DISPLACEMENT CORRECTION AND DEFORMATION FORECAST OF FOUNDATION PIT WITH FEEDFORWARD NEURAL NETWORK
基于前馈神经网络的基坑测斜位移校正与变形预测研究

Due to the great depth,good continuity and high reliability of monitoring,bore inclinometer becomes a main monitoring measure for the deformation of foundation pit walls. In the process of field measurement with inclinometer,blocking often occurs in the bottom of inclinometer. Measured displacements can be corrected with data from some reliable points,and the displacements of blocked section may be deduced through feedforward neural network. Furthermore,the local displacements may be corrected,and the deformation trend of foundation pit walls can be forecasted with feedforward neural network.