Font Size: a A A

Prediction Of Mining Subsidence Parameters Based On BP Neural Network

Posted on:2018-05-24Degree:MasterType:Thesis
Country:ChinaCandidate:K KangFull Text:PDF
GTID:2321330533962800Subject:Surveying and mapping engineering
Abstract/Summary:PDF Full Text Request
The exploitation of coal resources results in the surface movement and deformation,which may cause surface subsidence,cracks and other disasters.It has seriously affected the safe production of the mining area and the normal life of the surrounding residents,and caused a great threat to the development of the regional economy.Therefore,the mining subsidence prediction model has important guiding significance for the determination of the scope and shape of the surface subsidence areaIn this paper,based on the measured data of Anyang mining area,the collected data of the mining areas in China are taken as the basic data,to measured data are analyzed and the results are obtained,and the subsidence of Anyang mining area is predicted,The main contents of this paper are as follows:(1)Based on the prediction of mining subsidence,In this paper,the probability integral method is selected.Firstly,the relationship between the expected parameters of probability integral method and geological mining conditions is introduced.Lay the foundation for the paper.As the mining area is expected to use the most extensive is the probability of integration method.So the expected accuracy of the parameters of the probability integral method determines the accuracy of the surface subsidence.(2)To reduce the experimental data on the network error.Use Origin 8.0 to smooth the raw data.At the same time,the influence of different selection methods on the expected results was analyzed.(3)The BP neural network model is introduced,and use its parameters to predict.Then the genetic algorithm is used to optimize the BP neural network.Then the genetic algorithm is used to optimize the BP neural network.The resulting network predicts the parameters and analyzes their accuracy.The accuracy of the two forecasting results is compared and the cause of the error is analyzed.(4)According to the measured data of Anyang mining area.By using genetic algorithm to optimize BP neural network,the parameters of probability integral method in Anyang mining area are predicted.Then the actual parameters of Anyang mining area are analyzed and compared.
Keywords/Search Tags:Mining subsidence, probability integral method, BP neural network, genetic algorithm
PDF Full Text Request
Related items