Multimode Process Monitoring Based on Switching Autoregressive Dynamic Latent Variable Model

Zhou, Le; Zheng, Jiaqi; Ge, Zhiqiang; Song, Zhihuan; Shan, Shengdao

doi:10.1109/tie.2018.2803727

Cited by 100 publications

(29 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, the data‐based process monitoring and fault detection methods have been well studied and widely applied in many areas . Traditional multivariate statistical process monitoring (MSPM) methods are almost always for uniformly sampled data, but actual industrial processes may not be able to collect variables data at a uniform sampling interval. A multi‐rate sampling system means that variables have multiple sampling rates.…”

Section: Introductionmentioning

confidence: 99%

Grouping multi‐rate sampling fault detection method for penicillin fermentation process

2020

Can J Chem Eng

View full text Add to dashboard Cite

For the multi-rate sampling problem of the penicillin fermentation process, some traditional methods cannot be solved due to the different lengths of samples. To solve this problem, a grouping multi-rate sampling fault detection method is proposed. The training sample set is divided into multiple groups according to different sampling rates of variables. Each group has the same sample length. We use the principle component analysis and k-nearest neighbour methods to build model for every group. Then the models of all groups are combined to determine the control limit. The PenSim2.0 software is used to generate a sample set of the penicillin fermentation process that contained multiple variables at different sampling rates. The simulation result shows the effectiveness of the proposed method. K E Y W O R D Sfault detection, group modelling, multi-rate sampling process, penicillin fermentation process

show abstract

Section: Introductionmentioning

confidence: 99%

Grouping multi‐rate sampling fault detection method for penicillin fermentation process

2020

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Another kind of approach is the thermographic data analysis method, which extracts the principal features from multiple thermal images and automatically recognize the defects using these features or loading matrixes. Recently, the data analysis and feature extraction technologies have been widely used in process modeling, monitoring, and optimization areas [12][13][14][15][16][17]. Utilizing their advantages, the main information can be maintained with few features and the minimum reconstruction errors [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Defect Detection in Composite Products Based on Sparse Moving Window Principal Component Thermography

Jie

Dai

Hou

et al. 2020

Advances in Polymer Technology

Self Cite

View full text Add to dashboard Cite

As a nondestructive testing (NDT) technology, pulsed thermography (PT) has been widely used in the defect detection of the composite products due to its efficiency and large detection range. To enhance the distinction between defective and defect-free region and eliminate the influence of the measurement noise and nonuniform background of the thermal image generated by PT, a number of thermographic data analysis approaches have been proposed. However, these traditional methods only consider the correlations among the pixel while leave the time series correlations unmodeled. In this paper, a sparse moving window principal component thermography (SMWPCT) method is proposed to incorporate several thermal images using the moving window strategy. Also, the sparse trick is used to provide clearer and more interpretable results because of the structure sparsity. The effectiveness of the method is verified by the defect detection experiment of carbon fiber-reinforced plastic specimens.

show abstract

“…Process complexity and high demands for process safety have driven the development of data-based process monitoring techniques, in particular, multivariate statistical process monitoring [1], [2]. Among them, the continuous latent variable (LV) models have been applied to fault detection for several decades [3]- [5]. These LV models are proved to be effective because they are able to decompose the observation space into the LV subspace and the residual subspace.…”

Section: Introductionmentioning

confidence: 99%

Systematic Development of a New Variational Autoencoder Model Based on Uncertain Data for Monitoring Nonlinear Processes

et al. 2019

Self Cite

View full text Add to dashboard Cite

Deep learning models have been applied to industrial process fault detection because of their ability to approximate the complex nonlinear behavior. They have been proven to outperform the shallow neural network models. However, there are no good guidelines on how to build these deep models. Therefore, a good deep model is often constructed through a trial-and-error exercise. It is not easy to interpret the model because of features that do not have any physical interpretation. In addition, latent variables (or features) in a deep model are not independent. This causes features to overlap with each other, resulting in challenges in evaluating distributions of features and designing suitable monitoring indices. Finally, typical deep learning models in process monitoring are used in a deterministic manner and do not automatically provide confidence levels for each decision. In this paper, a variational autoencoder is utilized to develop a framework for monitoring uncertain nonlinear processes. The learned latent variables are guaranteed to be independent (or orthogonal) of each other under a specific optimization objective with constraints. The proposed method provides the density estimates of latent variables and residuals instead of point estimates. The density functions are used to design appropriate indices for monitoring. A simulation example and an industrial paper machine example are presented to validate the effectiveness of the proposed method.

show abstract

Multimode Process Monitoring Based on Switching Autoregressive Dynamic Latent Variable Model

Cited by 100 publications

References 31 publications

Grouping multi‐rate sampling fault detection method for penicillin fermentation process

Grouping multi‐rate sampling fault detection method for penicillin fermentation process

Defect Detection in Composite Products Based on Sparse Moving Window Principal Component Thermography

Systematic Development of a New Variational Autoencoder Model Based on Uncertain Data for Monitoring Nonlinear Processes

Contact Info

Product

Resources

About