组合模型在隧道结构沉降预测中的应用研究

Application of Combination Model in the Tunnel Structure Settlement Prediction

针对传统组合模型建模准则单一、权值固定不变的缺陷,引入稳定度相关理论,构建一种新的最优组合预测模型,并对优性组合的评判方法以及预测成果的评价准则进行了研究。该模型的核心思想是依据单一模型建模阶段和预测阶段精度的一致性来赋予权值。分别利用组合模型、时间序列模型以及神经网络模型对地铁隧道结构的沉降量进行预测,并分析比较各自的预测结果。结果表明组合模型相对于各单一模型而言,预测效果更优、精度更高,能很好地集合单一模型的有效信息,是一种有效的地铁隧道结构沉降预测模型。

Aiming at the shortcomings of the traditional combination model,such as single modeling criterion and the fixed weight,we introduced the stability related theory into construct a new optimal combination forecast model,and studied the judgment method of the superior combination model and the evaluation criterion of the prediction results.The core idea of this model is to give weights according to the consistency of the accuracy of the modeling and prediction stages of a single model.Then,we used the combination model,time series model and neural network model to predict the settlement of subway tunnel structure,and analyzed and compared the prediction results of each model.The results show that the combination model has higher prediction accuracy,and is an effective model for predicting the settlement of subway tunnel structure.