Knowledge addition for improving the transfer learning from the laboratory to identify defects of hydraulic machinery
Authors:
- Anil Kumar,
- Adam Glowacz,
- Hesheng Tang,
- Jiawei Xiang
Abstract
This work proposes a solution to improve transfer learning from laboratory environment to real-world hydraulic machinery (centrifugal pump) for the effective identification of defects. The proposed method involves collecting vibration data, normalizing and computing Fast Fourier Transform (FFT) of the data, and adding attributes by combining the FFT of healthy real-world machinery with the FFT of laboratory machinery. The attribute addition is performed in the frequency domain to address phase lag issues in timedomain data. The resulting signal is transformed back to the time domain, and the envelope spectrum is obtained. An approximation model is constructed using the envelope spectrum and refined using data from industrial machinery. The refined model is then employed to identify defects in real machinery, specifically the centrifugal pump. The proposed knowledge addition-based transfer learning achieves an accuracy of 93%, which is 51% higher than the accuracy attained by the domain-adversarial neural network method.
- Record ID
- CUT83223ed7d1b249a3a5489580934da899
- Publication categories
- ;
- Author
- Journal series
- Engineering Applications of Artificial Intelligence, ISSN 0952-1976, e-ISSN 1873-6769
- Issue year
- 2023
- Vol
- 126, Pt. A
- Pages
- [1-12]
- Article number
- 106756
- Other elements of collation
- fot.; rys.; schem.; tab.; wykr.; Bibliografia (na s.) - 11-12; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 126, Pt. A
- Substantive notes
- Part of special issue: Artificial Intelligence for Machinery Diagnostics and Prognostics
- Data available online at: https://ieee-dataport.org/documents/acoustic-and-vibration-data-defect-cases-centrifugal-pump and https://ieee-dataport.org/documents/vibration-and-acoustic-data-defect-cases-cylindrical-roller-bearing-nbc-nu205e
- Keywords in English
- transfer learning, knowledge addition, fault diagnosis, deep learning
- ASJC Classification
- ; ;
- DOI
- DOI:10.1016/j.engappai.2023.106756 Opening in a new tab
- URL
- https://www.sciencedirect.com/science/article/pii/S0952197623009405 Opening in a new tab
- Language
- eng (en) English
- Score (nominal)
- 140
- Score source
- journalList
- Score
- Publication indicators
- Citation count
- 7
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT83223ed7d1b249a3a5489580934da899/
- URN
urn:pkr-prod:CUT83223ed7d1b249a3a5489580934da899
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.