P‐112: Analyzing Scrubber Failure Causes Using the CNN 1D Inception Module

Environmentally harmful gases generated during the OLED manufacturing process are burned by a scrubber and discharged as water‐soluble gases using a wet system. The gases are incompletely burned, causing residues to accumulate in the pipes and eventually clogging the pipes. It takes an average of 80 hours for the facility to be backed up, including identifying the condition of the facility, analyzing the cause, issuing the ‘work order’ for pipe cleaning, and restating the facility. And due to the analysis error, the pipe does not need to be cleaned, and the cleaning cost is wasted. In this study, the CNN 1Dinception module was used to automatically analyze the reason for the failure of the scrubber in real time. The developed AI model was applied to mass production and achieved an average accuracy of 99.4%. In particular, the “pipe clogging” mode was predicted with 100% accuracy.