Pattern recognition in audible sound energy emissions of AISI 52100 hardened steel turning: a MFCC-based approach

The main objective in machining processes is to produce a high-quality surface finish which, however, can be measured only at the end of the machining cycle. A more preferable method would be to monitor the quality during the cycle, what result a real-time, low-cost, and accurate monitoring method that can dynamically adjust the machining parameters and keep the target surface finish. Motivated by this premise, results of investigation on the relationship between emitted sound signal and surface finish during turning process are reported in this paper. Through experiments with AISI 52100 hardened steel, this work shows that such a correlation does exist presenting strong evidences that Mel-Frequency Cepstral Coefficients, extracted from sound energy, can detect different surface roughness levels, what makes it a promising feature for real-time process quality monitoring methods.