Neural Component Analysis for Fault Detection

Principal component analysis (PCA) is largely adopted for chemical process monitoring and numerous PCAbased systems have been developed to solve various fault detection and diagnosis problems. Since PCA-based methods assume that the monitored process is linear, nonlinear PCA models, such as autoencoder models and kernel principal component analysis (KPCA), has been proposed and applied to nonlinear process monitoring. However, KPCA-based methods need to perform eigen-decomposition (ED) on the kernel Gram matrix whose dimensions depend on the number of training data. Moreover, prefixed kernel parameters cannot be most effective for different faults which may need different parameters to maximize their respective detection performances. Autoencoder models lack the consideration of orthogonal constraints which is crucial for PCAbased algorithms. To address these problems, this paper proposes a novel nonlinear method, called neural component analysis (NCA), which intends to train a feedforward neural work with orthogonal constraints such as those used in PCA. NCA can adaptively learn its parameters through backpropagation and the dimensionality of the nonlinear features has no relationship with the number of training samples. Extensive experimental results on the Tennessee Eastman (TE) benchmark process show the superiority of NCA in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of NCA can be found in https://github.com/haitaozhao/Neural-Component-Analysis.git. Note to Practitioner: Online monitoring for chemical process has been considered as a critical and hard task in real industrial applications. In this paper, an innovative method called neural component analysis (NCA) is proposed for fault detection. NCA is a unified model including a nonlinear encoder and a linear decoder. Due to its simple and intuitive format, NCA has superior performance in both computational efficiency and fault detection which makes it suitable for process monitoring in real industrial applications. Moreover, the experimental results presented can be reproduced effortlessly.