A Crow Search Algorithm integrated with Lévy flight and dynamic awareness probability for optimized numerical control machining parameters

Abstract This paper proposes an efficient method for optimizing machining variables with numerical control (NC) achieved through an Enhanced Crow Search Algorithm (ECSA). In contemporary manufacturing, which relies on numerically controlled machining, the efficiency and accuracy of many processes, such as milling, drilling, and turning, heavily depend on the optimum settings for parameters. Traditional optimization methods often require revisions to account for the nonlinearities and multi-dimensional nature of these problems. Hence, it is proposed that the standard CSA should be improved with dynamic awareness probability and Levy flight mechanisms for better exploration and exploitation capabilities. This approach is applied to enhance the critical machining variables of the depth of cut, feed rate, and cutting speed during the roughing, semi-finishing, and finish milling of the SSCK80 machine tool. Thus, the results depicted very noticeable enhancements in this case study concerning surface roughness and improving the cutting performance and machining time compared to existing techniques. The results of this study provide an effective and efficient framework for parameter optimization, thus contributing to advancements in precision and energy-efficient manufacturing.