Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring

The traditional data-driven process monitoring methods may not be applicable for the system which has dynamic and multimode characteristics. In this paper, a novel scheme named modified t-distribution stochastic neighbor embedding using augmented Mahalanobis-distance for dynamic multimode chemical p...

Full description

Saved in:
Bibliographic Details
Main Authors: Haoyu Gu, Li Wang
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:International Journal of Chemical Engineering
Online Access:http://dx.doi.org/10.1155/2022/8460463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849470256258482176
author Haoyu Gu
Li Wang
author_facet Haoyu Gu
Li Wang
author_sort Haoyu Gu
collection DOAJ
description The traditional data-driven process monitoring methods may not be applicable for the system which has dynamic and multimode characteristics. In this paper, a novel scheme named modified t-distribution stochastic neighbor embedding using augmented Mahalanobis-distance for dynamic multimode chemical process monitoring (AKMD-t-SNE) is proposed to realize dynamic multimodal process monitoring. First, the augmented matrix strategy is utilized to ensure the sample contains the autocorrelation of the process. Moreover, AKMD-t-SNE method eliminates the scale and spatial distribution differences among multiple modes by calculating the kernel Mahalanobis distance between the samples to establish the global model. The features extracted via the proposed method are obviously non-Gaussian, and there will be a deviation in the construction of traditional statistics. Then, the support vector data description (SVDD) method is used to construct statistics to deal with this problem. In addition, a hybrid correlation coefficient method (HCC) is proposed to achieve fault isolation and improve the accuracy of isolation results. The advantages of the proposed scheme are illustrated by a numerical case and the Multimode Tennessee Eastman Process (MTEP) benchmark.
format Article
id doaj-art-d41756634c1147259a789e88bf02f9a1
institution Kabale University
issn 1687-8078
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series International Journal of Chemical Engineering
spelling doaj-art-d41756634c1147259a789e88bf02f9a12025-08-20T03:25:12ZengWileyInternational Journal of Chemical Engineering1687-80782022-01-01202210.1155/2022/8460463Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process MonitoringHaoyu Gu0Li Wang1School of Electrical and Electronic EngineeringSchool of Electrical and Electronic EngineeringThe traditional data-driven process monitoring methods may not be applicable for the system which has dynamic and multimode characteristics. In this paper, a novel scheme named modified t-distribution stochastic neighbor embedding using augmented Mahalanobis-distance for dynamic multimode chemical process monitoring (AKMD-t-SNE) is proposed to realize dynamic multimodal process monitoring. First, the augmented matrix strategy is utilized to ensure the sample contains the autocorrelation of the process. Moreover, AKMD-t-SNE method eliminates the scale and spatial distribution differences among multiple modes by calculating the kernel Mahalanobis distance between the samples to establish the global model. The features extracted via the proposed method are obviously non-Gaussian, and there will be a deviation in the construction of traditional statistics. Then, the support vector data description (SVDD) method is used to construct statistics to deal with this problem. In addition, a hybrid correlation coefficient method (HCC) is proposed to achieve fault isolation and improve the accuracy of isolation results. The advantages of the proposed scheme are illustrated by a numerical case and the Multimode Tennessee Eastman Process (MTEP) benchmark.http://dx.doi.org/10.1155/2022/8460463
spellingShingle Haoyu Gu
Li Wang
Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
International Journal of Chemical Engineering
title Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
title_full Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
title_fullStr Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
title_full_unstemmed Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
title_short Modified t-Distribution Stochastic Neighbor Embedding Using Augmented Kernel Mahalanobis-Distance for Dynamic Multimode Chemical Process Monitoring
title_sort modified t distribution stochastic neighbor embedding using augmented kernel mahalanobis distance for dynamic multimode chemical process monitoring
url http://dx.doi.org/10.1155/2022/8460463
work_keys_str_mv AT haoyugu modifiedtdistributionstochasticneighborembeddingusingaugmentedkernelmahalanobisdistancefordynamicmultimodechemicalprocessmonitoring
AT liwang modifiedtdistributionstochasticneighborembeddingusingaugmentedkernelmahalanobisdistancefordynamicmultimodechemicalprocessmonitoring