فهرست نشریات علمی دسترسی آزاد ایران

This research presents an intelligence-driven and multi-objective framework for forecasting and risk management in smart supply chains. In this framework, data from IoT sensors, digital twin models, and historical records are collected in the data layer and processed in the predictive analytics layer by machine learning models to predict demand, delay, and risk. Then, the multi-objective NSGA-II algorithm is used to balance the three main objectives (cost reduction, risk reduction, and delivery time improvement). The results show that the proposed framework is able to provide a set of Pareto solutions with a reasonable balance between economic and operational objectives. Pareto front analysis and trade-off relationships indicate the stability of the model against parameter fluctuations and its ability to support intelligent decision-making. Overall, the proposed model is an efficient tool for optimizing decisions in dynamic and uncertain supply chain environments.