Prediction of Cutting Conditions in Turning AZ61 and Parameters Optimization Using Regression Analysis and Artificial Neural Network

Autor: Nabeel H. Alharthi, Sedat Bingol, Adel T. Abbas, Adham E. Ragab, Mohamed F. Aly, Hamad F. Alharbi
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Zdroj: Advances in Materials Science and Engineering, Vol 2018 (2018)
Druh dokumentu: article
ISSN: 1687-8434
1687-8442
DOI: 10.1155/2018/1825291
Popis: All manufacturing engineers are faced with a lot of difficulties and high expenses associated with grinding processes of AZ61. For that reason, manufacturing engineers waste a lot of time and effort trying to reach the required surface roughness values according to the design drawing during the turning process. In this paper, an artificial neural network (ANN) modeling is used to estimate and optimize the surface roughness (Ra) value in cutting conditions of AZ61 magnesium alloy. A number of ANN models were developed and evaluated to obtain the most successful one. In addition to ANN models, traditional regression analysis was also used to build a mathematical model representing the equation required to obtain the surface roughness. Predictions from the model were examined against experimental data and then compared to the ANN model predictions using different performance criteria such as the mean absolute error, mean square error, and coefficient of determination.
Databáze: Directory of Open Access Journals
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje