Development of a Laboratory Type Glass Anomaly Detection System

Abstract

This paper demonstrates the successful design and testing of a prototype glass anomaly detection system developed to improve quality control processes in insulating glass production. This prototype system has demonstrated consistent performance under different test conditions, offering high sensitivity, reliability, and fast scanning capabilities.
 Image processing algorithms and machine learning models were used to identify and locate defects on glass surfaces in the manufacturing process. The experiments show that this technology can provide significant advantages to the insulating glass manufacturing industry and prevent the production of defective products by reducing costs.
 This study aims to provide guidance to researchers and industry professionals aiming to improve quality control processes. It is also considered that this technology has the potential to be utilized in other industries. Therefore, this study may find a wider industrial application area in the future and has the potential to encourage similar projects.