Abstract
The improvement of sensing technology enables the collection of multiple process variables during product fabrication. This paper introduces a feature ranking scheme based on sparse distance correlation (SpaDC) that promotes diversity and assesses general dependency between process features and the quality variable. Theoretical properties, simulation studies, and real-case applications in semiconductor manufacturing demonstrate the effectiveness of the SpaDC method.
Type
Publication
Technometrics
Motivation
Motivation: Monitor the process variables before measure the quality.
Formulation
Juan Du
Assistant Professor
My research interests include knowledge-infused data science for quality improvement, industrial data analytics and machine learning, and system informatics and control for manufacturing applications.