Statistical Process Monitoring of the Tennessee Eastman Process Using Parallel Autoassociative Neural Networks and a Large Dataset

Abstract

In this article, the statistical process monitoring problem of the Tennessee Eastman process is considered using deep learning techniques. This work is motivated by three limitations of the existing works for such problem. First, although deep learning has been used for process monitoring extensively, in the majority of the existing works, the neural networks were trained in a supervised manner assuming that the normal/fault labels were available. However, this is not always the case in real applications. Thus, in this work, autoassociative neural networks are used, which are trained in an unsupervised fashion. Another limitation is that the typical dataset used for the monitoring of the Tennessee Eastman process is comprised of just a small number of data samples, which can be highly limiting for deep learning. The dataset used in this work is 500-times larger than the typically-used dataset and is large enough for deep learning. Lastly, an alternative neural network architecture, which is called parallel autoassociative neural networks, is proposed to decouple the training of different principal components. The proposed architecture is expected to address the co-adaptation issue of the fully-connected autoassociative neural networks. An extensive case study is designed and performed to evaluate the effects of the following neural network settings: neural network size, type of regularization, training objective function, and training epoch. The results are compared with those obtained using linear principal component analysis, and the advantages and limitations of the parallel autoassociative neural networks are illustrated.

A Direct Transfer Entropy-Based Multiblock Bayesian Network for Root Cause Diagnosis of Process Faults

“…The TEP is an industrial benchmark chemical process, and it has been extensively utilized in numerous fields such as fault diagnosis, process control, and optimization. − The simulated process model and control structure for the TEP, developed by refs and and downloaded from , are used to perform the simulation of process faults in this work. The process flow diagram of the TEP is presented in Figure .…”

Accuracy Is Not Enough: Optimizing for a Fault Detection Delay

“…Our decision to utilize the Tennessee Eastman Process dataset in our study is based on several factors. First, TEP has been widely adopted by many researchers, as evident from the works of Heo et al [36,37], Sun et al [38], and Park et al [39]. Second, the published papers we reviewed did not adequately address or fulfill the specific objectives of our research.…”

A Hybrid Deep Learning-Based Unsupervised Anomaly Detection in High Dimensional Data

“…We describe two alternative objective functions in this section: hierarchical error and denoising criterion. The authors in [60] proposed the concept of hierarchical error to establish a hierarchy (i.e., relative importance) amongst non-linear principal components Analysis (PCA), which is utilizing the reconstruction error as the objective function [61]. Thus, it demonstrated that maximization of the principal variable variance is equal to the residual variance minimization in linear PCA.…”

“…Figure 3: Different objective functions are depicted schematically: (a) Reconstruction error; (b) Hierarchical error; and (c) Denoising criterion[61] …”