Machine learning models for surface roughness monitoring in machining operations

Abstract

Machining manufacturing companies are faced with ever-increasing demands in terms of quality, product variability and cost reduction. To address these constraints, machining monitoring systems for surface integrity control are an expected solution. However, due to the harsh machining environment, the sensor options for monitoring are limited and, as a result, so is the direct information available. To address this limitation, in this work, machine learning based models are developed for continuous prediction of surface roughness in machining operations. The proposed models use as inputs cutting forces, temperature and vibration data acquired by robust sensors suitable for the machining environment.