Optimization of a self-tuning force control system for the milling process using a dynamic enhanced genetic algorithm

When milling structural components with varying axial depths and widths, cutting forces tend to fluctuate, negatively impacting tool life and machining accuracy. To mitigate the force fluctuations and enhance tool longevity, developing a simple, reliable, and easy-to-implement force control system for milling is essential, which is an important step toward advancing intelligent manufacturing. This paper explores the use of genetic algorithms ( GA ) for powerful optimization capabilities in developing self-tuning milling force controllers. A comprehensive framework for optimizing a fuzzy logic controller using an enhanced GA is specifically designed for the milling process. The optimization integrates the GA with a simulation model, fine-tuning membership functions and optimizing fuzzy rule selection. The enhanced GA incorporates the Integral of Time-weighted Absolute Error ( ITAE ) as the fitness criterion to improve the robustness and responsiveness of the controller. The optimized fuzzy logic controller is implemented within a computer numerical control system, adjusting feed rates in real-time to control milling forces. The performance of the proposed controller is validated through step and slope milling tests, demonstrating an average control accuracy of 95.52%. Comparative evaluations with other controllers show that the proposed system offers a significant improvement, achieving up to 4.58% better control accuracy in step milling tests.