Abnormal data detection for industrial processes using adversarial autoencoders support vector data description

Qiu, Kepeng; Song, Weihong; Wang, Peng

doi:10.1088/1361-6501/ac4f02

Cited by 8 publications

(4 citation statements)

References 34 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many models achieved decent anomaly detection results by combining with VAE. For example, article [12] uses neural networks to transform the original data into the feature space and then applies Support Vector Data Description (SVDD) to classify the data. The stochastic process methods, represented by the Gaussian Process (GP), are probability-based non-parameter models which adequately deal with nonlinear and strongly coupled data analysis problems under supervised/semi-supervised conditions.…”

Section: Deep Learning Based Algorithmmentioning

confidence: 99%

Variational Auto Encoder fused with Gaussian Process for Unsupervised Anomaly Detection

Guan

2023

Preprint

View full text Add to dashboard Cite

The identification of abnormal data in high-dimensional and high-complexity situations is a challenging subject. In order to improve the accuracy of abnormal data detection, in this article, we first use Variational Auto Encoder (VAE) to extract the features of high-dimensional data to achieve the effect of data dimensionality reduction. Then the Gaussian process model is applied to establish the latent space's feature distribution field and guide the data's displacement in the latent space. The joint probability distribution matrix of the latent space data is adopted to establish the feedback channel between latent space data distribution and VAE data mapping. Finally, the characteristic distribution field of the Gaussian process model is fed back to the VAE to realize the separation of normal data and abnormal data at the data mapping level.

show abstract

Section: Deep Learning Based Algorithmmentioning

confidence: 99%

Variational Auto Encoder fused with Gaussian Process for Unsupervised Anomaly Detection

Guan

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The FBPC [33] is a procedure in which penicillin-producing bacteria carry out their vital metabolic activities under the appropriate fermentation conditions provided. The process flow chart is depicted in figure 13.…”

Section: Fed-batch Penicillin Cultivation Processmentioning

confidence: 99%

Semi-supervised Echo State Network with Partial Correlation Pruning for Time-Series Variables Prediction in Industrial Processes

Huang¹,

Wang²,

Yang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

For an ordinary echo state network (ESN), redundant information in the huge reservoir will lead to degradation of the prediction performance of the network, especially when the labels of the samples are limited. To solve this problem, a semi-supervised ESN with partial correlation pruning (PCP-S2ESN) is proposed in this paper to scientifically capture the essential association between two reservoir variables while controlling for the influence of other factors. In this way, redundant neurons and their connection weights in the reservoir are eliminated, so that the prediction accuracy is significantly enhanced by optimizing the network structure. Moreover, anunsupervised pre-training procedure is introduced to modify the input weight matrix and reservoir connection weight matrix of the ESN, which successfully achieves precise prediction of time-series variables with limited labels. The superiority of the PCP-S2ESN model is demonstrated through two benchmark prediction tasks and the fed-batch penicillin cultivation (FBPC) process.

show abstract

“…Due to various market demands, drifting disturbance and fluctuating system settings, industrial manufacturing processes are inevitably operated under different working conditions, which are called multimode processes [1,2]. In such processes, there are several stable working points with different statistical characteristics, hence their data do not obey Gaussian distributions, which is the premise of the traditional statistical process monitoring schemes [3].…”

Section: Introductionmentioning

confidence: 99%

Sparse representation and modified density peak clustering-based state identification for multimode processes

Wang¹,

Chen²,

Zheng³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Industrial processes with high dimensional data are generally operated with mixed normal/faulty states in different modes which are difficult to be automatically and accurately identified. In this paper, a state identification framework is proposed for multimode processes. First, a key variable selection approach is presented based on sparse representation to eliminate redundant variables. Then, the modified density peak clustering (MDPC) is proposed to identify different states, in which a distance measurement with a time factor is constructed to select out all the possible cluster centers; and the sum of squared error(SSE) based approach is developed to determine the optimal cluster centers automatically. Further, considering that the mode attributes may be mixed with the fault attributes, a two-step “coarse-to-fine identification” strategy is designed to precisely identify the mode and the faults in each mode. Finally, three cases including a numerical simulation, Tennessee Eastman (TE) benchmark process and an actual semiconductor manufacturing process are given to show the feasibility of the proposed method.

show abstract

Abnormal data detection for industrial processes using adversarial autoencoders support vector data description

Cited by 8 publications

References 34 publications

Variational Auto Encoder fused with Gaussian Process for Unsupervised Anomaly Detection

Variational Auto Encoder fused with Gaussian Process for Unsupervised Anomaly Detection

Semi-supervised Echo State Network with Partial Correlation Pruning for Time-Series Variables Prediction in Industrial Processes

Sparse representation and modified density peak clustering-based state identification for multimode processes

Contact Info

Product

Resources

About