Home > Published Issues > 2020 > Volume 9, No. 6, June 2020 >

Self-learning Optimization of Turning Process Parameters Based on NSGA-II and ANNs

Shenghao Shi, Hui Zhang, and Peng Mou
Department of Mechanical Engineering, Tsinghua University, Beijing, China

Abstract—This paper proposes an optimization method of turning process parameters based on nondominated sorting genetic algorithm II (NSGA-II) and artificial neural networks (ANNs). In the period of computer-aided process planning (CAPP), each machining operation with its process parameters should be given in sequence for the final output of workshop documentation and machining program. NSGA-II algorithm is used in the optimization of process parameters, including spindle speed, feed rate, depth of cut, etc. ANNs are used to predict the performance parameters, including cut force and surface roughness as constraints or objective of the optimization process. This process is a self-learning process because in the period of machining, data and signal from CNC is collected as training sample to iterate the artificial neural networks. 

Index Terms—CAM, CAPP, optimization, machine learning

Cite: Shenghao Shi, Hui Zhang, and Peng Mou, "Self-learning Optimization of Turning Process Parameters Based on NSGA-II and ANNs," International Journal of Mechanical Engineering and Robotics Research, Vol. 9, No. 6, pp. 841-846, June 2020. DOI: 10.18178/ijmerr.9.6.841-846

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.