Image processing algorithm for detection, quantification and classification of microdefects in wire electric discharge machined precision finish cut surfaces

This study aims to create an image processing algorithm that categorises the wire electric discharge machine (WEDM) processed finish cut surfaces, based on surface microdefects. The also detects defect locations and suggests alternate parameter settings for improving integrity. proposed automated analysis is more precise, efficient repeatable compared manual inspection. Also, method can be used automatic data generation suggest changes in closed loop systems. During training phase, mean, standard deviation area fraction of enhanced binary images are extracted stored. dataset consists 27 WEDM with labels, ‘coarse’, ‘average’ ‘smooth’. trained model capable categorising any machined by detecting If not classified as a smooth image, then input will suggested minimise done Euclidean distance between current datapoint nearest ‘smooth’ class datapoint.