A Novel Quality-Related Incipient Fault Detection Method Based on Canonical Variate Analysis and Kullback-Leibler Divergence for Large-Scale Industrial Processes

Quality-related fault detection is an effective way to ensure the stability of product quality and the safety of industrial processes. Quality abnormality is often caused by incipient faults, which propagate through the connectivity path among the equipment and subsystems, and eventually become significant faults that affect product quality and production efficiency. In this article, a quality-related incipient fault detection method for large-scale industrial process is proposed. First, a fault-relevant variable selection strategy based on Kullback-Leibler divergence (KLD) is proposed to obtain the optimal variable subsets of quality-related and quality-unrelated faults. Second, canonical variate analysis is applied to estimate the canonical variables from the collected processes data. Third, considering that KLD has a high sensitivity to incipient faults, it is used to quantify the dissimilarity between the distributions of canonical vectors before and after fault occurs. Finally, Bayesian inference is employed to fuse the detection results of all sub-blocks to get an intuitive global detection result. The advantages and validity of the proposed scheme are verified based on the Tennessee Eastman process.