A Covariate-Regulated Sparse Subspace Learning Model and Its Application to Process Monitoring and Fault Isolation

Abstract

Multivariate functional data are increasingly common in various applications. This paper introduces a covariate-regulated sparse subspace learning (CSSL) model to address the challenges of complex, time-varying cross-correlation in such data, with applications in process monitoring and fault isolation. The efficacy of the CSSL model is demonstrated through simulations and a case study using SCADA data from wind turbines.

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.