Institute of Marine Science and Technology, Shandong University, Qingdao, Shandong, People's Republic of China.
School of Engineering and Technology, China University of Geosciences (Beijing), Beijing 100084, People's Republic of China.
Philos Trans A Math Phys Eng Sci. 2023 Sep 4;381(2254):20220303. doi: 10.1098/rsta.2022.0303. Epub 2023 Jul 17.
Due to improper operation of the shield construction process and unknown geological surveys, shield construction faces many risks in passing through complex strata, among which the excavation face instability is the most serious, potentially leading to disastrous accidents. To address these issues, this research focuses on the limit support pressure and the excavation face stability in the soil when crossing the Yangtze River. First, an analytical formula for the limit support pressure of the excavation face is established through the wedge model. The support safety coefficient is used to assess the excavation face stability quantitatively. Then the rough set algorithm is used to analyse the sensitivity of each index to establish the reduced evaluation index system for the excavation face stability. The back propagation (BP) neural network is used to train the learning data, and a neural network evaluation model with a prediction error of 5.7675 × 10 is established. The prediction performance of BP is verified by comparison with the TOPSIS prediction model and the cloud model. The evaluation method proposed in this paper provides an essential reference for evaluating the underwater shield tunnel excavation face stability. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.
由于盾构施工过程中的操作不当和未知的地质调查，盾构施工在穿越复杂地层时面临许多风险，其中最严重的是开挖面失稳，可能导致灾难性事故。针对这些问题，本研究聚焦于盾构穿越长江时的土中极限支护压力和开挖面稳定性。首先，通过楔形体模型建立了开挖面极限支护压力的解析公式，利用支护安全系数对开挖面稳定性进行定量评估。然后，采用粗糙集算法分析各指标对开挖面稳定性的敏感性，建立了开挖面稳定性的简化评价指标体系。利用反向传播（BP）神经网络对学习数据进行训练，建立了预测误差为 5.7675×10 的神经网络评价模型。通过与逼近理想解排序法（TOPSIS）预测模型和云模型的对比，验证了 BP 的预测性能。本文提出的评价方法为评价水下盾构隧道开挖面稳定性提供了重要参考。本文是“交通基础设施与材料失效分析中的人工智能”主题的一部分。
