Affiliation:
1. School of Engineering, Deakin University, Waurn Ponds 3216, Victoria, Australia e-mail:
2. Faculty of Design and Creative Technologies, Auckland University of Technology, Auckland 1010, New Zealand e-mail:
Abstract
Additive manufacturing (AM), partly due to its compatibility with computer-aided design (CAD) and fabrication of intricate shapes, is an emerging production process. Postprocessing, such as machining, is particularly necessary for metal AM due to the lack of surface quality for as-built parts being a problem when using as a production process. In this paper, a predictive model for cutting forces has been developed by using artificial neural networks (ANNs). The effect of tool path and cutting condition, including cutting speed, feed rate, machining allowance, and scallop height, on the generated force during machining of spherical components such as prosthetic acetabular shell was investigated. Also, different annealing processes like stress relieving, mill annealing and β annealing have been carried out on the samples to better understand the effect of brittleness, strength, and hardness on machining. The results of this study showed that ANN can accurately apply to model cutting force when using ball nose cutters. Scallop height has the highest impact on cutting forces followed by spindle speed, finishing allowance, heat treatment/annealing temperature, tool path, and feed rate. The results illustrate that using linear tool path and increasing annealing temperature can result in lower cutting force. Higher cutting force was observed with greater scallop height and feed rate while for higher finishing allowance, cutting forces decreased. For spindle speed, the trend of cutting force was increasing up to a critical point and then decreasing due to thermal softening.
Subject
Industrial and Manufacturing Engineering,Computer Science Applications,Mechanical Engineering,Control and Systems Engineering
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献