Deep learning technologies for shield tunneling: Challenges and opportunities

Zhou, Cheng; Gao, Yuyue; Chen, Elton J.; Ding, Lieyun; Qin, Wenbo

doi:10.1016/j.autcon.2023.104982

Cited by 21 publications

(4 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main types of automatic measurement for shield machines are laser guidance and gyroscope guidance. The laser guidance system, in comparison to the gyroscope guidance system, can timely reflect the attitude of the shield machine, with simple operation and high guidance accuracy [26]. Laser guidance functionality is based on directing a laser beam emitted from a fully automatic laser theodolite fixed on the tunnel lining segments towards an electronic laser target positioned on the upper right portion of the shield machine's front.…”

Section: Measurement Of Shield Attitudementioning

confidence: 99%

Prediction of shield tunneling attitude: a hybrid deep learning approach considering feature temporal attention

Zeng,

Chen,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate prediction of shield attitude deviation is essential to ensure safe and efficient shield tunneling. However, previous studies have predominantly emphasized temporal correlation, which has limitations in engineering guidance and prediction accuracy. This research proposes a hybrid deep learning approach considering feature temporal attention (FTA-N-GRU) for shield attitude prediction. To elucidate the contributions of each parameter, the Integrated Gradients algorithm is leveraged for parameter sensitivity analysis. The results from the Bangladesh Karnaphuli River Tunnel Project indicate that: the proposed model outperforms other models in prediction accuracy. The integration of feature attention can adaptively allocate attention weights to input parameters, facilitating inexperienced operators in discerning crucial parameter variations and decision-making. By incorporating temporal attention, the model effectively explores the connection among different output time steps, improving overall prediction accuracy and reliability. Consequently, operators are empowered with timely information to proactively adjust operations before deviations occur, underscoring the significance of this approach in promoting safe and efficient shield tunneling practices.

show abstract

Section: Measurement Of Shield Attitudementioning

confidence: 99%

Prediction of shield tunneling attitude: a hybrid deep learning approach considering feature temporal attention

Zeng,

Chen,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The reciprocating motion of the mud pump piston within the cylinder was simulated and analyzed using the Abaqus finite element software. Given the complex operating conditions of the cylinder friction pair in practical scenarios, the following assumptions were made to ensure the smooth progress of the simulation: 1 The friction pair of the cylinder was treated as an ideal axisymmetric model. 2 The materials used for various components, including the piston and the cylinder, are considered continuous, uniform, and isotropic.…”

Section: Preprocessing For Simulationmentioning

confidence: 99%

“…The motion analysis of the piston within the cylinder liner was conducted in three loading steps: 1 Simulating the piston's interference fit within the cylinder aimed to achieve initial sealing. 2 Keeping the cylinder, piston, steel core, and tableting static, with the premise of initial preloading force, the working pressure of 6 MPa was uniformly applied on the right end face of the piston in contact with the mud, as indicated by the red arrow in Figure 4.…”

Section: Preprocessing For Simulationmentioning

confidence: 99%

“…In recent years, with the vigorous development of global infrastructure construction, tunnel construction technology has witnessed unprecedented rapid advancement. In the meantime, tunnel construction is facing the challenges of complex geological conditions and difficult construction environments [1], which demand not only innovative engineering techniques but also improvements in construction equipment and comprehensive solutions [1]. As a key technology of tunnel construction, the slurry shield method combines a shield machine with a mud circulation system to realize the tunnel excavation and tunnel support at the same time so as to provide substantial support for urban development and infrastructure construction [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Thermo–Solid Coupling Analysis of Bionic Piston for a Mud Pump in Tunnel Engineering

Tian,

et al. 2023

Buildings

View full text Add to dashboard Cite

With the development of mud shield tunnel construction technology, the demands on the working performance of a mud pump are becoming higher and higher. As one of the critical components of a mud pump that is easy to wear, the performance of the piston directly affects the operational efficiency and lifespan of the mud pump. The bionic shape of the piston was designed under the guidance of non-smooth surface characteristics of natural organisms to enhance friction and wear performance as well as longevity. The stress field and temperature field characteristics of the pistons with three bionic structures (pit, stripe, and prismatic) were analyzed based on finite element simulation. The stress field analysis results indicated that, for the prismatic shape and pit shape pistons, the maximum stress was concentrated in the lip regions, and both of them bore large stress at the root. For the stripe-shaped piston, the stress was dispersed on both sides of the stripe structure, the stress at the root was small, and the stress gradient along the axial direction was relatively gentle. The stripe-shaped bionic structure can significantly improve the stress distribution state on the piston surface, and the optimal stripe width was recommended to be between 1 and 1.5 mm. The temperature field analysis results indicated that, for the stripe-shaped piston, the surface temperature and heat flux were the smallest, and the temperature gradient was relatively smaller than that of pit-shaped and prismatic-shaped pistons, so it was easier to dissipate heat. When the stripe width was 1.5 mm, the temperature distribution was the most uniform, and the heat flux in localized areas was the smallest, so the heat generated by friction was relatively easy to discharge in the unit area.

show abstract

Earthwork digital twin for teleoperation of an automated bulldozer in edge dumping

You

Zhou

Ding

et al. 2023

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

The unstructured construction site with a complex and changeable environment brings challenges to human–machine interaction. In this study, the earthwork digital twin (DT) is proposed to realize accurate and real‐time perception, which can support the teleoperation of an automated bulldozer. The overall framework includes anterior‐time DT, real‐time DT, and posterior‐time DT, which integrates three‐dimensional modeling, edge detection, and blade trajectory algorithms. Multidimensional heterogeneous data in bulldozer teleoperation can be displayed in real‐time to ensure construction safety. Big data during teleoperation of the construction process can be collected, stored, and analyzed. The DT proposed in this study was successfully applied in a major construction project in China, and testing results show its universality, robustness, and advanced performance. The key technologies proposed in this study can be applied to solve the common problems in the construction industry, which is promising for future intelligent construction.

show abstract

Deep learning technologies for shield tunneling: Challenges and opportunities

Cited by 21 publications

References 98 publications

Prediction of shield tunneling attitude: a hybrid deep learning approach considering feature temporal attention

Prediction of shield tunneling attitude: a hybrid deep learning approach considering feature temporal attention

Thermo–Solid Coupling Analysis of Bionic Piston for a Mud Pump in Tunnel Engineering

Earthwork digital twin for teleoperation of an automated bulldozer in edge dumping

Contact Info

Product

Resources

About