Journal of Engineering Research and Reports

Modern product design requires a balanced optimization of cost, quality, and manufacturability to remain competitive in the era of Industry 4.0 and 5.0. Traditional optimization approaches are often unable to manage these conflicting objectives simultaneously. This study proposes an AI-based multi-objective optimization framework integrating machine learning models and evolutionary algorithms to enhance design decision-making. Pre-AI data (2020–2025) and post-AI data (2025–2030) were analyzed to evaluate practical improvements. Results show a 9.91% reduction in cost, 40.38% reduction in defect rate, and 18.37% improvement in manufacturability after AI implementation. To ensure the reliability of predictions, RMSE and R² metrics were calculated using Python-based evaluation tools. RMSE improved from 12.6 to 3.4, and R² increased from 0.68 to 0.94, confirming high predictive accuracy. The findings demonstrate that AI-driven multi-objective optimization significantly improves product quality, efficiency, and manufacturing feasibility. This research establishes a scalable and data-driven framework suitable for intelligent and sustainable product design in modern industrial environments.