Key points are not available for this paper at this time.
Performance Evaluation of Genetic Algorithm and Particle Swarm Optimization in Off-Site Construction Scheduling Mizanoor Rahman, Sang Hyeok Han Pages 275-282 (2024 Proceedings of the 41st ISARC, Lille, France, ISBN 978-0-6458322-1-1, ISSN 2413-5844) Abstract: Off-site construction (OSC) is gaining significant attention due to its promising benefits, including reduced time, cost, and waste, along with improved quality, productivity, and safety. However, the dynamic nature of the production process (i.e., non-typical process time) introduces challenges in OSC production line, such as: (i) bottlenecks: (ii) workstation idle time; and (iii) identification of an optimal production sequence. To leverage the full benefits of OSC, a superior production planning and scheduling optimization method become imperative. Therefore, this paper aims to compare the computational performance of the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for optimizing OSC production schedule. The methodology consists of the three key steps, including: (i) data analysis; (ii) development of GA and PSO algorithms; (iii) implementation of both GA and PSO in a real-life wall panel production line in Edmonton, Canada. The results reveal that GA outperforms PSO in minimizing project completion time (PCT). Specifically, for 160 wall panels, the PCT using GA is 6112 min, whereas with PSO, it is 6122 min. Conversely, PSO produces results more quickly than GA. For the same set of 160 wall panels, the model runtime is 17.97 sec for GA and 6.0 sec for PSO. The findings of this study offer valuable insights for production managers in selecting the most effective algorithm for optimizing production schedules. Keywords: Off-site construction, Genetic algorithm, Particle swarm optimization, Manufacturing, Schedule DOI: https://doi.org/10.22260/ISARC2024/0037 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley Presentation Video: https://youtu.be/Hay7lPnRxfc?si=df0JwOXr7XIvu3ot
Rahman et al. (Mon,) studied this question.