Application of cloud-based machine learning in cutting tool condition monitoring

Mijodrag Milošević; Dejan  Lukić; Gordana Ostojić; Milovan  Lazarević; Aco Antić

doi:10.24867/JPE-2022-01-020

Vol. 25 No. 1 (2022)

Original Research Article

Application of cloud-based machine learning in cutting tool condition monitoring

FULL TEXT ARTICLE (PDF)

Mijodrag Milošević,
Dejan Lukić,
Gordana Ostojić,
Milovan Lazarević,
Aco Antić

more info

Mijodrag Milošević University of Novi Sad, Faculty of Technical Sciences, Departman for Production Engineering, Trg Dositeja Obradovica 6, 21000 Novi Sad, Serbia

Dejan Lukić University of Novi Sad, Faculty of Technical Sciences, Departman for Production Engineering, Trg Dositeja Obradovica 6, 21000 Novi Sad, Serbia

Gordana Ostojić

Milovan Lazarević

Aco Antić

Published 2022-06-30

Keywords

Cloud manufacturing,
machine learning,
I 4.0,
smart maintenance,
condition monitoring

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

One of the primary technologies in the Industry 4.0 concept refers to Smart maintenance or predictive maintenance that includes continuous or periodic sensor monitoring of physical changes in the condition of manufacturing resources (Condition monitoring). In this way, production delays or failures are timely prevented or minimized. In this context, the paper present a developed cloud-based system for monitoring the condition of cutting tool wear by measuring vibration. This system applies a machine learning method that is integrated within the MS Azure cloud system. The verification was performed on the data of the calculated central moments during the turning process, for cutting tool inserts with different degrees of wear.

FULL TEXT ARTICLE (PDF)