Fan Yang

TL;DR: The comparison of modeling results demonstrates that the deep learning technique is especially suitable for soft sensor modeling because of the following advantages over traditional methods.

Abstract: Latent variable (LV) models have been widely used in multivariate statistical process monitoring. However, whatever deviation from nominal operating condition is detected, an alarm is triggered based on classical monitoring methods. Therefore, they fail to distinguish real faults incurring dynamics anomalies from normal deviations in operating conditions. A new process monitoring strategy based on slow feature analysis (SFA) is proposed for the concurrent monitoring of operating point deviations and process dynamics anomalies. Slow features as LVs are developed to describe slowly varying dynamics, yielding improved physical interpretation. In addition to classical statistics for monitoring deviation from design conditions, two novel indices are proposed to detect anomalies in process dynamics through the slowness of LVs. The proposed approach can distinguish whether the changes in operating conditions are normal or real faults occur. Two case studies show the validity of the SFA-based process monitoring approach. © 2015 American Institute of Chemical Engineers AIChE J, 61: 3666–3682, 2015

TL;DR: Four main causes are identified as the culprits for alarm overloading, namely, chattering alarms due to noise and disturbance, alarm variables incorrectly configured, alarm design isolated from related variables, and abnormality propagation owing to physical connections.

TL;DR: A direct causality detection approach suitable for both linear and nonlinear connections is described, based on an extension of the transfer entropy approach, and a direct transfer entropy (DTE) concept is proposed to detect whether there is a direct information flow pathway from one variable to another.

TL;DR: The Gaussian kernel method is applied to generate pseudo continuous time series from the original binary alarm data to reduce the influence of missed, false, and chattering alarms.