An analytical comparison of meta-heuristic algorithms for cellular manufacturing optimization

The cellular manufacturing system is an approach based on the nature of group technology that can reduce overhead costs. These systems are designed to organize machine cells and components to reduce movement between cells and enhance the efficiency of machine usage in manufacturing environments. The purpose of this article is cellular manufacturing system optimization by comparison of meta-heuristic algorithms. This study is considered to be a mixed and applied methodology. In this way, firstly, are identified through the systematic content screening process, effective factors of cellular manufacturing system appraisal. Then through the two bases of the meta-heuristic algorithm is determined the difference between the function of the gray wolf optimizer algorithm in cellular manufacturing system appraisal from the particle swarm optimization algorithm. Despite extensive research on CMS, few studies have systematically compared meta-heuristic optimization algorithms in this context, leaving a gap in identifying the most effective methods for optimal system design. This study addresses this gap using a mixed-methods approach: first, eight key factors influencing CMS appraisal were identified through a systematic content screening process; then, the Gray Wolf Optimizer (GWO) and Particle Swarm Optimization (PSO) algorithms were implemented using Lingo software to evaluate their performance in Iran’s automotive industry. Results show that the GWO algorithm achieves higher accuracy in optimizing CMS configurations. This study contributes to theory and practice by integrating systematic content analysis with meta-heuristic algorithm comparison, providing insights for researchers and practitioners seeking to enhance sustainable manufacturing performance. • Identify key criteria for evaluating cellular manufacturing system performance. • Compare two meta-heuristic methods in manufacturing system optimization. • Use decision analytics to enhance manufacturing line planning. • Demonstrate superior accuracy of the gray wolf optimizer. • Recommend algorithm-driven strategies for resource efficiency.