Ejection pressure monitoring device and method, recording medium, and coating apparatus

By combining unsupervised learning and supervised learning methods, the abnormality and probability of the ejection pressure are calculated, and the problem of difficulty in detecting unknown abnormalities in the prior art is solved, and effective abnormality judgment and detection of ejection pressure is achieved.

CN119303808AActive Publication Date: 2025-01-14SCREEN HOLDINGS CO LTD
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202410905735.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-07-11
Filing Date
2024-07-08
Publication Date
2025-01-14
Estimated Expiration
2044-07-08

AI Technical Summary

Technical Problem

The existing ejection pressure monitoring technology is difficult to detect unknown abnormalities that are not expected in advance and cannot effectively deal with unknown abnormalities.

Method used

Using a method combining unsupervised learning and supervised learning, the abnormality of the ejection pressure is judged through pressure data acquisition, feature quantity calculation, abnormality calculation and abnormal probability calculation. The unsupervised learning model calculates the abnormality degree, the supervised learning model calculates the abnormality probability, and comprehensively judges the abnormality of the pressure data.

Benefits of technology

The detection ability of unknown abnormality can be improved by calculating the probability of abnormality in the case of pre-conceived abnormality, and appropriate detection by calculating the degree of abnormality in the case of unknown abnormality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119303808A_ABST
    Figure CN119303808A_ABST
Patent Text Reader

Abstract

The invention provides an ejection pressure monitoring device and method, a recording medium, and a coating apparatus, which can appropriately detect an unknown abnormality which is not assumed in advance for ejection pressure. A discharge pressure measurement unit (911) acquires pressure data. A feature amount calculation unit (913) calculates a feature amount of the pressure data. An abnormality degree calculation unit (915) uses an unsupervised learning model (M1) that outputs an abnormality degree indicating the degree of distribution of the feature amount that deviates from normal as an input, and calculates an abnormality degree for the feature amount calculated by the feature amount calculation unit. An abnormality probability calculation unit (917) uses a supervised learning model (M2) that outputs an abnormality probability indicating the probability of belonging to the specific abnormalities (A) and (B), using the feature amount as an input, and calculates an abnormality probability for the feature amount calculated by the feature amount calculation unit (913). An abnormality determination unit (919) determines an abnormality in the pressure data using the abnormality degree calculated by the abnormality degree calculation unit (915) and the abnormality probability calculated by the abnormality probability calculation unit.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • JP1978046643A

  • Chemicals supplying device

    JP1998061558A

  • Droplet injection device and display device manufacturing method

    JP2006026584A

  • Abnormality detection device, abnormality detection method, and abnormality detection program

    JP2012098133A

  • Anomaly prediction device, anomaly prediction system, anomaly prediction method, and anomaly prediction program

    JP2022125288A