As manufacturing processes become increasingly sophisticated, the abundance of real‐time multivariate data is also increasing. However, the vast majority of data in manufacturing is normal, and abnormal data is scarce, making it difficult to establish correlations between various data sets. While a model‐centric approach holds importance when applying AI in manufacturing, a data‐centric approach, based on domain knowledge of each process equipment, can yield better results. We refer to this approach as engineer's sense. We used the anomaly transformer as an anomaly detection model for time series data, and were able to improve performance through improvements with data centric. The study found that a focus on data‐centric improvement led to higher performance compared to model‐centric improvement. This method identified 88% higher anomaly F1 scores in the evaluation and is expected to be utilized on additional manufacturing equipment in the future. This will result in significant cost and time savings.
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.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)