Defect Detection of Scroll Fixed Using AI Machine Vision Inspection

This study was conducted to improve the process quality and productivity of the scroll compressor fixed parts for high-efficiency air conditioners. We have developed a defect detection technique for scroll fixed components through vision inspection due to lack of manpower when a defect occurs in the processing process and a long time to analyze the cause of the defect. In general, conventional vision inspection has low detection capability when there are various defect items such as complex shapes, defect types, sizes, and locations. However, in this study, we developed improvement measures for process defects through the application of AI algorithms with a machine vision inspection automation system. The model was classified and designed to facilitate AI learning by classifying images by standard based on scroll fixed component images collected with vision in the field, and setting brightness and regions of interest. Defect detection of fixed scroll components was determined by applying a CNN deep learning algorithm by increasing the amount of data using data augmentation techniques.