Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes
Actual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of i...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/2/987 |
_version_ | 1797437175734730752 |
---|---|
author | Shu Wang Yicheng Wang Jiarong Tong Yuqing Chang |
author_facet | Shu Wang Yicheng Wang Jiarong Tong Yuqing Chang |
author_sort | Shu Wang |
collection | DOAJ |
description | Actual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of industrial data, challenges remain. Based on the concept of multimodal modeling, this paper proposes a multimodal process monitoring method based on the variable-length sliding window-mean augmented Dickey–Fuller (VLSW-MADF) test and dynamic locality-preserving principal component analysis (DLPPCA). In the offline stage, considering the fluctuation characteristics of data, the trend variables of data are extracted and input into VLSW-MADF for modal identification, and different modalities are modeled separately using DLPPCA. In the online monitoring phase, the previous moment’s historical modal information is fully utilized, and modal identification is performed only when necessary to reduce computational cost. Finally, the proposed method is validated to be accurate and effective for modal identification, modeling, and online monitoring of multimodal processes in TE simulation and actual plant data. The proposed method improves the fault detection rate of multimodal process fault monitoring by about 14% compared to the classical DPCA method. |
first_indexed | 2024-03-09T11:16:01Z |
format | Article |
id | doaj.art-84a158fb853f4fcd8f01a60a8d30e5d1 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T11:16:01Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-84a158fb853f4fcd8f01a60a8d30e5d12023-12-01T00:30:53ZengMDPI AGSensors1424-82202023-01-0123298710.3390/s23020987Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal ProcessesShu Wang0Yicheng Wang1Jiarong Tong2Yuqing Chang3College of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaActual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of industrial data, challenges remain. Based on the concept of multimodal modeling, this paper proposes a multimodal process monitoring method based on the variable-length sliding window-mean augmented Dickey–Fuller (VLSW-MADF) test and dynamic locality-preserving principal component analysis (DLPPCA). In the offline stage, considering the fluctuation characteristics of data, the trend variables of data are extracted and input into VLSW-MADF for modal identification, and different modalities are modeled separately using DLPPCA. In the online monitoring phase, the previous moment’s historical modal information is fully utilized, and modal identification is performed only when necessary to reduce computational cost. Finally, the proposed method is validated to be accurate and effective for modal identification, modeling, and online monitoring of multimodal processes in TE simulation and actual plant data. The proposed method improves the fault detection rate of multimodal process fault monitoring by about 14% compared to the classical DPCA method.https://www.mdpi.com/1424-8220/23/2/987multimode processmode identificationprocess monitoringstatistical modeling |
spellingShingle | Shu Wang Yicheng Wang Jiarong Tong Yuqing Chang Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes Sensors multimode process mode identification process monitoring statistical modeling |
title | Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes |
title_full | Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes |
title_fullStr | Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes |
title_full_unstemmed | Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes |
title_short | Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes |
title_sort | fault monitoring based on the vlsw madf test and dlppca for multimodal processes |
topic | multimode process mode identification process monitoring statistical modeling |
url | https://www.mdpi.com/1424-8220/23/2/987 |
work_keys_str_mv | AT shuwang faultmonitoringbasedonthevlswmadftestanddlppcaformultimodalprocesses AT yichengwang faultmonitoringbasedonthevlswmadftestanddlppcaformultimodalprocesses AT jiarongtong faultmonitoringbasedonthevlswmadftestanddlppcaformultimodalprocesses AT yuqingchang faultmonitoringbasedonthevlswmadftestanddlppcaformultimodalprocesses |