Intelligent parameters reconfiguration system for enhancing machine tools sustainability using real-time data-driven: an experimental cutting speed investigation

Industrial manufacturing is not trivial and complex since there are dimensional and tolerance product changes, differences in raw material and variations in machine models. Hence, this research proposes an Intelligent Parameters Reconfiguration System (IPRS) approach for enhancing manufacturing performance and extending cutting tool lifespan through detailed machining parameter setup. The approach joins real-time data acquisition and cutting-edge machine learning techniques to improve the turning machining setup. This research uses related works to conceptualise the IPRS structure in four main steps: machining sensing, data acquisition, data processing and parameters prediction, and automatic machine reconfiguration. The approach enabled dynamic adjustments in cutting speed based on predicted wear, resulting in a notable reduction of 5.6 minutes in manufacturing time and an improvement of 0.2 µm in surface finish. However, it is important to highlight that the experimental solution evaluation was carried out in a controlled scenario using a potentiometer to control the cutting speed on CNC lathes. Therefore, the applicability and scalability of the solution in a real scenario have significant limitations, and the cutting speed control must have direct integration with the machine's numerical control. As future research, the IPRS approach should consider other influential parameters like cutting depth and feed rate.