摘要
利用遗传算法的全局寻优特性,与小波神经网络相结合,建立遗传小波神经网络模型,并将其运用于高铁沉降预测,通过与BP神经网络、小波神经网络在高铁沉降预测的实验对比分析,结果表明遗传小波神经网络在高铁沉降预测中的稳定性更好、精度更高。
This paper took advantages of the genetic algorithms to seek all the data in order to calculate the best result, and combined the genetic algorithms with wavelet neural network to set up the genetic wavelet neural network for the settlement of high-speed railway. The paper did the experimental contrast analysis which in the prediction of high-speed railway settlement by back propagation neural network and wavelet neural network. The results indicate that the genetic wavelet neural network in the prediction of high-speed railway settlement is more stable in terms of stability and more accurate in the perspective of accuracy.
出处
《地理空间信息》
2016年第10期93-94,97,共3页
Geospatial Information
基金
广西空间信息与测绘重点实验室基金资助项目(1103108-06)
关键词
沉降预测
BP神经网络
小波神经网络
遗传小波神经网络
残差
settlement prediction
BP neural network
wavelet neural network
genetic wavelet neural network
residual error
