Modeling and optimization of cutting force and surface roughness in the milling process of Inconel 738 by Neural Network and Genetic Algorithm

Imani, Lila; Rahmani Hanzaki, Ali; Hamzeloo, Seyed Reza; Davoodi, Behnam

Modeling and optimization of cutting force and surface roughness in the milling process of Inconel 738 by Neural Network and Genetic Algorithm

Document Type : Original Article

Authors

Lila Imani ¹

Ali Rahmani Hanzaki ²

Seyed Reza Hamzeloo ³

Behnam Davoodi ⁴

¹ Mechanical Engineering Department, Shahid Rajaee Teacher Training University, Tehran, Iran

² Mechanical Engineering, Assistant Professor, Shahid Rajaee Teacher Training University, Tehran, Iran

³ Mechanical Engineering, Assistant Professor, Shahid Rajaee Teacher Training University, Tehan, Iran

⁴ Associate Professor of Mechanical Engineering, Iran University of Science and Technology

Abstract

Milling is an important and conventional method of metal Cutting, in which many studies have been fulfilled so far. Study of machining the nickel-based superalloys is felt to be essential due to their high strength and various applications in the power plants, aerospace industries etc. Cutting force and surface roughness are two of the important factors in machinability that due to the high importance of it, has been studied. In this article, the influence of four parameters of machining nickel-based superalloys, namely, cutting speed, feed rate, depth of cut and presence or absence of cooling as research inputs on the milling of Inconel 738 were investigated. In total, 64 experiments have been completed as full factorial design. By measuring cutting forces and surface roughness of the samples after the milling process, the obtained models were utilized to predict the effect of various above parameters, to optimize the milling parameters and to obtain the desired surface finish. In addition, the artificial intelligence techniques such as neural network and genetic algorithm were employed to predict the output parameter and to find the optimum milling parameters. The comparison of the experimental and predicted results shows the success of the modeling with 97 percent accuracy and a precise optimization.

Keywords

Modeling and Optimization

Cutting force

Surface roughness

Inconel 738

Neural network

Subjects