.png){kind=icon}
.png){kind=icon}
Return
An efficient self-adaptive planning algorithm for shield machine attitude and segment assembly considering machine–segment interaction
.png){kind=icon}
OA
AI
DOI：10.1016/j.jrmge.2025.09.015.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Both shield machine attitude and segment assembly play crucial roles in ensuring the construction quality of shield tunnels. This study proposes an efficient Self-Adaptive Planning Algorithm (SAPA) for shield machine attitude control and segment assembly, which jointly considers shield machine attitude planning and segment assembly point selection. A series of efficient three-dimensional (3D) computational methods is developed for multiple key indicators, including distance deviation, angular deviation, cylinder stroke difference, tail clearance, and stagger-jointed assembly. With the developed self-adaptive weighting method, SAPA achieves a balanced optimization of all indicators, ensuring compliance with all control criteria during shield tunneling. Importantly, SAPA fully accounts for the interaction between the shield machine and segments during shield advancement and segment assembly. A series of analyses reveals that SAPA significantly outperforms the traditional fixed-weight method, primarily due to the self-adaptive weighting method. Among the evaluated optimization algorithms, Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm demonstrates the best overall performance while satisfying engineering computational speed constraints. As the calculation interval increases, the overall performance of SAPA declines, while computational time decreases exponentially. A calculation interval of 0.1 m is recommended as it provides a favorable balance between accuracy and efficiency. Compared to the traditional trajectory correction method, SAPA enables fully autonomous trajectory correction with greater efficiency, effectively avoiding over-correction and reducing labor costs.
Keywords:
shield tunnel
shield machine attitude
segment assembly
self-adaptive
optimization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.2
Papers:
2.6K
Citations:
1.2W