灰色神经网络组合模型在变形监测数据分析中的应用

摘要

According to the gray and nonlinear characteristics of the data in the prediction of foundation pit deformation,a new method by combination model of grey neural network is proposed to predict the deformation of foundation pit.In this paper,the grey model and neural network model are combined to form a combined forecasting model.Integration of the advantages of the two models,and combined with examples,the prediction results by the grey model,neural network model and grey neural network combined model are compared and analyzed.The results show that the prediction results by grey neural network combined model are more precise,and it has certain reference significance for deformation monitoring of the production practice.%针对基坑变形预测中数据的灰色性和非线性的特点,提出用灰色神经网络组合模型预测基坑变形的新方法.该文将灰色模型与神经网络模型并联构成组合预测模型,融合二者的优点,并结合实例,将灰色模型、神经网络模型和灰色神经网络组合模型的预测结果进行对比分析.结果表明:灰色神经网络组合模型的预测结果更精确,对变形监测的生产实践具有一定的参考意义.