当前位置: X-MOL 学术Tunn. Undergr. Space Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A critical evaluation of machine learning and deep learning in shield-ground interaction prediction
Tunnelling and Underground Space Technology ( IF 6.7 ) Pub Date : 2020-12-01 , DOI: 10.1016/j.tust.2020.103593
Pin Zhang , Huai-Na Wu , Ren-Peng Chen , Tian Dai , Fan-Yan Meng , Hong-Bo Wang

Abstract The interaction between a shield machine and the ground is a complicated problem involving numerous extrinsic and intrinsic factors. Machine learning (ML) algorithms have been recently employed to predict tunnel-soil interactions. This study introduces a more powerful algorithm termed the deep learning (DL) long short-term memory (LSTM) neural network, to identify the interaction between a shield machine and the ground; this network can predict tunnelling-induced maximum settlement, the longitudinal settlement curve, and shield operational parameters. In addition, the generalisation ability of LSTM is comprehensively compared with that of a conventional ML algorithm—random forest (RF)—based on field records collected from two practical tunnel projects. A standard process of developing an ML or DL algorithm-based model, including the pre-processing of raw data, feature selection, determination of optimum hyper-parameters, and evaluation of prediction performance and generalization ability, was introduced. The results indicated that the RF-based model performs capably in terms of predicting tunnelling-induced maximum settlement, and that the LSTM-based model is suitable for predicting longitudinal settlement curves and shield operational parameters. Furthermore, the generalization ability of the LSTM-based model is better than that of the RF-based model. The strong robustness of the LSTM-based model enables its application in different types of tunnel projects.

中文翻译:

机器学习和深度学习在盾地相互作用预测中的批判性评估

摘要 盾构机与地面的相互作用是一个复杂的问题,涉及众多外在和内在因素。最近使用机器学习 (ML) 算法来预测隧道-土壤相互作用。本研究引入了一种更强大的算法,称为深度学习 (DL) 长短期记忆 (LSTM) 神经网络,以识别盾构机与地面之间的相互作用;该网络可以预测隧道开挖引起的最大沉降、纵向沉降曲线和盾构操作参数。此外,基于从两个实际隧道项目中收集的现场记录,将 LSTM 的泛化能力与常规 ML 算法——随机森林 (RF) 的泛化能力进行了综合比较。开发基于 ML 或 DL 算法的模型的标准过程,介绍了原始数据的预处理、特征选择、最优超参数的确定以及预测性能和泛化能力的评估。结果表明,基于 RF 的模型在预测隧道引起的最大沉降方面表现出色,基于 LSTM 的模型适用于预测纵向沉降曲线和盾构操作参数。此外,基于 LSTM 的模型的泛化能力优于基于 RF 的模型。基于 LSTM 的模型的强大鲁棒性使其能够应用于不同类型的隧道项目。结果表明,基于 RF 的模型在预测隧道引起的最大沉降方面表现出色,基于 LSTM 的模型适用于预测纵向沉降曲线和盾构操作参数。此外,基于 LSTM 的模型的泛化能力优于基于 RF 的模型。基于 LSTM 的模型的强大鲁棒性使其能够应用于不同类型的隧道项目。结果表明,基于 RF 的模型在预测隧道引起的最大沉降方面表现出色,基于 LSTM 的模型适用于预测纵向沉降曲线和盾构操作参数。此外,基于 LSTM 的模型的泛化能力优于基于 RF 的模型。基于 LSTM 的模型的强大鲁棒性使其能够应用于不同类型的隧道项目。
更新日期:2020-12-01
down
wechat
bug