A Framework for Implementing Industry 4.0 Technologies in Smart Manufacturing Environments

This study presents an Industry 4.0–oriented framework for optimizing smart manufacturing environments through the integration of machine learning, evolutionary computation, and cyber–physical systems (CPS). Using 1,510 operational observations collected from an industrial spray-drying process, the framework combines Random Forest Regression (RFR) for predictive modeling with a Genetic Algorithm (GA) for process optimization. The RFR model achieved strong predictive performance (R² = 0.9144), demonstrating its capability to capture nonlinear relationships among process variables. The GA exhibited stable convergence behaviour and achieved a 5.91% improvement in the optimized inlet temperature, alongside measurable gains in thermal efficiency (3.2%) and energy consumption (1.8%). Sensitivity analysis identified Time, Outside Temperature, Humidity, and Tower settings as the most influential variables affecting system performance. The results indicate that the integration of predictive modeling and evolutionary optimization can enhance decision support and operational efficiency within a CPS-based manufacturing environment. While the framework demonstrates promising performance within the studied process, its applicability to other industrial domains and real-time deployment requires further validation.