Machine vision based automated inspection approach for clutch friction disc (CFD)

Abstract

Machine vision is a technology and method used to provide automated image-driven analysis in applications such as inspection, process control, and guidance, and is very popular in industries nowadays. Computer/machine vision has been extensively developed and used in production to achieve precise automatic control. This paper presented an image processing approach, a subset of machine vision, for the visual inspection system of the Clutch Friction Disc (CFD) produced for 2 wheelers. Image processing is used to inspect different parts of the CFD. After previous operations of production, a part enters the inspection system, where the geometry and size of the part are inspected, and then image processing technology is used to decide to accept or reject the product. This paper presented the work constructed using a python program with OpenCV which aims to identify the major defects in clutch friction plates, by using different image processing techniques. With the proposed approach decision can be made automatically that whether the processed part will be accepted or rejected and then will be identified as “Ok tested” and “Faulty” pieces.