A machine vision system for defect detection of a traveling grate conveyor

Abstract

A major goal of many manufactures is minimizing unscheduled downtime caused by equipment breakdown. To achieve this goal, an automatic defect detection system for the equipment can be employed. This paper presents a machine vision application for detecting defects in a traveling grate conveyor in pelletizing industry and similar industries. For this purpose, a video stream of the conveyor is captured by a camera and sent to a computer. In the computer, the image of each grate is extracted from the stream and then by processing its image over a sliding window, the damaged parts are detected. The detection rate of the proposed method is more than 98%.