Geological adaptive intelligent control of earth pressure balance shield machine based on deep reinforcement learning DOI Creative Commons
Xuanyu Liu, Wenshuai Zhang, Cheng Shao

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(8)

Published: July 27, 2024

Abstract Scientific and precise control of tunnelling parameters is utmost importance during the construction shield machines. Given complexity working environment, manual operation highly prone to causing safety accidents. Therefore, achieving intelligent machine crucial. Based on this, this paper proposes a geological adaptive method earth pressure balance using Deep Deterministic Policy Gradient (DDPG) algorithm as framework, with Actor-Critic basis. Firstly, DDPG agent constructed replace screw conveyor system main body strategy implementation. Secondly, an environmental model established by utilizing mechanism between sealed cabin speed. The real-time pressure, target error serve state space, while speed used action space. A combined reward function set based accuracy. Finally, Actor network interacts environment under supervision Critic network. Successful training achieved when cumulative value maximized, resulting in output optimal strategy. In paper, dynamically regulates interacting realize ensure dynamic excavation face pressure. test results show that has good effect various conditions, can complete 72 kinds soil transition tasks. It strong adaptability respond well changes conditions. This approach enhances intelligence machine, mitigating inaccuracies attributed human operation, which provides guarantee safe whilst exhibiting valuable engineering applications.

Language: Английский

A tunneling speed enhancement method for super-large-diameter shield machines considering strata heterogeneity DOI
Jian Zhang,

Jinjian Hu,

Chaoyang Zong

et al.

Tunnelling and Underground Space Technology, Journal Year: 2025, Volume and Issue: 159, P. 106496 - 106496

Published: Feb. 27, 2025

Language: Английский

Citations

0
Selection Method and Application of Dual‐Mode TBM in Composite Strata: A Case Study of Shenzhen Metro Line 14 DOI Creative Commons
Jizheng Huang,

Xiaoyue Kang,

Gaoyu Ma

et al.

Advances in Civil Engineering, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

With the continuous development of urban railway construction, metro tunnels tend to cross complex geological formations. Single‐mode tunnel boring machines (TBMs), typically designed accommodate a specific type rock mass, often encounter severe eccentric cutter wear and attitude deflection, when tunneling in composite strata. The inadequate support pressure exerted by TBM under single excavation mode that fails balance soil water weak strata may result collapse face. dual‐mode equipment, which has flexible adaptability environment could be potential solution problems longitudinal However, traditional selection methods mainly focus on influence parameters an individual stratum, according empirical analysis. While requires comprehensive consideration combined effects efficiency, duration, cost related distribution different Based comparison projects using equipment worldwide their parameters, fundamental principles were proposed this research. A fuzzy evaluation model was developed for earth balanced (EPB) open cutting determine limit length each section adjustment. Finally, case study Shenzhen Metro Line 14 presented verify innovative method TBM. results show are consistent with actual project, based field‐obtained operational parameters.

Language: Английский

Citations

0
A physics-data-driven method for predicting surface and building settlement induced by tunnel construction DOI
You Wang,

Q. J. Fan,

Fang Dai

et al.

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 179, P. 107020 - 107020

Published: Dec. 25, 2024

Language: Английский

Citations

3
Rapid Prediction of Cutterhead Torque in Hard-Rock Tunneling Using IEWOA-TSVD-ITELM DOI Creative Commons
Long Li, Zaobao Liu

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 88658 - 88680

Published: Jan. 1, 2024

Language: Английский

Citations

1
A singular spectrum analysis-enhanced BiTCN-selfattention model for runoff prediction DOI
Wenchuan Wang,

Feng-rui Ye,

Yiyang Wang

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Dec. 12, 2024

Language: Английский

Citations

1
Geological adaptive intelligent control of earth pressure balance shield machine based on deep reinforcement learning DOI Creative Commons
Xuanyu Liu, Wenshuai Zhang, Cheng Shao

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(8)

Published: July 27, 2024

Abstract Scientific and precise control of tunnelling parameters is utmost importance during the construction shield machines. Given complexity working environment, manual operation highly prone to causing safety accidents. Therefore, achieving intelligent machine crucial. Based on this, this paper proposes a geological adaptive method earth pressure balance using Deep Deterministic Policy Gradient (DDPG) algorithm as framework, with Actor-Critic basis. Firstly, DDPG agent constructed replace screw conveyor system main body strategy implementation. Secondly, an environmental model established by utilizing mechanism between sealed cabin speed. The real-time pressure, target error serve state space, while speed used action space. A combined reward function set based accuracy. Finally, Actor network interacts environment under supervision Critic network. Successful training achieved when cumulative value maximized, resulting in output optimal strategy. In paper, dynamically regulates interacting realize ensure dynamic excavation face pressure. test results show that has good effect various conditions, can complete 72 kinds soil transition tasks. It strong adaptability respond well changes conditions. This approach enhances intelligence machine, mitigating inaccuracies attributed human operation, which provides guarantee safe whilst exhibiting valuable engineering applications.

Language: Английский

Citations

0