考虑车流量的BP神经网络模型预测吹填土地区路基工后沉降

Prediction of post-construction settlement of subgrade in dredger fill area by BP neural network model considering traffic flow

根据吹填土路基工后沉降原理,选取曹妃甸北环路吹填土路基某一断面的车流量和时间作为影响因素,建立了考虑车流量的BP神经网络模型,并将之用于吹填土路基的工后沉降预测。与泊松曲线模型和双曲线模型的预测结果对比后发现,BP神经网络模型预测精度更高,误差在4%以内,从而验证了考虑车流量的BP神经网络模型在解决该类问题上的简便性和适用性。

Based on the principles of post-construction settlement of subgrade in dredger fill area,the traffic flow and time of a section of the dredger fill subgrade in the North Ring Road of Caofeidian were selected as the influencing factors,and the BP neural network model considering traffic flow was established and used for the post-construction settlement prediction of the dredger fill subgrade.After comparing with the prediction results of Poisson curve model and hyperbolic model,it is found that the BP neural network model has higher prediction accuracy and the error is less than 4%,which verifies the applicability and simplicity of BP neural network model considering traffic flow in solving such problems.