Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis
Sensors · 13.03.2024 · 24 (6) · 1830
DOI: 10.3390/s24061830 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.03.2024. Verfasst von Saif Ullah und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Trade, Industry and Energy, Ministry of Trade, Industry & Energy (MOTIE, Korea), Korea Industrial Complex Corporation.
Abstract (Originalsprache)
This study introduces an innovative approach for fault diagnosis of a multistage centrifugal pump (MCP) using explanatory ratio (ER) linear discriminant analysis (LDA). Initially, the method addresses the challenge of background noise and interference in vibration signals by identifying a fault-sensitive frequency band (FSFB). From the FSFB, raw hybrid statistical features are extracted in time, frequency, and time–frequency domains, forming a comprehensive feature pool. Recognizing that not all features adequately represent MCP conditions and can reduce classification accuracy, we propose a novel ER-LDA method. ER-LDA evaluates feature importance by calculating the explanatory ratio between interclass distance and intraclass scatteredness, facilitating the selection of discriminative features through LDA. This fusion of ER-based feature assessment and LDA yields the novel ER-LDA technique. The resulting selective feature set is then passed into a k-nearest neighbor (K-NN) algorithm for condition classification, distinguishing between normal, mechanical seal hole, mechanical seal scratch, and impeller defect states of the MCP. The proposed technique surpasses current cutting-edge techniques in fault classification.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.
- Prognosis and Diagnostic Technologies Co., Ulsan 44610, Republic of Korea.
ORCID-Profile: Saif Ullah, Zahoor Ahmad, Jong-Myon Kim
Förderung
- Ministry of Trade, Industry and Energy
- Ministry of Trade, Industry & Energy (MOTIE, Korea)
- Korea Industrial Complex Corporation
Zitieren
APA
Ullah, S., Ahmad, Z., & Kim, J. M. (2024). Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis. Sensors, 24(6), 1830. https://doi.org/10.3390/s24061830
Vancouver
Ullah S, Ahmad Z, Kim JM. Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis. Sensors. 2024;24(6):1830. doi:10.3390/s24061830
BibTeX
@article{Ullah2024,
author = {Ullah, Saif and Ahmad, Zahoor and Kim, Jong-Myon},
title = {Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis},
journal = {Sensors},
year = {2024},
volume = {24},
number = {6},
pages = {1830},
doi = {10.3390/s24061830}
}
EUVIMED