Prediction of surface roughness and cutting forces using RSM, ANN, and NSGA-II in finish turning of AISI 4140 hardened steel with mixed ceramic tool

• Published in: International journal of advanced manufacturing technology Vol. 97; no. 5-8; pp. 1931 - 1949
• Main Authors: Meddour, Ikhlas, Yallese, Mohamed Athmane, Bensouilah, Hamza, Khellaf, Ahmed, Elbah, Mohamed
• Format: Journal Article
• Language: English
• Published: London Springer London 01.07.2018; Springer Nature B.V
• Subjects: Artificial neural networks; CAE) and Design; Ceramic tools; Chromium molybdenum steels; Classification; Computer-Aided Engineering (CAD; Cutting force; Cutting forces; Cutting parameters; Cutting speed; Engineering; Feed rate; Genetic algorithms; High strength steels; Industrial and Production Engineering; Mathematical models; Mechanical Engineering; Media Management; Multiple objective analysis; Neural networks; Nose; Optimization; Original Article; Response surface methodology; Sorting algorithms; Surface roughness; Tool steels; Topographic maps; Turning (machining); NSGA-II; ANN; AISI 4140 steel; Hard turning; Surface roughness; Multi-objective optimization; Cutting forces; RSM
• ISSN: 0268-3768; 1433-3015
• DOI: 10.1007/s00170-018-2026-6

This paper aims at modeling surface roughness and cutting force in finish turning of AISI 4140 hardened steel with mixed ceramic tool. For this purpose, an attempt is made to improve prediction by using Artificial Neural Networks (ANN) technique. The effects of the process inputs, namely cutting speed, depth of cut, feed rate, and tool nose radius on the output responses are evaluated using response surface methodology (RSM). Also, this paper provides a profound examination of the surface roughness through the bearing area curve analysis (BAC) of the three-dimensional topographic maps of the machined surfaces, where relevant criteria representing surface roughness are used. It was established that machining with larger nose radius and lower feed rate produces surfaces with better functional characteristics and that the undesired effect of feed rate can be reduced by increasing the cutting speed. Desirability function approach (DF) and the Non-dominated Sorting Genetic Algorithm (NSGA-II) coupled with ANN models are used to solve different multi-objective optimization problems. It is found that NSGA-II is more efficient than DF method and offers diverse sets of non-dominated solutions that satisfy the requirements of parts quality, productivity, and cutting force, which lead to better competitiveness. Furthermore, the NSGA-II coupled with ANN models allowed to predict minimal value of Ra much less than the values of the experimental data.