Research Area:  Metaheuristic Computing
Machining parameter optimization can be an effective way to reduce the energy consumption of machining processes and contribute to sustainable manufacturing. In this paper, the energy-aware machining parameter optimization problem is described and formulated. Based on the description and formula, an approach which considers multiple machining parameters including spindle speed, feed rate, depth of cut and width of cut simultaneously is developed. This approach consists of two key steps: modelling the energy consumed in the machining process and searching for the optimal machining parameters. In the modelling step, a hybrid modelling method which integrates regression and artificial neural networks (ANN) is developed to characterize the relationship between energy consumption and the machining parameters and obtain the energy consumption prediction model. In the searching step, an improved flower pollination algorithm (FPA) is presented to achieve the further searching for the optimal machining parameters with energy consideration. The approach has been tested and validated on multiple groups of experimental data. The results demonstrate that the approach can lead to a more accurate energy consumption prediction and an optimal solution for machining parameters.
Keywords:  
Machining parameter optimization
machining process
description
formula
spindle speed
feed rate
depth of cut
energy consumption
Author(s) Name:  Jianxing Liu, Xiaoxia Li, Zhibo Sui
Journal name:  
Conferrence name:   2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Publisher name:  IEEE
DOI:  https://doi.org/10.1109/SMC52423.2021.9659139
Volume Information:  
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9659139