A Machine Vision System for Gear Defect Detection

Abstract

This study introduces a machine vision system (MVS) developed for the inspection and removal of defective gears to enhance the efficiency of mass production processes. The system employs a rotary table that transports gears through the inspection stage at a controlled speed. Various defects, including missing teeth, surface irregularities, and dimensional deviations, are reliably identified through this method. Faulty gears are automatically separated from the production line using a pneumatic actuator. Experimental evaluations confirm the system’s high accuracy and consistency, with a defect detection standard deviation of less than 1%. This level of deviation corresponds to a defect detection accuracy exceeding 98%, with both precision and recall consistently surpassing 96%. By reducing manual intervention and accelerating quality control procedures, the proposed system contributes to improved production efficiency and product quality, offering a practical and effective solution for manufacturing environments.