同济大学学报（自然科学版）2026，Vol.54Issue(7)：993-1004,12.DOI:10.11908/j.issn.0253-374x.25113
基于改进BiLSTM代理模型的基坑分步开挖变形计算方法
Calculation Method for Stepwise Excavation-induced Deformation in Foundation Pits Based on BiLSTM Surrogate Model
摘要
Abstract
In this paper,a BO-BiLSTM-Att surrogate model is proposed to efficiently calculate the excavation-induced deformation.The BiLSTM network is integrated with Att to capture temporal mapping relationships between input and output parameters.The Bayesian optimization(BO)is implemented to identify optimal hyperparameters,thereby further enhancing the model's computational accuracy.Through a numerical case,the applicability and efficiency of BO in hyperparameter optimization are verified by comparison with PSO and GA.Subsequently,the surrogate model is trained by BO-optimized hyperparameters and its effectiveness in staged deformation calculation is demonstrated through the difference between predicted values and true values of test sets.Finally,the computational accuracy between BiLSTM network and BiLSTM-Att under identical hyperparameters is compared.It is shown that Att can improve the model's computational accuracy.The proposed surrogate model has enhanced the computational accuracy(R2=0.967)and generalization capability(mean average error 0.875 mm)in testing scenarios.关键词
基坑变形/机器学习/注意力机制(Att)/贝叶斯优化(BO)/超参数Key words
excavation deformation/machine learning/attention mechanism(Att)/Bayesian optimization(BO)/hyperparameter分类
交通工程引用本文复制引用
金钰寅,狄宏规,何平,周顺华..基于改进BiLSTM代理模型的基坑分步开挖变形计算方法[J].同济大学学报（自然科学版）,2026,54(7):993-1004,12.基金项目
国家自然科学基金(52278456) （52278456）
