A fuzzy–digital twin optimization framework for simultaneous management of waste and energy consumption in sustainable manufacturing
Hamed Nozari, Zornitsa Yordanova
Abstract
Sustainable manufacturing systems require intelligent methods to balance economic performance with environmental responsibility. This research presents a digital twin-fuzzy multi-objective optimization framework for simultaneously managing cost, energy consumption, and waste in sustainable manufacturing. In this framework, fuzzy logic is used to model data uncertainty, a digital twin is used to obtain real-time data from the manufacturing process, and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to generate a Pareto front and analyze the relationships between economic and environmental objectives. The proposed model was tested in 10 simulated scenarios based on digital twin data. The results showed that the proposed framework maintained the service level above 95%, reduced the total cost by 14% and the amount of waste by 18% compared to the baseline. Pareto front analysis also showed that although there is a relative conflict between economic and environmental objectives, this conflict is controllable. Also, sensitivity analysis revealed that energy ceiling and machinery efficiency have the greatest impact on the sustainability and profitability of the system. Overall, the proposed framework provides a reliable, quantitative decision-making tool for managers and policymakers on the path to green and sustainable production.