An Algorithm for Optimizing the Process Parameters of the Spindle Process of Universal CNC Machine Tools Based on the Most Probable Explanation of Bayesian Networks

Abstract

As an essential component of a universal CNC machine tool, the spindle plays a critical role in determining the accuracy of machining parts. The three cutting process parameters (cutting speed, feed speed, and cutting depth) are the most important optimization input parameters for studying process optimization. Better processing quality is often achieved through their optimization. Therefore, it is necessary to study the three cutting process parameters of the CNC machine tool spindle. In this paper, we proposed an improved algorithm incorporated with the beetle antennae search algorithm for the most probable explanation in Bayesian networks to achieve optimization calculation of process parameters. This work focuses on building adaptive dynamic step parameters to improve detection behavior. The chaotic strategy is discretized and used to establish the dominant initial population during the population initialization. This article uses four standard network data sets to compare the time and fitness values based on the improved algorithm. The experimental results show that the proposed algorithm is superior in time and accuracy compared to similar algorithms. At the same time, an optimization example for the actual machining of a universal CNC machine tool spindle was provided. Through the optimization of this algorithm, the true machining quality was improved.