AI-Enabled Data-Driven Optimization of Manufacturing Operations and Supply Chain Systems

Modern manufacturing and supply chain systems face increasing complexity due to demand variability, operational uncertainty, and global disruptions. This study proposes an AI-enabled data-driven optimization framework to improve operational efficiency, decision-making, and supply chain resilience in Industry 4.0 environments. The framework integrates machine learning, Industrial Internet of Things (IIoT), predictive analytics, and optimization techniques within a unified architecture. Multi-source industrial data collected from ERP/MES systems and IoT sensors are processed using preprocessing and feature engineering techniques before applying AI models including LSTM, Random Forest, ANN, and SVM. The proposed system supports production scheduling, inventory optimization, logistics coordination, and real-time KPI monitoring. Experimental results demonstrate significant improvements in forecasting accuracy, production efficiency, equipment utilization, and supply chain performance, with LSTM achieving the highest prediction accuracy of 95.1%. The findings demonstrate that AIintegrated industrial systems significantly enhance operational intelligence, adaptability, and real-time decision support. The proposed framework provides a scalable and intelligent solution for smart manufacturing and supply chain optimization.