A digital twin-based neutrosophic multi-objective optimization model for smart supply chains in the food industry

This research proposes a Digital Twin-Based Neutrosophic Multi-objective Mathematical Model for smart supply chains in the food industry, aimed at optimizing total cost, service level, and environmental impact under uncertainty. The model incorporates digital twin technology for real-time monitoring and decision-making, while neutrosophic logic is used to handle uncertainty in key parameters such as demand, costs, and capacities. A hybrid Grey Wolf-Genetic Algorithm (GWGO) is developed to solve the model efficiently, leveraging the Grey Wolf Optimizer's exploration capability and the Genetic Algorithm's exploitation strength. Sensitivity and robustness analyses are conducted, revealing that demand significantly impacts total cost, and the model consistently performs well under varying uncertainty levels. This study provides valuable managerial insights for improving operational efficiency, sustainability, and decision-making in dynamic and complex supply chains. Future research directions include applying the model to other industries and integrating advanced predictive analytics.