Technical Name 先進製程控制之決策型虛擬量測大數據分析技術
Project Operator National TsingHua University
Project Host 簡禎富
This technology aims to automatically extractdefine features from a data-driven perspective through a series of data engineering, machine learningensemble learning technologies via the big data collected from equipment sensorsquality characteristic measurement results. For products that have no quality measurement, a virtual metrology resultpredicted confidence score are provided as a decision-making basis for process control.
Scientific Breakthrough
In the past, when using device sensing data for virtual metrology, it was necessary to incorporate domain knowledge to define key intervalsstatistics of the profile in advance for analysis. This technology integrates statistics, machine learning,decision analysis methods, automatically defines key intervalsconverts them into interpretable features, combines unsupervised clustering methods to reduce errors, constructs predictive models,calculates confidence scores for predicted values.
Industrial Applicability
This technology takes high-tech manufacturing as the priority to be introduced. According to the development status of other manufacturing industries, after completing the external sensor of the equipmentimproving the information system to link the production historyquality characteristics, it can be imported for application. Because this technology does not need to rely too much on domain knowledge,traditional industries can use this to gradually carry out digital transformationmaintain corporate competitiveness.
Matching Needs
Keyword Decision-based Virtual Metrology Intelligence Manufacturing Advanced Process Control Fault Detection and Classification Machine Learning Sensor Data Analytics Automatic Feature Engineering Ensemble Learning and Prediction Yield Enhancement High-tech Manufacturing
  • Contact
Other people also saw