.png){kind=icon}
.png){kind=icon}
Return
Life-cycle-aware structural optimization of timber lattice shells using multi-task graph reinforcement learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.istruc.2026.112134.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel multi-task optimization framework is created for low-carbon timber lattice shells. • Structural and environmental objectives are optimized within a unified formulation. • Objective switching is enabled without predefined weighting or repeated optimization. • Large-scale lattice shells are optimized more efficiently than a genetic algorithm by 15–20%. • Optimization behavior depends on structural configuration and geometric constraints.
Keywords:
multi-task optimization
timber lattice shells
life-cycle awareness
structural optimization
graph reinforcement learning
Journal
IF:
4.3
Papers:
1.2W
Citations:
2.7W
