Maximizing Anomaly Detection Performance Using Latent Variable Models in Industrial Systems

In conventional process monitoring, a latent variable model (LVM) is first learned in offline training and the statistics related to extracted latent features and residuals are then used for online monitoring. However, such a practice ignores the dynamic interaction between modeling and monitoring, rendering useful online samples underexplored. This study proposes a novel LVMs-based monitoring framework that exploits the interaction using a weighting strategy and the maximum likelihood method to improve the monitoring performance with online information. The key idea is to integrate a weighting vector to components which contribute to the fault detection indices for more effective online fault information extraction. We use the maximum likelihood ratio to optimize the weighting vector and construct a new fault detection index accordingly. Case studies on a numerical example and a three-phase flow facility demonstrate the effectiveness of our approach. Note to Practitioners—A large number of anomaly detection methods in industrial systems has emerged in recent years. Latent variable models are the dominant branch of anomaly detection methods with substantial research and practice. However, fault detection performance is still unexpected especially for some minor faults that cause underwhelming fluctuation. Based on LVM models, we investigate the performance maximization method of industrial fault detection. The main mechanism is a weighting strategy that connects the normal data and the online sample to be monitored. We do not attach any additional conditions besides the existing requirements for LVM models. Also, it is the class of LVM methods that can be benefited from this novel strategy rather than a specific approach, which has been verified using principal component analysis and canonical correlation analysis. Moreover, the fault detection performance has boosted for all kinds of fault types. Notice we use general linear LVM models for deriving the methodology. Extension to nonlinear methods is still an open question for the sake of the introduced non-convex optimization.

I. Introduction

Data-driven process monitoring is gaining increasing attention, owing to the development of large-scale and complex modern industrial processes [1], [2], [3]. Operators can collect and store large amounts of data via the burgeoning distributed control system (DCS) to extract valuable features for distinguishing between normal and faulty status [4], [5]. Thus, data-driven process monitoring is more versatile and convenient for industrial processes,in contrast with the model-based counterpart that depends on accurate process mechanisms.