针对单一模型在隧道变形预测上精度不高的问题,提出了一种基于小波分析理论的神经网络模型,该模型克服了BP神经网络模型存在的收敛速度慢、结构设计盲目、易陷入局部极小点的缺陷,通过将该模型与时间序列模型、Levenberg-Marquardt法BP神经网络模型、遗传神经网络模型预测的结果比较,可以看出小波神经网络在隧道的变形预测中网络结构更简单、收敛速度更快、预测精度更高。
Based on the fact that single model's prediction precision in tunnel deformation monitoring is not very high, this paper proposes a Neural Network model based on Wavelet analysis theory, which can overcome slow convergence speed, blindness of structure design and local minimum of BP Neural network. Compared with time series model, Levenberg-Marquardt BP Neural Network model, and GA-BP Neural Network model, prediction results show thatWavelet Neural Network model has a simple network structure, faster convergence speed and higher prediction precision in tunnel deformation monitoring.