Surface defect detection and prediction in carbide cutting tools treated by lasers

Laser surface engineering of cutting tools is used to improve the performance processes via altering material interaction between tool and workpiece. processing applied cemented carbide can induce various thermal mechanical defects including porosity, splatter, cracks, balling, spherical pores, voids, dissociation. Those could be detrimental integrity tool, therefore parametric optimization crucial limit control possible post-processing defects. This study aimed identify classify in post laser processed carbides better understand relationship parameters resultant integrity. A region convolutional neural network (R-CNN) was trained for identification classification these using scanning electron microscopy images (SEM) as inputs. The R-CNN provided a quantitative analysis each defect with an average accuracy 91%. Using data from matched parameters, back propagation (BPNN) act predictive network. predicts number proportion when grain size, roughness are entered. this 96.6%. effect individual on estimated by method, enabling tools. For first time predict based tool’s