[关键词]
[摘要]
采用机器学习方法,建立了一个基于先期区域地质信息及隧道沉降学习资料的盾构隧道长期沉降预测模型,并以南京地铁二号线盾构隧道为例进行算例分析。结果表明:该沉降预测模型能够筛选主要影响因素,并且能够寻找最佳监督学习算法和最优参数;不同监督学习算法中,核支持向量机算法与人工神经网络算法对于该模型都能使模型达到较高的精度,然而其对参数的依赖性很高,需要细致的调参才能提高预测精度;以人工神经网络算法作为监督学习算法,经调参后,沉降预测模型的最终预测准确度可达0.86,十倍交叉验证平均准确度为0.82。
[Key word]
[Abstract]
Based on advanced regional geological information and tunnel settlement data, a long-term settlement prediction model of shield tunnel using machine learning method was proposed. The model was demonstrated by a case study of Nanjing Metro Line 2 shield tunnel. The results show that the prediction model can analyze and obtain the main influencing factors of long-term tunnel settlement and find the best supervised learning algorithm and optimal parameters. Among the different supervised learning algorithms, both the kernel support vector machine (KSVM) algorithm and the artificial neural network (ANN) algorithm can achieve high accuracy, but require careful parameters adjustment to improve the prediction accuracy. Using the ANN algorithm as supervised learning algorithm and after parameters adjusting, the final prediction accuracy of the model can reach 0.86 and the average accuracy of tenfold cross-validation is 0.82.
[中图分类号]
U231
[基金项目]