Dynamic concurrent kernel CCA for strip-thickness relevant fault diagnosis of continuous annealing processes

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

“…This is because both approaches entail differentiating the statistical index, which is difficult if the chain involves a kernel function [86]. Nevertheless, many researchers have derived analytical expressions for either kernel contributions-based diagnosis [66,79,81,83,87,94,119,127,133,136,146,150,156,157,162,164,194,213,241,268,275,276,278,279,288,289,293] or kernel reconstructions-based diagnosis [86,117,140,155,161,163,176,217,236,254,265,285]. However, most derivations are applicable only when the kernel function is the RBF, Equation (5).…”

“…In 2017, Zhu et al [240] first proposed the kernel concurrent CCA for quality-relevant monitoring. Liu et al [241] followed with its dynamic version. In a very recent work by Yu et al [277], a faster version of kernel CCA was proposed, to be discussed later in Section 4.8.…”

“…Multi-block kernel ICA was proposed by Zhang and Ma [133] to monitor the CAP case study as well. Enhanced results for the CAP was achieved by Liu et al [241] by using dynamic concurrent kernel CCA with multi-block analysis for fault isolation. Peng et al [283] also used a prior process knowledge of the TEP to partition the 33 process variables into 3 sub-blocks, each monitored by adaptive dynamic kernel ICA.…”

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

“…Ever since Schölkopf et al (1998) laid the foundations of kernel PCA, several other kernel MSPM methods have been reported in the literature. Recent works include the kernel dynamic PCA by Fezai et al (2018) and Jaffel et al (2016), the enhanced kernel PCA by Nguyen and Golinval (2010), the kernel PLS based generalized likelihood ratio test by Botre et al (2016), the kernel dynamic ICA by Fan and Wang (2014), the weighted kernel ICA for non-Gaussian data by Cai et al (2017), the kernel CVA by Samuel and Cao (2015), and the dynamic concurrent kernel CCA by Liu et al (2018a). Fault diagnosis using kernels applied to support vector machines (SVM) was also explored in numerous works, as surveyed by Yin and Hou (2016).…”

“…The most widely used kernel function in these studies, e.g. Cheng et al (2010); Nguyen and Golinval (2010); Fan and Wang (2014); Samuel and Cao (2015); Bernal-de Lázaro et al 2016; Liu et al (2018a), is the Gaussian radial basis function, which we refer to as the RBF kernel for the rest of this paper. Other choices include the polynomial and sigmoid kernels, to name a few.…”