Modeling of Machining Force in Hard Turning Process

In this work, we develop a modeling based on an Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) to predict the machining force components generated during hard turning of a bearing steel with CBN cutting tool. The inputs of the ANN model were the cutting parameters (cutting spee...

Full description

Saved in:
Bibliographic Details
Published inMechanika (Kaunas, Lithuania : 1995) Vol. 24; no. 3; p. 367
Main Authors Makhfi, Souad, Haddouche, Kamel, Bourdim, Abdelghafour, Habak, Malek
Format Journal Article
LanguageEnglish
Published Kaunas Kauno Technologijos Universitetas 01.05.2018
Kaunas University of Technology
Subjects
Analysis
Artificial neural networks
Back propagation algorithms
Back propagation networks
Bayesian analysis
Bearing steels
Computer simulation
Cutting parameters
Cutting speed
Cutting tools
Engineering Sciences
Machining
Mathematical models
Modelling
Neural networks
Regression analysis
Regularization
Structural steels
Tool steels
Training
Turning
Turning (machining)
United States
Online AccessGet full text

Cover

More Information
Summary:In this work, we develop a modeling based on an Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) to predict the machining force components generated during hard turning of a bearing steel with CBN cutting tool. The inputs of the ANN model were the cutting parameters (cutting speed, feed and depth-of-cut) and the workpiece hardness. The network training is performed by using experimental data. The optimal network architecture is determined after several simulations by Matlab Neural Network Toolbox. Back-propagation by Bayesian Regularization in combination with Levenberg– Marquardt algorithm is employed for training. The ANN approach is suitable to estimate the machining force components such as feed-force, radial-force and tangentialforce; for this purpose, the results are compared to those obtained by experiment, and the maximum average MAPE value of 4.58% was obtained for the machining force prediction. Also, the ANN results were compared to those obtained by MLR model. It was shown that the ANN model produced more successful results.
ISSN:1392-1207
2029-6983
DOI:10.5755/j01.mech.24.3.19146