Comparison of A Fuzzy Supply Chain Model with learning effect using Evolutionary Algorithms
AbstractDecision support systems in the field of supply chain management require novel approaches due to the uncertainties and dynamic environments. This study suggests a fuzzy supply chain model with learning effect that is enhanced by evolutionary algorithms in order to improve decision-making and increase flexibility. Fuzzy logic is integrated to capture uncertainty, while evolutionary algorithms and learning curves are used to handle the supply chain's dynamic character. To maximize the fuzzy model parameters and enable automatic adaptation and evolution over time, the evolutionary algorithm is presented. The model dynamically adapts to changing situations through the optimization process, which helps to promote more effective and flexible decision-making. In the dynamic landscape of supply chain management, the integration of evolutionary algorithms with fuzzy models and learning curves has shown promise in enhancing decision-making processes. This research investigates and compares the performance of three popular evolutionary algorithms-Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Genetic Algorithm (GA)-in optimizing a Fuzzy Supply Chain Model with Learning Effect. The objective is to determine which algorithm offers superior adaptability and efficiency for addressing uncertainties and dynamic learning environments.