An Autonomous Model to Classify Lathe's Cutting Tools Based on TSFRESH, Self-Organised Direction Aware Data Partitioning Algorithm and Machine Learning Techniques

Thiago E. Fernandes; Guilherme  P. C. de Miranda; Alexandre  F. Dutra; Matheus  A. M. Ferreira; Matheus P. Antunes; Marcos  V. G. R. da Silva; Eduardo  P. de Aguiar

doi:10.48011/asba.v2i1.1092

Thiago E. Fernandes Federal University de Juiz de Fora
Guilherme P. C. de Miranda Federal University de Juiz de Fora
Alexandre F. Dutra Federal University de Juiz de Fora
Matheus A. M. Ferreira Federal University de Juiz de Fora
Matheus P. Antunes Federal University de Juiz de Fora
Marcos V. G. R. da Silva Federal University de Juiz de Fora
Eduardo P. de Aguiar Federal University de Juiz de Fora

DOI: https://doi.org/10.48011/asba.v2i1.1092

Keywords: Autonomous learning, Empirical data analyses, Machine learning, Machining processes

Abstract

The machining processes are of major importance to industries, due to the fact that these processes take part in the manufacturing of a substantial portion of mechanical components. Hence, during these processes, operational interruptions and accidents induced by fault occurrence are likely to cause economic losses. Concerning these consequences, real-time monitoring can result in productivity and safety increase along with cost reduction. This paper aims to discuss an autonomous model based on self-organised direction aware data partitioning algorithm and machine learning techniques, including features extraction and selection based on hypothesis tests, to solve the adressed problem. The model proposed in this work was evaluated using a data set acquired in a real machining system at the Manufacturing Processes Laboratory of Federal University of Juiz de Fora (UFJF).