Enhancing Facility Layout Optimization: A Performance Analysis of Genetic Algorithm Variants in Dynamic Facility Layout Problems

Facility Layout optimization is a crucial aspect of operations management, impacting efficiency, productivity, and overall operational costs. In dynamic environments, where layout adjustments are frequent due to changes in product demand, machinery breakdowns, or workforce variations, it becomes imperative to employ efficient optimization techniques. This research paper presents an investigation into the performance of various Genetic Algorithm (GA) variants to address the challenging Dynamic Facility Layout Problem. Three primary approaches for dynamic facility layout optimization have been examined: Genetic Algorithm (GA), GA with Local Search, and Machine Learning-Enhanced GA for robust layout design. The results show that the Machine Learning-Enhanced GA outperforms the traditional GA and Genetic Algorithm with Local Search in terms of both solution quality and adaptability to dynamic changes. This suggests that leveraging machine learning techniques can significantly enhance the effectiveness of Genetic Algorithms in addressing DFLP. © (2024), (International Association of Engineers). All rights reserved.