Research On High-Speed Railway Subgrade Settlement Prediction System Based On GEP

As the basic structure of ballast less track,subgrade is the most important link in the course of railway track laying,and make a scientific prediction.At present,there are strict requirements on the data,the error of human factors is too large and the prediction accuracy is not high in the commonly used methods of theoretical calculation and measured data analysis.In view of the shortcomings of the commonly used settlement prediction methods,this paper puts forward the application of cloud adaptive GEP algorithm in the prediction of subgrade settlement.It is of great significance to promote the development of high speed railway subgrade settlement prediction.In this paper,the basic theory of subgrade settlement is studied,and several common prediction models are analyzed and discussed,such as regression analysis model,time series model,gray model and BP neural network model.On this basis,an evolutionary algorithm,gene expression programming(GEP),is introduced.On this basis,an evolutionary algorithm of gene expression programming(GEP)is introduced,and its algorithm flow and implementation method are analyzed in detail.It is found that the mutation rate,the crossover rate and the numerical constant have great influence on the performance of the GEP algorithm.However,the traditional methods still use the fixed crossover rate and mutation rate,and the method of dealing with the numerical constant is complex,which leads to the existence of local convergence,and the result is not accurate.In this paper,we propose an improved algorithm which combines cloud model with GEP,which is called GEP(CAGEP).The algorithm uses adaptive constant creation strategies,cloud crossover and mutation strategy and the population effective crossover strategy of the traditional GEP algorithm using adaptive cloud respectively,dynamic adjustment variation and crossover probability,so GEP algorithm can avoid local optimization,improve the convergence speed and accuracy,so as to optimize the performance of the search algorithm.And the effectiveness of the GEP algorithm is verified by comparing the results of the experiments.The GEP algorithm is applied to the prediction model of railway subgrade settlement and deformation,and the programming language is used to develop the model of subgrade settlement prediction based on cloud adaptive GEP,and using cloud traditional GEP algorithm,adaptive GEP algorithm,BP neural network and gray algorithm respectively on the subgrade settlement deformation prediction sample data and comparative analysis.The experimental results show that the cloud adaptive GEP algorithm has the highest prediction accuracy,and is more suitable for the prediction of subgrade settlement.