A new intelligent approach of surface roughness measurement in sustainable machining of AM-316L stainless steel with deep learning models

Abstract

Due to the manufacturing sector's digitalization and ability to combine quality measurement and production data, machine learning and deep learning for quality assurance hold enormous potential. In this situation, industries may process data to inform data-driven estimates of product quality, thanks to predictive excellence. This research investigates the machinability of Laser Powder Bed Fusion (LPBF) − 316L stainless steel specimens, focusing on the impact of cutting parameters and cooling conditions (Dry, MQL, CO2 and CO2 + MQL) on surface roughness. The research employs advanced data augmentation techniques, incorporating TransGAN and multi-head attention (MHA) based Alexnet model for surface imperfection classification. The results highlight the effectiveness of the proposed methodology in accurately classifying surface conditions and underscore the superior performance of the MHA-Alexnet algorithm compared to alternative models (Alexnet and AE-Alexnet). Overall, the study contributes valuable insights into optimizing machining parameters and cooling strategies for enhanced surface finish in additively manufactured alloys.