Nonlinear Real‐time Process Monitoring and Fault Diagnosis Based on Principal Component Analysis and Kernel Fisher Discriminant Analysis

Abstract

The aim of this paper is to propose a novel real-time process monitoring and fault diagnosis method based on the principal component analysis (PCA) and kernel Fisher discriminant analysis (KFDA). There is a need to develop this method in order to overcome the inherent limitations of the current kernel FDA method. The idea of the method is to initially reduce dimensionality using PCA and then to map the score data in the reduced original space to the high-dimensional feature space via a nonlinear kernel function. Following this, the optimal Fisher feature vector and discriminant vector are extracted to perform process monitoring. If faults occur, the method uses the degree of similarity between the optimal discriminant vector presented and the optimal discriminant vector of the faults in the historical dataset to perform a diagnosis. The proposed method can effectively capture nonlinear relationships in process variables. In comparison with kernel FDA, the PCA plus kernel FDA method is more efficient and has a more rapid response when used to undertake online monitoring and fault diagnosis. In this study, the method is evaluated by applying it to the fluid catalytic cracking unit (FCCU) process. As a consequence, its effectiveness is demonstrated.

A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes

“…A nonlinear real‐time process monitoring and FDD method for a fluid catalytic cracking unit (FCCU) process have also been proposed by Zhang et al. 147.…”

Application of Machine Learning in Industrial Boilers: Fault Detection, Diagnosis, and Prognosis

“…As one of the earliest and most well-established methods, PCA is known as a multivariate statistical method that has been successfully applied in fault detection and diagnosis of various chemical processes [56][57][58]. Generally, PCA-based diagnosis method requires a series of decision functions, which could be created by the comparison of reference model and actual process to reflect the health state of the system [59,60].…”

Optimization of time‐variable‐parameter model for data‐based soft sensor of industrial debutanizer

“…The statistical methods or soft computing have been applied in different data‐based soft sensors. The most popular of them are multivariate statistical regression techniques include multiple linear regressions (MLRs), partial least squares (PLS), principal component analysis (PCA) model, genetic fuzzy model, support vector machine method, artificial neural networks (ANN), a combination with PCA model and ANN, a PLS‐radial basis function neural network–based model, and a combination with linear regressions (LRs) model and ANN . The data‐based model has gained the reputation by extending the availability of the recorded data in the process industries and computational power on it …”