Application of Particle Swarm Optimization and Bacterial Foraging Optimization in Parallel Assembly Sequence Planning: A Systematic Review

This systematic review explores the application of Particle Swarm Optimization (PSO), Bacterial Foraging Optimization (BFO), and their hybrid forms in Parallel Assembly Sequence Planning (PASP) across complex manufacturing sectors such as automotive, aerospace, and renewable energy. Traditional heuristic and exact methods often struggle with the dynamic and intricate nature of modern assembly processes. Advanced bio-inspired algorithms like PSO and BFO offer significant improvements in efficiency, accuracy, and scalability. A systematic search of databases including Engineering Village, Science Direct, and Web of Science (1995–2024) identified studies explicitly using PSO, BFO, or hybrids in PASP with performance metrics. The review highlights enhancements in convergence rates, assembly efficiency, and robustness achieved through these algorithms. Additionally, the integration of PSO and BFO with Industry 4.0 technologies, such as the Internet of Things (IoT) and Artificial Intelligence (AI), is discussed, emphasizing their potential to create intelligent, real-time adaptive PASP systems. The findings reveal that these advanced algorithms not only optimize assembly sequences but also reduce time and costs while improving product quality and flexibility. The review concludes with proposed future research directions, including real-time optimization methods and deeper integration with Industry 4.0 technologies, to address scalability and adaptability challenges in modern manufacturing environments.