.png){kind=icon}
.png){kind=icon}
Return
Machine learning-based multi-objective prestress optimization framework of suspend dome structure and case study
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engstruct.2024.118987.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Intelligent optimization algorithms are widely employed for the prestress optimization of suspend domes to determine the optimal cable forces. This process involves numerous complex iterative calculations, with each iteration including a corresponding finite element analysis. Such a process is both cumbersome and time-consuming. In this study, a machine learning-based surrogate model integrated with an intelligent optimization algorithm was developed to address the prestress optimization problem in suspend domes. This optimization problem incorporates multiple objective constraints, including maximum vertical displacement, maximum lateral displacement of the support, uniformity of the cable force, and maximum cable force value. The efficiency and effectiveness of the proposed method were demonstrated through two case studies. Results show that the proposed method reduced computational time by 95 % and ensured convergence by effectively integrating the surrogate model with a multi-objective optimization strategy.
Keywords:
Suspend dome
Machine learning
Multi-objective
Prestress optimization
Surrogate model
Journal
IF:
6.4
Papers:
2.1W
Citations:
8.7W