An Intelligent Fuzzy Fish Algorithm for Manufacturing Process Optimization Under Uncertainty

Manufacturing systems operate under significant uncertainty due to machine variability, human factors, and fluctuating operating conditions. Classical optimization techniques often struggle to address such imprecision effectively. This paper introduces a novel Fuzzy Fish Algorithm (FFA) that integrates fuzzy logic with swarm intelligence to solve multi-objective manufacturing optimization problems. The proposed method simultaneously minimizes production cost and defect rate while maximizing throughput. Fuzzy membership functions are employed to handle vagueness in manufacturing performance indicators, while fish-inspired collective behavior guides global search. Numerical experiments conducted in MATLAB demonstrate that the proposed FFA achieves superior convergence speed, solution quality, and robustness compared with Genetic Algorithm, Particle Swarm Optimization, and Ant Colony Optimization. The results confirm that FFA is a promising optimization framework for smart manufacturing and Industry 4.0 systems.