A Clustering-Based Whale Optimisation Algorithm for Multi-Objective Flexible Job Shop Problems

As the evolution of Industry 4.0 accelerates, the confluence of the Internet of Things (IoT) with intelligent systems amplifies the urgency to optimise problem-solving capability of pivotal industrial sectors including manufacturing, transportation, and energy management. Central to manufacturing sector is the Job Shop Scheduling Problem (JSP). Addressing JSP efficiently heralds significant gains in productivity and cost efficiency. While traditional optimisation algorithms, including nature-inspired meta-heuristics, have made significant progress, they often grapple with the complexities presented by real-world scheduling problems, such as Flexible JSP (FJSP) and multi-objective FJSP (MOFJSP). This research introduces the C-MOEWOA, a specialised clustering-based Whale Optimisation Algorithm for tackling MOFJSP. This model blends sub-population methods with core components of Differential Evolution (DE) to help enhance exploration and expedite convergence. Additionally, our integration of non-linear coefficient vectors with adaptive weights strikes a balance between exploration and exploitation, preventing stagnation at local optima.Benchmark evaluations using Kacem problem instances highlight C-MOEWOA's superiority compared to various well-known algorithms. For example, in Kacem 1 problem instances, our model notably minimised the makespan, surpassing several benchmark algorithms. Additionally, in Kacem 5, it achieved parallel optimal results for the total workload. These findings not only underscore the effectiveness of C-MOEWOA but also its versatility, positioning it as one of the leading contenders for solving the Multi-Objective Flexible Job Shop Problem (MOFJSP).