Abstract
Hard turning has become an attractive alternative to the more time-consuming and costly grinding technique. Unfortunately, high-quality prediction of the surface roughness generated during hard turning is difficult due to the technical complexities involved. Hence, it is currently receiving much research attention. The objective of this paper is to survey the current state of the soft computing techniques for surface roughness prediction in hard turning. It focuses on three areas: data acquisition, feature selection, and prediction model of surface roughness. First, the characteristics of hard turning and surface roughness are introduced, and a framework of the soft computing techniques is presented. Then, the three key areas are surveyed thoroughly. Finally, the recommendations and challenges faced by industry and academia are discussed, and the conclusions are drawn.
Highlights
The current work presents a review of the soft computing techniques used for predicting surface roughness in hard turning processes
(1) Most data employed for surface roughness prediction in hard turning are static factors such as cutting parameters, tool geometry, and workpiece hardness
Dynamic signals picked up by sensors are employed to some extent, such as cutting vibrations, cutting forces, audible sounds, and cutting temperatures
Summary
Hessainia et al [53] employed tool vibration in the radial and tangential directions, and cutting parameters such as cutting speed, feed rate, and depth of cut as the main inputs for surface roughness prediction in the hard turning of 42CrMo4 hardened steel. He et al [52] used cutting parameters and cutting vibration signals to predict surface roughness based on a detailed analysis of the workpiece surface formation mechanism.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
