No abstract

No abstract

No abstract

No abstract

The machining processes are of major importance to industries, due to the factthat these processes take part in the manufacturing of a substantial portion of mechanicalcomponents. 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 evaluatedusing a data set acquired in a real machining system at the Manufacturing Processes Laboratory of Federal University of Juiz de Fora (UFJF).