Batch process monitoring based on WGNPE–GSVDD related and independent variables

Hui, Yongyong; Zhao, Xiaoqiang

doi:10.1016/j.cjche.2018.09.022

Cited by 8 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It may lose crucial features and reduce performance. With consideration of each data in data space, the simplest idea is to separate the variable into independent space and related space via mutual information (MI) [5,6,7] and establish a monitoring model in the two spaces [8]. Although multi-block methods ( i.e., multi-block PCA, multi-block PLS, localized Fisher discriminant analysis) can overcome this problem, multi-block may increase the work of establishing models [1].…”

Section: Introductionmentioning

confidence: 99%

Independent and Related Variable Fault Detection Based on Information Concentrated Variational Auto-encoder

Yang

Wang

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

With the rapid development of deep learning methods, the variational auto-encoder (VAE) has been utilized for nonlinear process monitoring. However, most VAE-based methods hardly consider the inner independent and related relationship of each variable. To overcome this problem, a novel VAE named independent and related variable information concentrated variational auto-encoder (IRVIC-VAE) is proposed. To concentrate the independent and related information, a loading weight matrix regularization based on the mutual information of variables with gaussian distribution is introduced so that the variables can separate into two subspaces that contain independent and related information in latent variables. The original data space decomposed via IRVIC-VAE is orthogonal and approximate to normal distribution. For process monitoring, the independent variable space and related variable space are combined to establish two statistics according to Kullback-Leibler divergence and 2-norm. Finally, the performance and effectiveness of IRVIC-VAE are testified by Tennessee Eastman (TE) process.

show abstract

Section: Introductionmentioning

confidence: 99%

Independent and Related Variable Fault Detection Based on Information Concentrated Variational Auto-encoder

Yang

Wang

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…However, a good dimensionality reduction algorithm should be able to extract comprehensive information of process data, because its feature extraction ability directly affects the process monitoring performance. Therefore, some dimensionality reduction algorithms focused on both global and local features have been proposed to improve the monitoring effects (Hui and Zhao, 2018a;Miao et al, 2015;Zhan et al, 2019;Zhang et al, 2011). However, these algorithms always assume that process data are independent of time and ignore the autocorrelation.…”

Section: Introductionmentioning

confidence: 99%

Batch process monitoring based on global enhanced multiple neighborhoods preserving embedding

Yao

Zhao

et al. 2021

Transactions of the Institute of Measurement and Control

Self Cite

View full text Add to dashboard Cite

Batch process generally has varying dynamic characteristic that causes low fault detection rate and high false alarm rate, and it is necessary and urgent to monitor batch process. This paper proposes a global enhanced multiple neighborhoods preserving embedding based fault detection strategy for dynamic batch process. Firstly, the angle neighbor is defined and selected to compensate for the insufficient expression for the spatial similarity of samples only by using the distance neighbor, and the time neighbor is introduced to describe the time correlations between samples. These three types of neighbors can fully characterize the similarity of the samples in time and space. Secondly, considering the minimum reconstruction error and the order information of three types of neighbors, an enhanced objective function is constructed to prevent the loss of order information when neighborhood preserving embedding (NPE) calculates the reconstruction weights. Furthermore, the enhanced objective function and a global objective function are organically combined to extract both global and local features, to describe process dynamics and visualize process data in a low-dimensional space. Finally, a monitoring index based on support vector data description is constructed to eliminate adverse effects of non-Gaussian data for monitoring performance. The advantages of the proposed method over principal component analysis, neighborhood preserving embedding, dynamic principal component analysis and time NPE are demonstrated by a numerical example and the penicillin fermentation process simulation.

show abstract

“…23,24 Therefore, to reveal the inherent properties of process data effectively, Tong and Yan 25 proposed a method that considered the global-local structures. Hui and Zhao 26 divided the batch process variables into related and independent variables and then used the corresponding method to realize process monitoring. Zhao and Tao 27 proposed a tensor global-local model in batch process monitoring.…”

Section: Introductionmentioning

confidence: 99%

Multiway dynamic nonlinear global neighborhood preserving embedding method for monitoring batch process

Hui

Zhao

2020

Measurement and Control

Self Cite

View full text Add to dashboard Cite

Aiming at the dynamic and nonlinear characteristics of batch process, a multiway dynamic nonlinear global neighborhood preserving embedding algorithm is proposed. For the nonlinear batch process monitoring, kernel mapping is widely used to eliminate nonlinearity by projecting the data into high-dimensional space, but the nonlinear relationships between batch process variables are limited by many physical constraints, and the infinite-order mapping is inefficient and redundant. Compared with the basic kernel mapping method which provides an infinite-order nonlinear mapping, the proposed method considers the dynamic and nonlinear characteristics with many physical constraints and preserves the global and local structures concurrently. First, the time-lagged window is used to remove the auto-correlation in time series of process variables. Second, a nonlinear method named constructive polynomial mapping is used to avoid unnecessary redundancy and reduce computational complexity. Third, the global neighborhood preserving embedding method is used to extract structures fully after the dynamic and nonlinear characteristics are processed. Finally, the effects of the proposed algorithm are demonstrated by a mathematical model and the penicillin fermentation process.

show abstract

Batch process monitoring based on WGNPE–GSVDD related and independent variables

Cited by 8 publications

References 32 publications

Independent and Related Variable Fault Detection Based on Information Concentrated Variational Auto-encoder

Independent and Related Variable Fault Detection Based on Information Concentrated Variational Auto-encoder

Batch process monitoring based on global enhanced multiple neighborhoods preserving embedding

Multiway dynamic nonlinear global neighborhood preserving embedding method for monitoring batch process

Contact Info

Product

Resources

About