Artificial intelligence-optimized shield parameters for soft ground tunneling in urban environment: A case study of Bangkok MRT Blue Line

Abstract

This paper presents a study on multi-objective optimization (MOO) of shield operational parameters (SOPs) for soft ground tunneling using a tunnel boring machine (TBM) in an urban environment, focusing on the case study of the MRT Blue Line in Bangkok. The investigation aims to determine the optimal combination of SOPs, consisting of face pressure ($F_p$), thrust force ($T_f$), grout pressure ($G_p$), and percent grout filling ($G_f$), along with relevant environmental factors, including tunnel depth ($T_d$), inverted groundwater level ($W_i$), and type of surrounding soil ($T_s$). The primary objective is to enhance the penetration rate ($P_{avg}$), in terms of average value), as cost consideration, while mitigating ground surface settlement ($S$), as safety (serviceability) consideration. Using long short-term memory (LSTM) neural networks as predictive models, the results yield coefficient of determination (R²) values of 0.81 and 0.96, root mean square error (RMSE) values of 5.91 mm/min and 3.09 mm, and average bias factor values of 0.99 and 0.88 for the $P$ and $S$ predictive models, respectively, based on validation datasets. This integrated framework, which combines the non-dominated sorting genetic algorithm (NSGA-II) with LSTM neural networks, is applied to MOO to identify the optimal SOPs, while accounting for their influence on $S$ variation as a time-series over 11 timesteps, as considered in this study. For simplification and practical field implementation, the same set of SOP values is applied across all 11 timesteps during the optimization process. Using the proposed optimization framework, the optimal results demonstrate improvements in $P_{avg}$, increasing by up to 109.8% (from 13.99 to 29.35 mm) and in $S$, reducing up to 79.6% (from 34.55 to 7.06 mm) when MOO is conducted as a time series using the simplified method. This finding provides a valuable approach to effectively address the sequential uncertainties of relevant factors in soft ground tunneling for similar projects.

Keywords

Tunneling / Optimization / Penetration rate / Ground surface settlement / Long short-term memory / Non-dominated sorting genetic algorithm

Data availability

The dataset and code that support the findings of this study are publicly available at https://github.com/Sahatsawat-Wainiphithapong/AI-optimized-shield-tunneling-framework.

CRediT authorship contribution statement

Sahatsawat Wainiphithapong: Data curation, Visualization, Methodology, Software, Investigation, Writing - original draft, Formal analysis. Chana Phutthananon: Writing - review & editing, Visualization, Supervision, Validation, Methodology, Conceptualization, Funding acquisition. Sompote Youwai: Validation, Methodology, Formal analysis, Software. Pitthaya Jamsawang: Writing - review & editing, Funding acquisition. Phattarawan Malaisree: Resources, Data curation. Ochok Duangsano: Resources, Data curation. Pornkasem Jongpradist: Writing - review & editing, Funding acquisition, Supervision, Methodology, Conceptualization.

Declaration of competing interest

Dr. Pornkasem Jongpradist is an associate editor for Underground Space and was not involved in the editorial review or the decision to publish this article. All authors declare that there are no competing interests.

Acknowledgement

The authors gratefully acknowledge the financial support provided by King Mongkut’s University of Technology Thonburi (KMUTT), Thailand Science Research and Innovation (TSRI), and National Science, Research and Innovation Fund (NSRF) Basic Research Fund: Fiscal year 2026 under the project titled “Application of artificial intelligent and advanced computation for infrastructure project”. The corresponding author (C. Phutthananon) acknowledges the financial support from the National Research Council of Thailand (NRCT) under Grant No. N42A680226. This project was also funded by the National Research Council of Thailand (NRCT) and King Mongkut’s University of Technology North Bangkok under Contract No. N42A680120.

References

[1] Akbarzadeh M., Haghshenas S. S., Jalali S. M. E., Zare S., & Mikaeil R. (2022). Developing the rule of thumb for evaluating penetration rate of TBM, using binary classification. Geotechnical and Geological Engineering, 40(9), 4685-4703.

[2] Anitescu C., Atroshchenko E., Alajlan N., & Rabczuk T. (2019). Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 59(1), 345-359.

[3] Azadi A. H. S., Khalilzadeh M., Antucheviciene J., Heidari A., & Soon A. (2024). A sustainable multi-objective model for capacitated-electric-vehicle-routing-problem considering hard and soft time windows as well as partial recharging. Biomimetics, 9(4), 242.

[4] Babaveisi V., Paydar M. M., & Safaei A. S. (2018). Optimizing a multiproduct closed-loop supply chain using NSGA-II, MOSA, and MOPSO meta-heuristic algorithms. Journal of Industrial Engineering International, 14, 305-326.

[5] Bandyopadhyay S., Saha S., Maulik U., & Deb K. (2008). A simulated annealing-based multiobjective optimization algorithm: AMOSA. IEEE Transactions on Evolutionary Computation, 12(3), 269-283.

[6] Cao Y. P., Luo W., Xue Y. D., Lin W. R., & Zhang F. (2024). Modelbased offline reinforcement learning framework for optimizing tunnel boring machine operation. Underground Space, 19, 47-71.

[7] Chen L., Tian Z. Y., Zhou S. H., Gong Q. M., & Di H. G. (2024). Attitude deviation prediction of shield tunneling machine using TimeAware LSTM networks. Transportation Geotechnics, 45, 101195.

[8] Chen R. P., Zhang P., Wu H. N., Wang Z. T., & Zhong Z. Q. (2019). Prediction of shield tunneling-induced ground settlement using machine learning techniques. Frontiers of Structural and Civil Engineering, 13(6), 1363-1378.

[9] Cho K., van Merriënboer B., Bahdanau D., & Bengio Y. (2014a). On the properties of neural machine translation: Encoder-decoder approaches. In Proceedings of SSST-8, eighth workshop on syntax, semantics and structure in statistical translation (pp. 103-111). October 25, 2014, Doha, Qatar.

[10] Cho K., van Merriënboer B., Gulcehre C., Bahdanau D., Bougares F., Schwenk H., & Bengio Y. (2014b). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proceedings of the 2014 conference on empirical methods in natural language processing (pp.1724-1734). October 25-29, 2014, Doha, Qatar.

[11] Deb K. (2011). Multi-objective optimisation using evolutionary algorithms:An introduction. In Multi-objective evolutionary optimisation for product design and manufacturing (pp.3-34). Springer.

[12] Deb K., Pratap A., Agarwal S., & Meyarivan T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182-197.

[13] Do N. A., Dias D., Golpasand M. R. B., Dang V. K., Nait-Rabah O., Pham V. V., & Dang T. T. (2022). Numerical analyses of twin stacked mechanized tunnels in soft grounds - Influence of their position and construction procedure. Tunnelling and Underground Space Technology, 130, 104734.

[14] Do N. A., Dias D., & Oreste P. (2014). Three-dimensional numerical simulation of mechanized twin stacked tunnels in soft ground. Journal of Zhejiang University-Science A (Applied Physics & Engineering), 15, 896-913.

[15] Fu X. L., Wu M. Z., Tiong R. L. K., & Zhang L. M. (2024). Datadriven joint multi-objective prediction and optimization for advanced control during tunnel construction. Expert Systems with Applications, 238, 122118.

[16] Fu X. L., & Zhang L. M. (2021). Spatio-temporal feature fusion for realtime prediction of TBM operating parameters: A deep learning approach. Automation in Construction, 132, 103937.

[17] Gao B. Y., Wang R. R., Lin C. J., Guo X., Liu B., & Zhang W. G. (2021). TBM penetration rate prediction based on the long short-term memory neural network. Underground Space, 6(6), 718-731.

[18] Geshniani Y. V., Kamranrad R., & Emami I. (2020). A multi-objective scheduling payment pattern for project cash flow by considering resource constraints (a case study in power transfer system). International Journal of Industrial and Systems Engineering, 35(3), 299-313.

[19] Guo K., & Zhang L. M. (2022). Data-driven optimization for mitigating tunnel-induced damages. Applied Soft Computing, 115, 108128.

[20] Hajihassani M., Kalatehjari R., Marto A., Mohamad H., & Khosrotash M. (2020). 3D prediction of tunneling-induced ground move-ments based on a hybrid ANN and empirical methods. Engineering with Computers, 36, 251-269.

[21] Hamdia K. M., Zhuang X. Y., & Rabczuk T. (2021). An efficient optimization approach for designing machine learning models based on genetic algorithm. Neural Computing and Applications, 33, 1923-1933.

[22] Hasanipanah M., Noorian-Bidgoli M., Armaghani D. J., & Khamesi H. (2016). Feasibility of PSO-ANN model for predicting surface settlement caused by tunneling. Engineering with Computers, 32, 705-715.

[23] Huang J. T., Ji A. K., Zhang L. M., Fu X. L., & Song X. Q. (2025). Data-driven optimization for enhanced excavation efficiency in tunnel construction: A case study. Engineering Applications of Artificial Intelligence, 142, 109868.

[24] Ibragimov E., Kim Y., Lee J. H., Cho J., & Lee J. J. (2024). Automated pavement condition index assessment with deep learning and image analysis: An end-to-end approach. Sensors, 24(7), 2333.

[25] Kang Q., Chen E. J., Li Z. C., Luo H. B., & Liu Y. (2023). Attentionbased LSTM predictive model for the attitude and position of shield machine in tunneling. Underground Space, 13, 335-350.

[26] Kim D., Kwon K., Pham K., Oh J. Y., & Choi H. (2022). Surface settlement prediction for urban tunneling using machine learning algorithms with Bayesian optimization. Automation in Construction, 140, 104331.

[27] Kim D., Pham K., Oh J. Y., Lee S. J., & Choi H. (2022). Classification of surface settlement levels induced by TBM driving in urban areas using random forest with data-driven feature selection. Automation in Construction, 135, 104109.

[28] Koopialipoor M., Fahimifar A., Ghaleini E. N., Momenzadeh M., & Armaghani D. J. (2020). Development of a new hybrid ANN for solving a geotechnical problem related to tunnel boring machine performance. Engineering with Computers, 36, 345-357.

[29] Lin S. S., Zhang N., Zhou A. N., & Shen S. L. (2022). Time-series prediction of shield movement performance during tunneling based on hybrid model. Tunnelling and Underground Space Technology, 119, 104245.

[30] Liu B. K., Penaka S. R., Lu W. Z., Feng K. L., Rebbling A., & Olofsson T. (2023a). Data-driven quantitative analysis of an integrated open digital ecosystems platform for user-centric energy retrofits: A case study in northern Sweden. Technology in Society, 75, 102347.

[31] Liu B. K., Vu-Bac N., Zhuang X. Y., Fu X. L., & Rabczuk T. (2022). Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites. Composites Science and Technology, 224, 109425.

[32] Liu B. K., Vu-Bac N., Zhuang X. Y., Lu W. Z., Fu X. L., & Rabczuk T. (2023b). Al-DeMat: A web-based expert system platform for computationally expensive models in materials design. Advances in Engineering Software, 176, 103398.

[33] Liu B. K., Vu-Bac N., Zhuang X. Y., & Rabczuk T. (2020). Stochastic multiscale modeling of heat conductivity of Polymeric clay nanocomposites. Mechanics of Materials, 142, 103280.

[34] Liu B., Wang J. W., Wang R. R., Wang Y. X., & Zhao G. Z. (2023). Intelligent decision-making method of TBM operating parameters based on multiple constraints and objective optimization. Journal of Rock Mechanics and Geotechnical Engineering, 15(11), 2842-2856.

[35] Liu B. K., Wang Y. Z., Rabczuk T., Olofsson T., & Lu W. Z. (2024). Multi-scale modeling in thermal conductivity of polyurethane incorporated with phase change materials using physics-informed neural networks. Renewable Energy, 220, 119565.

[36] Liu W. L., Li A., & Liu C. J. (2022). Multi-objective optimization control for tunnel boring machine performance improvement under uncertainty. Automation in Construction, 139, 104310.

[37] Mahmoodzadeh A., Mohammadi M., Daraei A., Ali H. F. H., AlSalihi N. K., & Omer R. M. D. (2020). Forecasting maximum surface settlement caused by urban tunneling. Automation in Construction, 120, 103375.

[38] Moore J., & Chapman R. (1999). Application of particle swarm to multiobjective optimization. USA: Department of Computer Science and Software Engineering, Anburn University.

[39] Ocak I., & Seker S. E. (2013). Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes. Environmental Earth Sciences, 70, 1263-1276.

[40] Pan Y., Wang Z. Y., Sun L., & Chen J. J. (2024). Dynamic prediction and multi-objective optimization on driving position of tunnel boring machine (TBM): An automated deep learning approach. Acta Geotechnica, 19, 5611-5636.

[41] Phutthananon C., Lertkultanon S., Jongpradist P., Duangsano O., Likitlersuang S., & Jamsawang P. (2023). Numerical investigation on the responses of existing single piles due to adjacent twin tunneling considering the lagging distance. Underground Space, 11, 171-188.

[42] Phutthananon C., Ratanakijkul P., Youwai S., Kongkitkul W., & Jongpradist P. (2024). Modeling the mechanical response of cementadmixed clay under different stress paths using recurrent neural networks. International Journal of Geosynthetics and Ground Engineering, 10, 16.

[43] Qin C. J., Liu M. Y., Zhang Z. N., Yu H. G., Jin Y. R., Sun H., Tao J. F., & Liu C. L. (2023). An adaptive operating parameters decisionmaking method for shield machine considering geological environment. Tunnelling and Underground Space Technology, 141, 105372.

[44] Samaniego E., Anitescu C., Goswami S., Nguyen-Thanh V. M., Guo H., Hamdia K., Zhuang X., & Rabczuk T. (2020). An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 362, 112790.

[45] Shan F., He X. Z., Armaghani D. J., & Sheng D. C. (2024a). Effects of data smoothing and recurrent neural network (RNN) algorithms for real-time forecasting of tunnel boring machine (TBM) performance. Journal of Rock Mechanics and Geotechnical Engineering, 16(5), 1538-1551.

[46] Shan F., He X. Z., Armaghani D. J., Xu H. D., Liu X. L., & Sheng D. C. (2024). Real-time forecasting of TBM cutterhead torque and thrust force using aware-context recurrent neural networks. Tunnelling and Underground Space Technology, 152, 105906.

[47] Shan F., He X. Z., Armaghani D. J., Zhang P., & Sheng D. C. (2022). Success and challenges in predicting TBM penetration rate using recurrent neural networks. Tunnelling and Underground Space Technology, 130, 104728.

[48] Shen S. L., Elbaz K., Shaban W. M., & Zhou A. N. (2022). Real-time prediction of shield moving trajectory during tunnelling. Acta Geotechnica, 17(4), 1533-1549.

[49] Su J., Wang Y. Z., Niu X. K., Sha S., & Yu J. Y. (2022). Prediction of ground surface settlement by shield tunneling using XGBoost and Bayesian optimization. Engineering Applications of Artificial Intelligence, 114, 105020.

[50] Suwansawat S. (2002). Earth pressure balance (EPB) shield tunneling in Bangkok: Ground response and prediction of surface settlements using artificial neural networks. [Doctoral dissertation, Massachusetts Institute of Technology, USA].

[51] Suwansawat S., & Einstein H. H. (2006). Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling. Tunnelling and Underground Space Technology, 21(2), 133-150.

[52] Tang L. B., & Na S. (2021). Comparison of machine learning methods for ground settlement prediction with different tunneling datasets. Journal of Rock Mechanics and Geotechnical Engineering, 13(6), 1274-1289.

[53] Tang Y., Yang J. S., You Y. Y., Fu J. Y., Zheng X. C., & Zhang C. (2024). Multi-output prediction for TBM operation parameters based on stacking ensemble algorithm. Tunnelling and Underground Space Technology, 152, 105960.

[54] Wang X. Q., Gao H. B., Jia Z. M., & Li Z. J. (2023). BL-YOLOv8: An improved road defect detection model based on YOLOv8. Sensors, 23 (20), 8361.

[55] Xia Y. Y., Zhang C., Wang C. X., Liu H. J., Sang X. X., Liu R., Zhao P., An G. F., Fang H. Y., Shi M. S., Li B., Yuan Y. M., & Liu B. K. (2023). Prediction of bending strength of glass fiber reinforced methacrylate-based pipeline UV-CIPP rehabilitation materials based on machine learning. Tunnelling and Underground Space Technology, 140, 105319.

[56] Xu C., Liu X. L., Wang E. Z., & Wang S. J. (2021). Prediction of tunnel boring machine operating parameters using various machine learning algorithms. Tunnelling and Underground Space Technology, 109, 103699.

[57] Yang T. H., Wen T., Huang X., Liu B., Shi H. B., Liu S. R., Peng X. X., & Sheng G. Z. (2024). Predicting model of dual-mode shield tunneling parameters in complex ground using recurrent neural networks and multiple optimization algorithms. Applied Sciences, 14 (2), 581.

[58] Yang Y. F., Liao S. M., & Liu M. B. (2023). Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework. Frontiers of Structural and Civil Engineering, 17, 994-1010.

[59] Yang Y., Liao Q. F., Wang J., & Wang Y. (2022). Application of multiobjective particle swarm optimization based on short-term memory and K -means clustering in multi-modal multi-objective optimization. Engineering Applications of Artificial Intelligence, 112, 104866.

[60] Yu S. H., Zhang Z. X., Wang S. F., Huang X., & Lei Q. H. (2024). A performance-based hybrid deep learning model for predicting TBM advance rate using Attention-ResNet-LSTM. Journal of Rock Mechanics and Geotechnical Engineering, 16(1), 65-80.

[61] Zeng J., Roy B., Kumar D., Mohammed A. S., Armaghani D. J., Zhou J., & Mohamad E. T. (2022). Proposing several hybrid PSOextreme learning machine techniques to predict TBM performance. Engineering with Computers, 38, 3811-3827.

[62] Zhang N., Zhang N., Zheng Q., & Xu Y. S. (2022). Real-time prediction of shield moving trajectory during tunnelling using GRU deep neural network. Acta Geotechnica, 17, 1167-1182.

[63] Zhang P., Wu H. N., Chen R. P., Dai T., Meng F. Y., & Wang H. B. (2020). A critical evaluation of machine learning and deep learning in shield-ground interaction prediction. Tunnelling and Underground Space Technology, 106, 103593.

[64] Zhou J., Qiu Y. G., Zhu S. L., Armaghani D. J., Li C. Q., Nguyen H., & Yagiz S. (2021). Optimization of support vector machine through the use of metaheuristic algorithms in forecasting TBM advance rate. Engineering Applications of Artificial Intelligence, 97, 104015.

[65] Zizka Z., & Thewes M. (2016). Recommendations for face support pressure calculations for shield tunnelling in soft ground. Deutsche Ausschuß für unterirdisches Bauen e. V. (DAUB).