Abstract: Determining the group forces of the thrust system is essential for trajectory control of tunnel boring machines (TBMs). Existing methods for selecting an optimal solution mainly consider the force variance among groups, while ignoring other constraints, such as uneven segment loading and excessive hydraulic shock. In this study, we develop a more comprehensive and robust framework for force allocation. First, a novel region-reconfigurable hydraulic system is designed, which enforces consistency among the forces acting on each segment. Then on this basis, for the ramping-up tunneling stage, quadratic programming (QP) is used to optimize force uniformity across the spatial dimension. Compared to the on-site allocation result, the improvement in force uniformity reaches up to 32.89%. Moreover, to address the hydraulic shock caused by excessive adjustment to the force, hydraulic compliance is introduced and optimized together with force uniformity using the non-dominated sorting genetic algorithm II (NSGA-II), which outperforms weighted QP by 1.25×10⁶ kN² in uniformity and 2.86 kN² in compliance. Analyzing performance in the steady tunneling stage, the service life of the components improves significantly. To avoid a non-existent solution for the thrust force vector, a genetic algorithm-based error tolerance method is developed. Therefore, all deviation rectification commands can be answered with a minor compromise of up to 3% in the fitting accuracy of the thrust force vector. In summary, this framework enhances the adaptability and robustness of the force allocation strategy, providing a reliable foundation for TBM trajectory control.

基于可动态分区推进系统的多缸推力解算技术

[1]ChenJS, MoHH, 2009. Numerical study on crack problems in segments of shield tunnel using finite element method. Tunnelling and Underground Space Technology, 24(1):91-102.

[2]ChenK, YangYD, 2017. Innovation and development trends of shield manufacturing technology in China. Tunnel Construction, 37(3):276-284 (in Chinese).

[3]DaiZY, LiPN, WangX, et al., 2022. Asymmetric force effect and damage analysis of unlooped segment of large-diameter shield under synchronous propulsion and assembly mode. Applied Sciences, 12(6):2850.

[4]DengKS, HuangJL, WangHG, 2015. Layout optimization of non-equidistant arrangement for thrust systems in shield machines. Automation in Construction, 49:135-141.

[5]DengKS, LiYY, ZhangXM, et al., 2021. Optimal layout design for thrust systems in earth pressure balance shield machines under sudden loads. Arabian Journal for Science and Engineering, 46(3):2793-2802.

[6]DengKS, TangXQ, WangLP, et al., 2011a. Force transmission characteristics for the non-equidistant arrangement thrust systems of shield tunneling machines. Automation in Construction, 20(5):588-595.

[7]DengKS, TangXQ, WangLP, et al., 2011b. Research on characteristics of deformation in thrust system for EPB shield machines. Tunnelling and Underground Space Technology, 26(1):15-21.

[8]DengKS, YinZR, MengBL, et al., 2019. A load-balancing-oriented symmetrical uneven layout design for thrust system in tunneling machines under composite ground. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 233(8):2847-2854.

[9]ElbazK, ShenSL, ZhouAN, et al., 2024. Reinforcement learning-based optimizer to improve the steering of shield tunneling machine. Acta Geotechnica, 19(6):4167-4187.

[10]GongJ, BaoTF, ZhuZ, et al., 2024. BIM-based framework of automatic tunnel segment assembly and deviation control. Underground Space, 16:59-78.

[11]GuoK, XuYP, LiJF, 2018. Thrust force allocation method for shield tunneling machines under complex load conditions. Automation in Construction, 96:141-147.

[12]GuoWT, GuoWZ, 2017. A novel self-adaptive thrust system of shield machine under complex geological working condition. Tunnelling and Underground Space Technology, 63:133-143.

[13]HarandizadehH, ArmaghaniDJ, AsterisPG, et al., 2021. TBM performance prediction developing a hybrid ANFIS-PNN predictive model optimized by imperialism competitive algorithm. Neural Computing and Applications, 33(23):16149-16179.

[14]HuM, WuBJ, ZhouWB, et al., 2022. Self-driving shield: intelligent systems, methodologies, and practice. Automation in Construction, 139:104326.

[15]JiaGP, HuoJZ, YangBW, et al., 2023. The real-time optimal attitude control of tunnel boring machine based on reinforcement learning. Applied Sciences, 13(18):10026.

[16]KongXX, TangL, LingXZ, et al., 2024. Development of shield model test system for studying the bias load of shield in soil-rock compound strata. Tunnelling and Underground Space Technology, 143:105464.

[17]LiJB, ChenZY, LiX, et al., 2023a. Feedback on a shared big dataset for intelligent TBM Part I: feature extraction and machine learning methods. Underground Space, 11:1-25.

[18]LiJB, ChenZY, LiX, et al., 2023b. Feedback on a shared big dataset for intelligent TBM Part II: application and forward look. Underground Space, 11:26-45.

[19]LiZM, Yazdani BejarbanehB, AsterisPG, et al., 2021. A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass. Soft Computing, 25(17):11877-11895.

[20]LinPH, WuMZ, XiaoZH, et al., 2024. Physics-informed deep reinforcement learning for enhancement on tunnel boring machine’s advance speed and stability. Automation in Construction, 158:105234.

[21]LiuXY, ShaoC, 2010. Present status and prospect of shield machine automatic control technology. Journal of Mechanical Engineering, 46(20):152-160 (in Chinese).

[22]MMC-Gamuda Tunnelling Training Academy, 2020. Tunnelling | Malaysia’s Self Driving TBMs. https://www.newcivilengineer.com/innovative-thinking/tunnelling-malaysias-self-driving-tbms-18-02-2020/

[23]ShiCH, WangZX, GongCJ, et al., 2022. Prediction of the additional structural response of segmental tunnel linings induced by asymmetric jack thrusts. Tunnelling and Underground Space Technology, 124:104471.

[24]ShiH, GongGF, YangHY, et al., 2013. Compliance of hydraulic system and its applications in thrust system design of shield tunneling machine. Science China Technological Sciences, 56(9):2124-2131.

[25]SASAC (State-owned Assets Supervision and Administration Commission of the State Council), 2023. Shanghai’s First Subway Using Self Driving Shield Technology Successfully Launched (in Chinese). http://www.sasac.gov.cn/n2588025/n2588129/c28677934/content.html

[26]TangL, KongXX, LingXZ, et al., 2022. Deviation correction strategy for the earth pressure balance shield based on shield-soil interactions. Frontiers of Mechanical Engineering, 17(2):20.

[27]WangJY, 2017. Super-large diameter shield tunneling technologies in China in recent decade. Tunnel Construction, 37(3):330-335 (in Chinese).

[28]WangS, ZhangYK, GongGF, 2024. Optimal decision-making system of shield tunneling parameters based on LSTM and MNSGA-II. Proceedings of 2024 IEEE International Conference on Automatic Control and Intelligent Systems, p.65-70.

[29]WangXY, YuanDJ, JinDL, et al., 2022. Determination of thrusts for different cylinder groups during shield tunneling. Tunnelling and Underground Space Technology, 127:104579.

[30]XuH, ZhouJ, AsterisPG, et al., 2019. Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate. Applied Sciences, 9(18):3715.

[31]XuJ, BuJF, ZhangLG, et al., 2023. Intelligent decision framework of shield attitude correction based on deep reinforcement learning. Proceedings of the 17th East Asian-Pacific Conference on Structural Engineering and Construction, p.1273-1287.

[32]YangYB, ZhouB, XieXY, et al., 2018. Characteristics and causes of cracking and damage of shield tunnel segmented lining in construction stage—a case study in Shanghai soft soil. European Journal of Environmental and Civil Engineering, 22(sup1):s213-s227.

[33]ZhangYK, GongGF, YangHY, et al., 2020. Precision versus intelligence: autonomous supporting pressure balance control for slurry shield tunnel boring machines. Automation in Construction, 114:103173.

[34]ZhangYK, GongGF, YangHY, et al., 2022. Towards autonomous and optimal excavation of shield machine: a deep reinforcement learning-based approach. Journal of Zhejiang University-SCIENCE A, 23(6):458-478.

[35]ZhangYK, GongGF, YangHY, et al., 2024. From tunnel boring machine to tunnel boring robot: perspectives on intelligent shield machine and its smart operation. Journal of Zhejiang University-SCIENCE A, 25(5):357-381.

[36]ZhengZ, LuoKD, TanXZ, et al., 2024. Autonomous steering control for tunnel boring machines. Automation in Construction, 159:105259.

[37]ZhuYT, ZhaiYX, MinR, et al., 2021. Model test on the synchronous technology combining with shield tunneling and segment assembling based on the linear distribution principle of the thrust force. IOP Conference Series: Earth and Environmental Science, 861:052079.

[38]ZhuYT, ZhuYF, ChenEJ, et al., 2023. Synchronous shield tunnelling technology combining advancement and segment fabrication: principle, verification and application. Underground Space, 13:23-47.