ПРОГНОЗ ОСАДОК ПРИ СТРОИТЕЛЬСТВЕ МЕТРОПОЛИТЕНА С ИСПОЛЬЗОВАНИЕМ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА Study on the Prediction of Subway Construction Settlement Based on Machine Learning

Xingzhong Nong, Yanmei Ruan, Junsheng Chen, Yuefeng Wu, Yuehua Liang, Wentian Xu

Аннотация


Для прогнозирования осадок поверхности при строительстве метро в различных строительных и геологических условиях используются три модели машинного обучения (нейронная сеть обратного распространения, метод опорных векторов и дерево экстремального повышения градиента (XGB)). Для создания опорного набора данных для обучения геологические условия, строительные параметры, методы прокладки щитовых тоннелей и возведения перекрытий при строительстве метро, особенности застройки на поверхности извлекаются из имеющихся отчетов о строительстве (геологические изыскания, результаты мониторинга, отчеты о щитовых проходках тоннелей) в районе Большого залива (КНР). 
Гиперпараметры моделей определены с помощью Байесовской оптимизации (BO). Вклад признаков в результаты прогнозирования машинного обучения определен количественно с использованием аддитивного объяснения Шепли (SHAP), и оценена эффективность набора тестов при различном количестве признаков. BO-XGB была признана оптимальной моделью машинного обучения для прогнозирования осадок грунта, вызванного строительством метро.


Полный текст статьи публикуется в английской версии журнала
«Soil Mechanics and Foundation Engineering”, vol.62, No.5


Литература


Akbarzadeh Arpachaei, M., Jalali, S.-M. E., and Khademian, A., "Determining the best depth of subway tunnel excavation considering ground type, support system characteristics, and tunneling cost: case study of Tabriz subway, Line 2", Bulletin Of Engineering Geology And The Environment, 82 (11): 423 (2023).

Peck, R. B., "Deep Excavations and Tunneling in Soft Ground", Proc. Of 7th ICSMFE, Mexico, 1969, (1969).

Attewell, P. B., Yeates, J., and Selby, A. R., "Soil Movements Induced by Tunnelling and their Effects on Pipelines and Structures", Methuen Inc New York Ny, (1986).

Anno, "Discussion. Subsurface settlement profiles above tunnels in clays. (R.J. MAIR, R.N. TAYLOR, A. BRACEGIRDLE (1993). Géotechnique 43, No. 2, 315-320).", (1995).

Mindlin, R. D., "Force at a Point in the Interior of a Semi-Infinite Solid", J.Appl.Phyas, .

Sagaseta, C., "Analysis of undrained soil deformation due to ground loss", Géotechnique, 37 (3): 301–320 (1987).

Verruijt, A. and Booker, J. R., "Surface settlements due to deformation of a tunnel in an elastic half plane", Géotechnique, 46 (5): 753–756 (1998).

"Stress Paths around a 3-D Numerically Simulated NATM Tunnel in Stiff Clay-All Databases", https://webofscience.clarivate.cn/wos/alldb/full-record/WOS:000086826400069 (2024).

Lee, C. J., Bing-Ru, W. U., and Chiou, S. Y., "Soil Movements Around a Tunnel in Soft Soils", Proceedings Of The National Science Council, Republic Of China, Part A. Physical Science And Engineering, 23 (2): (1999).

Ahmed, M. and Iskander, M., "Analysis of Tunneling-Induced Ground Movements Using Transparent Soil Models", Journal Of Geotechnical And Geoenvironmental Engineering, 137 (5): 525–535 (2011).

Suwansawat, S. and Einstein, H. H., "Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling", Tunnelling And Underground Space Technology Incorporating Trenchless Technology Research, 21 (2): 133–150 (2006).

Pourtaghi, A. and Lotfollahi-Yaghin, M. A., "Wavenet ability assessment in comparison to ANN for predicting the maximum surface settlement caused by tunneling", Tunnelling And Underground Space Technology Incorporating Trenchless Technology Research, 28: 257–271 (2012).

AbouRizk, Simaan, M., Xianguo, Zhang, Limao, and Wenying, "Intelligent Approach to Estimation of Tunnel-Induced Ground Settlement Using Wavelet Packet and Support Vector Machines", Journal Of Computing In Civil Engineering, 31 (2): 4016053.1 (2017).

Zhang, W.-S., Yuan, Y., Long, M., Yao, R.-H., Jia, L., and Liu, M., "Prediction of surface settlement around subway foundation pits based on spatiotemporal characteristics and deep learning models", Computers And Geotechnics, 168: 106149 (2024).

Rumelhart, D. E., Hinton, G. E., and Williams, R. J., "Learning representations by back-propagating errors", Nature, 323 (6088): 533–536 (1986).

Cortes, C. and Vapnik, V. N., "Support Vector Networks", Machine Learning, 20 (3): 273–297 (1995).

Chen, T. and Guestrin, C., "XGBoost: A Scalable Tree Boosting System", New York, NY, USA, (2016).

Djordjević, B., Mane, A. S., and Krmac, E., "Analysis of dependency and importance of key indicators for railway sustainability monitoring: A new integrated approach with DEA and Pearson correlation", Research In Transportation Business & Management, 41: 100650 (2021).

Lundberg, S. M. and Lee, S.-I., "A unified approach to interpreting model predictions", Red Hook, NY, USA, (2017).

Padarian, J., McBratney, A. B., and Minasny, B., "Game theory interpretation of digital soil mapping convolutional neural networks", SOIL, 6 (2): 389–397 (2020).

Kannangara, K. K. P. M., Zhou, W., Ding, Z., and Hong, Z., "Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method", Journal Of Rock Mechanics And Geotechnical Engineering, 14 (4): 1052–1063 (2022).

Jones, D. R., Schonlau, M., and Welch, W. J., "Efficient Global Optimization of Expensive Black-Box Functions", Journal Of Global Optimization, 13 (4): 455–492 (1998).

Frazier, P. I., "A Tutorial on Bayesian Optimization", (2018).


Ссылки

  • На текущий момент ссылки отсутствуют.