Online Process Monitoring Using Recursive Mutual Information-Based Variable Selection and Dissimilarity Analysis With No Prior Information

Zeng, Jing; Luo, Xiaoyi; Liang, Jun

doi:10.1109/access.2018.2873806

Cited by 5 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following prior knowledge, the component variables that are difficult to be measured online and the unchanged agitation speed are not considered in this study. The remaining 33 variables are described in Zeng et al (2018). A total of 960 samples are collected under normal state as training data.…”

Section: Te Processmentioning

confidence: 99%

Stacked sparse autoencoders that preserve the local and global feature structures for fault detection

Yin

Yan

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Although the model based on an autoencoder (AE) exhibits strong feature extraction capability without data labeling, such model is less likely to consider the structural distribution of the original data and the extracted feature is uninterpretable. In this study, a new stacked sparse AE (SSAE) based on the preservation of local and global feature structures is proposed for fault detection. Two additional loss terms are included in the loss function of SSAE to retain the local and global structures of the original data. The preservation of the local feature considers the nearest neighbor of data in space, while that of the global feature considers the variance information of data. The final feature is not only a deep representation of data, but it also retains structural information as much as possible. The proposed model demonstrates remarkable detection performance in case studies of a numerical process and the Tennessee Eastman process.

show abstract

Section: Te Processmentioning

confidence: 99%

Stacked sparse autoencoders that preserve the local and global feature structures for fault detection

Yin

Yan

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…The proposed method is specified on the TE process in this section. The TE process is a simulation of an actual chemical process and has been broadly applied to assess the validity of process monitoring methods. , The process includes 41 measured variables and 12 manipulated variables; we selected 33 variables that are commonly associated with process health as the monitored variables for following experiments . The TE data set provides normal data and 21 types of fault data for training and testing of models .…”

Section: Case Studymentioning

confidence: 99%

“…28,29 The process includes 41 measured variables and 12 manipulated variables; we selected 33 variables that are commonly associated with process health as the monitored variables for following experiments. 30 The TE data set provides normal data and 21 types of fault data for training and testing of models. 31 The training data set contained 960 normal samples under 48 h. In the testing data set, 21 types of faults were used, and 960 samples under 48 h were collected for each fault mode.…”

Section: Case Studymentioning

confidence: 99%

Mutual Information–Dynamic Stacked Sparse Autoencoders for Fault Detection

Yin

Yan

2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Data-based process monitoring is gaining increasing attention, especially deep learning modeling methods. Given that process data are inherently dynamic, the dynamic relationship of process data needs to be incorporated into the monitoring model. Measured variables have diverse characteristics; some variables have strong autocorrelation, but some have no or weak autocorrelation. Hence, a new nonlinear dynamic fault detection model based on mutual information (MI) and stacked sparse autoencoders (SSAE) was proposed. With input data taken as time series data, variables with a strong autocorrelation and their lag time of maximum autocorrelation were selected. Then, dynamic augmented data that contain the values of all measured variables at the current moment and the selected data were used as input of SSAE to extract features of cross-correlation and autocorrelation between variables. T 2 and Q statistical quantities were constructed to implement fault detection. The proposed MI−dynamic SSAE can not only automatically learn the key features of the present measurements but can also learn the latent information contained in the dynamic process data. Simulation studies on the Tennessee Eastman process were conducted to evaluate the performance of the proposed monitoring model.

show abstract

“…Shang et al proposed a new method to monitor the incipient fault by monitoring the statistical characteristics (mean, variance, skewness, kurtosis, etc) of the transformed component. Zeng et al proposed using recursive mutual information‐based variable selection and dissimilarity analysis with no prior information to monitor online process. Deng et al proposed a residual component weighting strategy by the mutual information between the sample weighted residual components and the original measured variables and built two monitoring statistics to detect the incipient faults.…”

Section: Introductionmentioning

confidence: 99%

A new incipient fault monitoring method based on modified principal component analysis

Yang

Wang

Liu

2019

Journal of Chemometrics

View full text Add to dashboard Cite

A novel multivariate statistical process monitoring (MSPM) method based on modified principal component analysis (PCA) is proposed to solve the low detection rate problem of incipient fault. In this modified PCA, on the basis of normal PCA model, the columns of loading matrix are reordered by mutual information between different statistic component matrices and training data. Then, instead of cumulative percent variance criterion, the principal component subspace is selected according to the largest mutual information. The selected PC subspace can maximally reflect fault characteristics into a new statistical index. Besides, a detection index based on the sliding average control chart statistic is proposed, which eliminates the effect of noise by proper averaging of the most recent samples, greatly improving the ability and accuracy of fault detection. The case study of a numerical simulation and Tennessee Eastman process shows that the proposed method can effectively detect incipient fault.

show abstract

Online Process Monitoring Using Recursive Mutual Information-Based Variable Selection and Dissimilarity Analysis With No Prior Information

Cited by 5 publications

References 29 publications

Stacked sparse autoencoders that preserve the local and global feature structures for fault detection

Stacked sparse autoencoders that preserve the local and global feature structures for fault detection

Mutual Information–Dynamic Stacked Sparse Autoencoders for Fault Detection

A new incipient fault monitoring method based on modified principal component analysis

Contact Info

Product

Resources

About