Optimizing Complex Manufacturing System Performance and Profitability with Intelligent Metaheuristic Techniques

Over the past two decades, nature-inspired optimization algorithms have gained significant attention due to their flexibility and effectiveness in solving complex engineering problems. However, improving the reliability of intricate systems remains computationally challenging. These problems, often characterized by nonlinear programming structures, pose challenges in finding optimal solutions within reasonable time constraints. This study employs the Gray Wolf Optimizer (GWO), a recent nature-inspired metaheuristic algorithm modeled on the hunting behavior and social hierarchy of gray wolves, to address several complex reliability optimization problems. To evaluate its performance, the GWO is compared with three well-established metaheuristic algorithms: Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), and Grasshopper Optimization Algorithm (GOA). A new stochastic model of a fly ash brick manufacturing plant is developed to demonstrate the practical application of these algorithms. The primary objective of the study is to evaluate the plant’s availability using various nature-inspired computational techniques. The application of these algorithms provides valuable insights into estimating critical performance factors and optimizing overall system availability. The results highlight the robustness and adaptability of computational intelligence techniques in solving complex optimization challenges. Moreover, the findings have practical implications for the design, operation, and maintenance planning of fly ash brick manufacturing systems. The derived statistical outcomes serve as a useful reference for enhancing system reliability, stability, and overall plant performance.