Using automation and machine learning to maximize tool use in turning centers for better surface finish

Abstract

In modern manufacturing industries, automated machining systems have become a necessity. However, optimizing resource utilization and achieving a good surface finish remain challenging tasks. Excessive tool usage and poor surface finish are common problems encountered in turning centers, which affect productivity and product quality. In this research, we propose an approach that leverages automation and machine learning techniques to maximize tool use and improve surface finish. Our objective is to investigate the relationship between tool life and surface roughness and to develop a method that can optimize cutting parameters for turning centers. We have conducted an experimental study to evaluate the proposed approach, which involves the automatic determination of cutting parameters based on machine learning algorithms, and concluded a cutting speed of 43.10[Formula: see text]m/min, the surface finish achieved for aluminum material was 1.98[Formula: see text][Formula: see text]m. In the case of mild steel material, the surface finish was 12[Formula: see text][Formula: see text]m at a cutting speed of 25.13[Formula: see text]m/min. Similarly, for cast iron material, the surface finish was 8.45[Formula: see text][Formula: see text]m at a cutting speed of 30.16[Formula: see text]m/min. Our results show that the proposed method outperforms the traditional manual method in terms of surface finish, tool usage, and machining time. Our approach can be applied to other machining systems, providing a practical and effective solution to improve the efficiency and quality of machining processes. This paper presents an experiment that explores the relationship between tool life and surface roughness. Furthermore, an automated approach is proposed for eliminating G code in machining, which can improve the efficiency of machine tools and result in a better surface finish. Objective: To maximize tool use and improve surface finish in turning centers by incorporating automation and machine learning. Idea: This research aims to explore the use of automation and machine learning in turning centers to optimize the cutting parameters and achieve a better surface finish. Description of the idea: The study was conducted by performing experiments on three different materials, i.e., aluminum, mild steel, and cast iron. The cutting parameters, including spindle speed, feed, and depth of cut, were controlled by a programmable logic controller (PLC) integrated with a tachometer and Vernier scale. The surface finish was measured using a surface roughness tester, and the data was analyzed using a supervised machine learning algorithm.