Hybrid Surrogate - Physics - AI Optimization of EPB-TBM Performance: A Data-Driven Application from the Jakarta Metro Project
DOI:
https://doi.org/10.9744/jti.28.2.117%20-%20139Keywords:
Tunnel Boring Machine (TBM) optimization, hybrid surrogate - physics - AI framework, physics-informed neural network (PINN), deep reinforcement learning (DRL), Bayesian evolutionary optimizationAbstract
The increasing complexity and geological unpredictability associated with mechanised tunnelling demand optimisation frameworks that go beyond static, offline parameter adjustments and embrace adaptive and physically coherent decision-making processes. Traditional metaheuristic algorithms, such as genetic algorithms (GA), particle swarm optimisation (PSO), and simulated annealing (SA), have been widely applied to optimise tunnel boring machine (TBM) performance. However, they are inherently limited by their lack of real-time adaptability and restricted physical interpretability. This research presents a hybrid surrogate–physics–AI optimization framework (H-SGP-BO–PINN–DRL) that redefines TBM optimization as a physics-constrained adaptive control challenge, shifting away from a static optimization model. The framework integrates a surrogate-assisted hybrid GA–PSO combined with Bayesian optimisation for a global search that considers uncertainty, a physics-informed neural network (PINN) that incorporates essential mechanical principles to ensure geotechnical feasibility, and a deep reinforcement learning (DRL) controller that enables real-time adjustments within physically feasible operational limits. The framework was validated using field data from EPB-TBM projects in the Jakarta MRT and Istanbul Metro systems, as well as synthetic datasets generated using FEM. The results show that the proposed method reduces the specific energy consumption (SEC) and improves the penetration rate (PR), while also demonstrating superior convergence stability and robustness compared to traditional metaheuristic and surrogate-based methods. Monte Carlo bootstrapping and Sobol global sensitivity analysis further identify thrust force and cutterhead rotation speed as the main factors affecting energy-performance variability. By integrating surrogate-assisted optimization, physics-informed learning, and reinforcement-based adaptability, this study introduces a new paradigm for intelligent TBM operation, enabling interpretable, energy-efficient, and deployable decision support for future smart and autonomous tunneling systems.
Downloads
References
[1] X. Fu, M. Wu, R. L. K. Tiong, and L. Zhang, “Data-driven joint multi-objective prediction and optimization for advanced control during tunnel construction,” Expert Syst Appl, vol. 238, p. 122118, 2023, doi: https://doi.org/10.1016/j.eswa.2023.122118.
[2] W. Liu, A. Li, and C.-Y. Liu, “Multi-objective optimization control for tunnel boring machine performance improvement under uncertainty,” Autom. Constr., 2022, doi: https://doi.org/10.1016/j.autcon.2022.104310.
[3] X. Wang et al., “QPSO-ILF-ANN-based optimization of TBM control parameters considering tunneling energy efficiency,” Front. Struct. Civ. Eng., vol. 17, pp. 25–36, 2023, doi: https://doi.org/10.1007/s11709-022-0908-z.
[4] Z. Ma, G. Wu, P. Suganthan, A. Song, and Q. Luo, “Performance assessment and exhaustive listing of 500+ nature inspired metaheuristic algorithms,” Swarm Evol Comput, vol. 77, p. 101248, 2022, doi: https://doi.org/10.48550/arxiv.2212.09479.
[5] K. Rajwar, K. Deep, and S. Das, “An exhaustive review of the metaheuristic algorithms for search and optimization: taxonomy, applications, and open challenges,” Artif. Intell. Rev., pp. 1–71, 2023, doi: https://doi.org/10.1007/s10462-023-10470-y.
[6] B. Toaza and D. Esztergár-Kiss, “A review of metaheuristic algorithms for solving TSP-based scheduling optimization problems,” Appl Soft Comput, vol. 148, p. 110908, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110908.
[7] O. Turgut, M. Turgut, and E. Kırtepe, “A systematic review of the emerging metaheuristic algorithms on solving complex optimization problems,” Neural Comput. Appl., vol. 35, pp. 14275–14378, 2023, doi: https://doi.org/10.1007/s00521-023-08481-5.
[8] C. Salam M and A. Khanifa, “An Interpretable Data-Driven Framework for Smart Tunnel Boring Machine Performance Analysis and Energy–Cost Optimization,” J. Tek. Ind. J. Keilmuan Dan Apl. Tek. Ind., vol. 28, no. 1, pp. 24–46, 2026, doi: https://doi.org/10.9744/jti.28.1.24-46.
[9] B. Abdollahzadeh et al., “Puma optimizer (PO): a novel metaheuristic optimization algorithm and its application in machine learning,” Clust Comput, vol. 27, pp. 5235–5283, 2024, doi: https://doi.org/10.1007/s10586-023-04221-5.
[10] A. Alorf, “A survey of recently developed metaheuristics and their comparative analysis,” Eng Appl Artif Intell, vol. 117, p. 105622, 2023, doi: https://doi.org/10.1016/j.engappai.2022.105622.
[11] W. Yi, R. Qu, L. Jiao, and B. Niu, “Automated Design of Metaheuristics Using Reinforcement Learning Within a Novel General Search Framework,” IEEE Trans. Evol. Comput., vol. 27, pp. 1072–1084, 2023, doi: https://doi.org/10.1109/tevc.2022.3197298.
[12] V. Goyal and J. Grand-Clément, “Robust Markov Decision Processes: Beyond Rectangularity,” Math Oper Res, vol. 48, pp. 203–226, 2022, doi: 10.1287/moor.2022.1259.
[13] P. Qu and L. Zhang, “Uncertainty-based multi-objective optimization in twin tunnel design considering fluid-solid coupling,” Reliab Eng Syst Saf, vol. 253, p. 110575, 2024, doi: https://doi.org/10.1016/j.ress.2024.110575.
[14] Y. Wang, C. Ye, and Y. Wang, “Hierarchical multi-objective optimization of proton exchange membrane fuel cell with parameter uncertainty,” Swarm Evol Comput, vol. 86, p. 101464, 2024, doi: https://doi.org/10.1016/j.swevo.2023.101464.
[15] N. Hassan and A. Saleem, “Neural Network-Based Adaptive Controller for Trajectory Tracking of Wheeled Mobile Robots,” IEEE Access, vol. 10, pp. 13582–13597, 2022, doi: https://doi.org/10.1109/access.2022.3146970.
[16] X. Li, L. Wang, Y. An, Q. Huang, Y. Cui, and H. Hu, “Dynamic path planning of mobile robots using adaptive dynamic programming,” Expert Syst Appl, vol. 235, p. 121112, 2023, doi: https://doi.org/10.1016/j.eswa.2023.121112.
[17] L. Zhang, Y. Li, L. Wang, J. Wang, and H. Luo, “Physics-data driven multi-objective optimization for parallel control of TBM attitude,” Adv Eng Inform., vol. 65, p. 103101, 2025, doi: https://doi.org/10.1016/j.aei.2024.103101.
[18] S. Hou, Y. Liu, J. Yu, R. Zhang, L. Cheng, and C. Gao, “Intelligent decision-making for TBM tunnelling control parameters using multi-objective optimization,” J. Rock Mech. Geotech. Eng., 2024, doi: https://doi.org/10.1016/j.jrmge.2024.09.001.
[19] F. Shan, X. He, D. J. Armaghani, and D. Sheng, “Effects of data smoothing and recurrent neural network (RNN) algorithms for real-time forecasting of tunnel boring machine (TBM) performance,” J. Rock Mech. Geotech. Eng., 2023, doi: https://doi.org/10.1016/j.jrmge.2023.06.015.
[20] K. Rajwar, K. Deep, and S. Das, “An exhaustive review of the metaheuristic algorithms for search and optimization: taxonomy, applications, and open challenges,” Artif. Intell. Rev., pp. 1–71, 2023, doi: https://doi.org/10.1007/s10462-023-10470-y.
[21] C. Salam M, M. Rinjani, O. Kural, M. Rinduwidara, and A. Khanifa, “Enhancing output in open-pit coal mining: The influence of front-loading geometry on machinery functionality,” Concurr. Eng., vol. 33, no. 1–4, pp. 145–170, Dec. 2025, doi: https://doi.org/10.1177/1063293X251361192.
[22] G. V. Priya and S. Ganguly, “Multi-swarm surrogate model assisted PSO algorithm to minimize distribution network energy losses,” Appl Soft Comput, vol. 159, p. 111616, 2024, doi: https://doi.org/10.1016/j.asoc.2024.111616.
[23] A. Younis and Z. Dong, “Adaptive surrogate assisted multi-objective optimization approach for highly nonlinear and complex engineering design problems,” Appl Soft Comput, vol. 150, p. 111065, 2023, doi: https://doi.org/10.1016/j.asoc.2023.111065.
[24] H. Kim, C. Park, and H. Kim, “Multi-task optimization with Bayesian neural network surrogates for parameter estimation of a simulation model,” Comput Stat Data Anal, vol. 204, p. 108097, 2024, doi: https://doi.org/10.1016/j.csda.2024.108097.
[25] Q. Lin, J. Hu, and Q. Zhou, “Parallel multi-objective Bayesian optimization approaches based on multi-fidelity surrogate modeling,” Aerosp. Sci. Technol., 2023, doi: https://doi.org/10.1016/j.ast.2023.108725.
[26] R. R. Faria, B. Capron, A. Secchi, and M. B. de Souza, “A data-driven tracking control framework using physics-informed neural networks and deep reinforcement learning for dynamical systems,” Eng Appl Artif Intell, vol. 127, p. 107256, 2024, doi: https://doi.org/10.1016/j.engappai.2023.107256.
[27] M. H. Saeed, H. Kazmi, and G. Deconinck, “Dyna-PINN: Physics-informed Deep Dyna-Q Reinforcement Learning for Intelligent Control of Building Heating System in Low-Diversity Training Data Regimes,” Energy Build., 2024, doi: https://doi.org/10.1016/j.enbuild.2024.114879.
[28] K. Elbaz, A. Zhou, and S. Shen, “Deep reinforcement learning approach to optimize the driving performance of shield tunnelling machines,” Tunn. Undergr. Space Technol., 2023, doi: https://doi.org/10.1016/j.tust.2023.105104.
[29] E. Soranzo, C. Guardiani, and W. Wu, “Reinforcement Learning for the Face Support Pressure of Tunnel Boring Machines,” Geosciences, 2023, doi: https://doi.org/10.3390/geosciences13030082.
[30] E. Martinez, F. Stauch, B. G. de Soto, and R. Sacks, “Integration of building information modelling and digital twin in mechanized tunnelling construction,” Eng. Constr. Archit. Manag., 2025, doi: https://doi.org/10.1108/ecam-01-2025-0031.
[31] S. Mostafa, R. L. Sousa, and H. H. Einstein, “Toward the automation of mechanized tunneling ‘exploring the use of big data analytics for ground forecast in TBM tunnels,’” Tunn. Undergr. Space Technol., 2024, doi: https://doi.org/10.1016/j.tust.2024.105643.
[32] J. Huang, A. Ji, L. Zhang, X. Fu, and X. Song, “Data-driven optimization for enhanced excavation efficiency in tunnel construction: A case study,” Eng Appl Artif Intell, vol. 142, p. 109868, 2025, doi: https://doi.org/10.1016/j.engappai.2024.109868.
[33] Y. Pan, Z. Wang, L. Sun, and J. Chen, “Dynamic prediction and multi-objective optimization on driving position of tunnel boring machine (TBM): an automated deep learning approach,” Acta Geotech., 2024, doi: https://doi.org/10.1007/s11440-024-02271-6.
[34] M. Ahmad, S. Keawsawasvong, M. R. Bin Ibrahim, M. Waseem, K. Reza Kashyzadeh, and M. M. Sabri Sabri, “Novel Approach to Predicting Soil Permeability Coefficient Using Gaussian Process Regression,” Sustainability, vol. 14, no. 14, p. 8781, 2022, doi: https://doi.org/10.3390/su14148781.
[35] P. Aivaliotis-Apostolopoulos and D. Loukidis, “Swarming genetic algorithm: A nested fully coupled hybrid of genetic algorithm and particle swarm optimization,” PLoS ONE, vol. 17, 2022, doi: https://doi.org/10.1371/journal.pone.0275094.
[36] Karishma and H. Kumar, “A novel hybrid model for task scheduling based on particle swarm optimization and genetic algorithms,” Math. Eng., 2024, doi: https://doi.org/10.3934/mine.2024023.
[37] W. Ouyang, G. Li, L. Chen, and S.-W. Liu, “Machine learning-based soil–structure interaction analysis of laterally loaded piles through physics-informed neural networks,” Acta Geotech., 2024, doi: https://doi.org/10.1007/s11440-023-02179-7.
[38] H. Zhou, H. Wu, B. B. Sheil, and Z. Wang, “A self-adaptive physics-informed neural networks method for large strain consolidation analysis,” Comput. Geotech., 2025, doi: https://doi.org/10.1016/j.compgeo.2025.107131.
[39] P. Lin, A. Ji, Y. Zhou, L. Zhang, and R. L. K. Tiong, “Automated position control of tunnel boring machine during excavation using deep reinforcement learning,” Appl Soft Comput, vol. 167, p. 112234, 2024, doi: https://doi.org/10.1016/j.asoc.2024.112234.
[40] P. Lin, L. Zhang, R. L. K. Tiong, and X. Song, “Physics-guided deep reinforcement learning for improved operation of TBM considering kinetic inertia stability,” Adv Eng Inform., vol. 63, p. 102943, 2025, doi: https://doi.org/10.1016/j.aei.2024.102943.
[41] K. Fu, A. Ye, and L. Zhou, “Parameterized fragility-based uncertainty influence quantification and sensitivity analysis methodology: Concept, formulation, and application,” Soil Dyn. Earthq. Eng., 2025, doi: https://doi.org/10.1016/j.soildyn.2024.109070.
[42] V. Karyofylli et al., “Sensitivity analysis and uncertainty quantification in predictive modeling of proton-exchange membrane electrolytic cells,” J. Power Sources, 2024, doi: https://doi.org/10.1016/j.jpowsour.2024.234209.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 maharani rindu widara, Chairul Salam M.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the Jurnal Teknik Industri: Jurnal Keilmuan dan Aplikasi Teknik Industri will be Open-Access articles distributed under the terms and conditions of the Creative Commons Attribution License (CC BY).
This work is licensed under a Creative Commons Attribution License (CC BY).
