Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation
Multiscale PCA (MSPCA) is a well-established fault-detection and isolation (FDI) technique. It utilizes wavelet analysis and PCA to extract important features from process data. This study demonstrates limitations in the conventional MSPCA fault detection algorithm, thereby proposing an enhanced MSP...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/15/5564 |
_version_ | 1797440714450141184 |
---|---|
author | Byanne Malluhi Hazem Nounou Mohamed Nounou |
author_facet | Byanne Malluhi Hazem Nounou Mohamed Nounou |
author_sort | Byanne Malluhi |
collection | DOAJ |
description | Multiscale PCA (MSPCA) is a well-established fault-detection and isolation (FDI) technique. It utilizes wavelet analysis and PCA to extract important features from process data. This study demonstrates limitations in the conventional MSPCA fault detection algorithm, thereby proposing an enhanced MSPCA (EMSPCA) FDI algorithm that uses a new wavelet thresholding criterion. As such, it improves the projection of faults in the residual space and the threshold estimation of the fault detection statistic. When tested with a synthetic model, EMSPCA resulted in a 30% improvement in detection rate with equal false alarm rates. The EMSPCA algorithm also relies on the novel application of reconstruction-based fault isolation at multiple scales. The proposed algorithm reduces fault smearing and consequently improves fault isolation performance. The paper will further investigate the use of soft vs. hard wavelet thresholding, decimated vs. undecimated wavelet transforms, the choice of wavelet decomposition depth, and their implications on FDI performance.The FDI performance of the developed EMSPCA method was illustrated for sensor faults. This undertaking considered synthetic data, the simulated data of a continuously stirred reactor (CSTR), and experimental data from a packed-bed pilot plant. The results of these examples show the advantages of EMSPCA over existing techniques. |
first_indexed | 2024-03-09T12:13:25Z |
format | Article |
id | doaj.art-f5f3b8b101294cd2adbd56be1ee90e26 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T12:13:25Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f5f3b8b101294cd2adbd56be1ee90e262023-11-30T22:50:36ZengMDPI AGSensors1424-82202022-07-012215556410.3390/s22155564Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and IsolationByanne Malluhi0Hazem Nounou1Mohamed Nounou2Chemical Engineering Program, Texas A&M University at Qatar, Doha P.O. Box 23874, QatarElectrical and Computer Engineering Program, Texas A&M University at Qatar, Doha P.O. Box 23874, QatarChemical Engineering Program, Texas A&M University at Qatar, Doha P.O. Box 23874, QatarMultiscale PCA (MSPCA) is a well-established fault-detection and isolation (FDI) technique. It utilizes wavelet analysis and PCA to extract important features from process data. This study demonstrates limitations in the conventional MSPCA fault detection algorithm, thereby proposing an enhanced MSPCA (EMSPCA) FDI algorithm that uses a new wavelet thresholding criterion. As such, it improves the projection of faults in the residual space and the threshold estimation of the fault detection statistic. When tested with a synthetic model, EMSPCA resulted in a 30% improvement in detection rate with equal false alarm rates. The EMSPCA algorithm also relies on the novel application of reconstruction-based fault isolation at multiple scales. The proposed algorithm reduces fault smearing and consequently improves fault isolation performance. The paper will further investigate the use of soft vs. hard wavelet thresholding, decimated vs. undecimated wavelet transforms, the choice of wavelet decomposition depth, and their implications on FDI performance.The FDI performance of the developed EMSPCA method was illustrated for sensor faults. This undertaking considered synthetic data, the simulated data of a continuously stirred reactor (CSTR), and experimental data from a packed-bed pilot plant. The results of these examples show the advantages of EMSPCA over existing techniques.https://www.mdpi.com/1424-8220/22/15/5564multiscale PCAprocess monitoringfault detectionfault isolationsensor faultswavelet analysis |
spellingShingle | Byanne Malluhi Hazem Nounou Mohamed Nounou Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation Sensors multiscale PCA process monitoring fault detection fault isolation sensor faults wavelet analysis |
title | Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation |
title_full | Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation |
title_fullStr | Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation |
title_full_unstemmed | Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation |
title_short | Enhanced Multiscale Principal Component Analysis for Improved Sensor Fault Detection and Isolation |
title_sort | enhanced multiscale principal component analysis for improved sensor fault detection and isolation |
topic | multiscale PCA process monitoring fault detection fault isolation sensor faults wavelet analysis |
url | https://www.mdpi.com/1424-8220/22/15/5564 |
work_keys_str_mv | AT byannemalluhi enhancedmultiscaleprincipalcomponentanalysisforimprovedsensorfaultdetectionandisolation AT hazemnounou enhancedmultiscaleprincipalcomponentanalysisforimprovedsensorfaultdetectionandisolation AT mohamednounou enhancedmultiscaleprincipalcomponentanalysisforimprovedsensorfaultdetectionandisolation |