Optimization of Casting Process Parameters Using Evolutionary Algorithms for Improved Material Quality

Abstract

The quality and performance of cast metal components are highly influenced by process parameters such as pouring temperature, mold design, cooling rate, and solidification conditions. Inadequate control of these parameters often leads to defects including porosity, shrinkage, cracks, and poor mechanical properties, affecting the reliability of engineering products. This study presents an optimization approach for casting process parameters using evolutionary algorithms to improve material quality, production efficiency, and defect minimization in metal casting operations. The proposed framework integrates computational modeling, statistical analysis, and intelligent optimization techniques to evaluate the influence of critical casting parameters on material performance and defect formation. A simulation-based methodology was implemented in which thermal behavior, fluid flow characteristics, solidification patterns, and microstructural evolution were analyzed under varying operational conditions. Evolutionary algorithms, including genetic algorithms and particle swarm optimization techniques, were employed to identify optimal process settings that maximize casting quality while minimizing material defects and production costs. Experimental and numerical results demonstrated significant improvements in dimensional accuracy, surface finish quality, mechanical strength, and defect reduction compared with conventional parameter selection methods. The optimized casting process also exhibited enhanced thermal stability, improved solidification uniformity, and reduced residual stress formation in fabricated components. Furthermore, the intelligent optimization framework enabled efficient process control and adaptive decision-making for complex casting environments. The study concludes that evolutionary algorithm-based optimization provides an effective and reliable solution for improving casting process performance and material quality in modern manufacturing industries. The findings contribute to the advancement of intelligent manufacturing systems through enhanced process optimization, defect prediction, and sustainable metal casting technologies for high-performance engineering applications.