Enhancing Quality of Multivariate Process Monitoring Based on Vine Copula and Active Learning Strategy

Abstract

This paper proposes a new process monitoring method based on vine copula and active learning strategy under a limited number of labeled samples. The proposed method uses active learning strategy and the generalized Bayesian inference-based probability (GBIP) index to choose samples that can provide the most significant information for the process monitoring model. An adaptive strategy is used to select the number of training samples in every active learning loop. Then, the vine copula-based dependence description (VCDD) is used to fulfill fault detection for complex chemical processes. The validity and effectiveness of the proposed approach are illustrated using a numerical example and the Tennessee Eastman (TE) benchmark process. The results show that the proposed method can maximize the process monitoring performance while minimizing the number of samples labeled.