Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

Abstract

Incipient fault monitoring is becoming very important in large industrial plants, as the early detection of incipient faults can help avoid major plant failures. Recently, Canonical Variate Dissimilarity Analysis (CVDA) has been shown to be an efficient technique for incipient fault detection, especially under dynamic process conditions. CVDA can be extended to nonlinear processes by introducing kernel-based learning. Incipient fault monitoring requires kernels with both good interpolation and extrapolation abilities. However, conventional single kernels only exhibit one ability or the other, but not both. To overcome this drawback, this study presents a Mixed Kernel CVDA method for incipient fault monitoring in nonlinear dynamic processes. Due to the use of mixed kernels, both enhanced detection sensitivity and a better depiction of the growing fault severity in the monitoring charts are achieved. Looking ahead, this work takes a step towards understanding the impact of kernel behavior in process monitoring performance.