Computer Numerical Control CNC Machine Health Prediction using ‎Multi-domain Feature Extraction and Deep Neural Network Regression

Authors

Dina adel, Mohamed El-Barawany, Hamdy Elminir, Hatem Elattar, Ebrahim Abdel Hamid

Abstract

Tool wear monitoring has become more vital in intelligent production to enhance Computer Numerical Control CNC machine health state. Multidomain features may effectively define tool wear status and help tool wear prediction. Prognostics and health management (PHM) plays a vital role in condition-based maintenance (CBM) to prevent rather than detect malfunctions in machinery. This has great advantage of saving costs of fault repair including human effort, financial costs as long as power and energy consumption. The huge evolution of Industrial Internet of Things (IIOT) and industrial big data analytics has made Deep Learning a growing field of research. The PHM society has held many competitions including PHM10 concerning CNC milling machine cutters data for tool wear prediction The purpose of this paper is to predict tool wear of CNC cutters and. We adopted a multi-domain feature extraction method for health statement of the cutters. and a deep neural network DNN method for tool wear prediction.

Recommended Citation

adel, Mohamed El-Barawany, Hamdy Elminir, Hatem Elattar, Ebrahim Abdel Hamid, Dina (2022) "Computer Numerical Control CNC Machine Health Prediction using ‎Multi-domain Feature Extraction and Deep Neural Network Regression," Journal of Engineering Research: Vol. 6: Iss. 5, Article 3.
Available at: https://digitalcommons.aaru.edu.jo/erjeng/vol6/iss5/3