Artifical intelligence inspired approach to numerically investigate chip morphology in machining AISI630

This study examines AISI630 steel to gain insight into the chip morphology. Chip morphology provides useful information about the plastic shear deformation involved in the machining process. The presented study aims to integrate the innovative artificial intelligence driven method to efficiently analyse the saw-tooth chip geometry. The paper used an artificial intelligence inspired algorithm based on the image processing of segmented chips that quantifies various output responses, including peak, valley, pitch, chip segmentation ratio, chip compression ratio, and shear angle. In order to generate chips related data, a finite element-based machining model was prepared for the stainless steel AISI630 workpiece. The performance of data collected using artificial intelligence (AI) inspired technique has been re-evaluated using manual image processing tool Image J software. The peaks and valleys of the chip’s morphology are used to calculate the chip segmentation ratio. The study showed valleys can introduce average percentage errors of 7.3%. The shear angle is computed using the chip compression ratio, with an average percentage error of 2.4%. In addition, pitch values obtained from chip morphology have a percentage error of 5.2%.