Surface roughness is a critical parameter in machining, as it affects the corrosion resistance and fatigue properties of the finished workpiece. For difficult-to-machine materials such as Inconel-625, ensuring desired levels of surface roughness is even more challenging. Accurate surface roughness estimation for such expensive alloys can help in reducing material wastage and enhancing machining efficiency. In this paper, machining data collected during the turning of a particularly difficult-to-machine alloy, Inconel-625, is presented. Inconel is widely used in aerospace applications and is difficult to machine, as unlike other materials, Inconel does not get softer with increasing temperature. This dataset comprises twenty-seven sets of vibration data collected using a triaxial accelerometer and corresponding force and moment data collected using a dynamometer, resulting in 382,189,197 samples in total, acquired during the dry turning of Inconel-625 on a Kirloskar Turnmaster 40 Lathe. A Mitutoyo Surface Roughness Tester was used to measure the surface roughness after each turning operation. This publicly available dataset will be of help to the scientific community in developing machine learning/deep learning based on-line surface roughness estimation models for turning processes.
Sakthivel et al. (Tue,) studied this question.