure may speed up the convergence and improve the performance.Comparing the forecast results with the Grey theory forecasting or BP algorithm,it is concluded that the improved BP neural network model has a better predicting result.As an example,the means is used to predict results in mined-out.A neural network prediction model was established.Results show that the neural network prediction model has high convergent speed and good prediction precision,so the model offers a useful approach for surface subsidence prediction in mined-out.
Artificial neural network Back propagation algorithm Genetic algorithm Mining subsidence Prediction of the mining subsidence
Zheng Yan Ma Fenghai Yang Fan
School of Geomatics,Liaoning Technical University,Fuxin 123000,China Rock-Soil and Structure Control Engineering Research Center,DaLian University,Dalian 116622,China School ofGeomatics,Liaoning Technical University,Fuxin 123000 China;Institute of Land Reclamation &
国际会议
The 2007 International Conference on Mine Hazards Prevention and Control(2007矿山灾害预防与控制国际学术会议)
青岛
英文
593-597
2007-10-17（万方平台首次上网日期，不代表论文的发表时间）