小波神经网络模型在高铁路基沉降预测中的应用研究

为了提高变形监测数据预测的精度与可靠性,提高神经网络预测方法的稳定性,尝试将小波分析与BP神经网络相结合的小波神经网络应用于高铁路基处的沉降监测数据处理中。综合小波分析与神经网络算法的优点,建立松散型及紧致型小波神经网络预测分析模型。通过实验数据对比分析,验证了采用紧致型小波神经网络预测模型能够较好地用来处理路基的动态变形监测数据,预测稳定性及预测精度较高。

Application of Wavelet Neural Network Model in the Settlement Prediction Research of High Railway Subgrade

In order to improve the accuracy and reliability of prediction of deformation monitoring data , and improve the stability of ar-tificial neural network prediction method , we try to combine the wavelet analysis with the BP neural network to apply the wavelet neural network in the data processing of high speed railway subgrade subsidence monitoring .We integrated the advantages of wavelet analysis and neural network algorithm , and then building high speed railway subgrade deformation of Loose and compact wavelet neural network forecasting analysis model .Through the comparison of experimental data analysis , we verify that the compact type of wavelet neural network prediction model can be well used to treat roadbed dynamic deformation monitoring data , and the stability prediction and the prediction precision is higher .