首页>
外国专利>
Plasma Etching Process Monitoring Device Using Machine Learning Model For Multi-channel Optical Emission Spectroscopy Analysis And Plasma Etching Process Monotoring Method Using The Same
Plasma Etching Process Monitoring Device Using Machine Learning Model For Multi-channel Optical Emission Spectroscopy Analysis And Plasma Etching Process Monotoring Method Using The Same
Plasma etching process diagnosis apparatus using machine learning model for multi-channel optical spectrum analysis that can predict the optimal etching end point time by extracting features from the optical data structure and processing the features with a machine learning classifier, and plasma etching process diagnostic method using the same This is initiated. The processor of the plasma etching process diagnosis apparatus of the present invention includes: an optical data collection unit for collecting real-time measured data from an optical sensor and storing the data in a database; a data processing unit that separates the data of the data collection unit into training data and test data by performing feature extraction in the feature extraction unit; and a data analysis unit in which the training data is learned by the machine learning classifier, and the training data and the test data are composed of etch endpoint data and non-end point data, respectively. According to the present invention, an optimal etch endpoint time can be predicted by extracting features from an optical data structure observed in real time and processing the features with a machine learning classifier.
展开▼
