WaveCORAL-DCCA: A Scalable Solution for Rotor Fault Diagnosis Across Operational Variabilities

Rezazadeh, Nima and De Oliveira, Mario and Lamanna, Giuseppe and Perfetto, Donato and De Luca, Alessandro (2025) WaveCORAL-DCCA: A Scalable Solution for Rotor Fault Diagnosis Across Operational Variabilities. Electronics, 14 (15). p. 3146. ISSN 2079-9292

Preview

Text electronics-14-03146.pdf - Published Version Available under License Creative Commons Attribution. Download (4MB)

Abstract

This paper presents WaveCORAL-DCCA, an unsupervised domain adaptation (UDA) framework specifically developed to address data distribution shifts and operational variabilities (OVs) in rotor fault diagnosis. The framework introduces the novel integration of discrete wavelet transformation for robust time–frequency feature extraction and an enhanced deep canonical correlation analysis (DCCA) network with correlation alignment (CORAL) loss for superior domain-invariant representation learning. This combination enables more effective alignment of source and target feature distributions without requiring any labelled data from the target domain. Comprehensive validation on both experimental and numerically simulated rotor datasets across three health conditions—i.e., normal, unbalanced, and misaligned—demonstrates that WaveCORAL-DCCA achieves an average diagnostic accuracy of 95%. Notably, it outperforms established UDA benchmarks by at least 5–17% in cross-domain scenarios. These results confirm that WaveCORAL-DCCA provides robust generalisation across machines, fault severities, and operational conditions, even with scarce target domain samples, offering a scalable and practical solution for industrial rotor fault diagnosis.

Item Type:	Article
Identification Number:	10.3390/electronics14153146
Dates:	Date Event 4 August 2025 Accepted 7 August 2025 Published Online
Uncontrolled Keywords:	rotor fault diagnosis; operational variabilities; unsupervised domain adaptation; wavelet transformation; deep canonical correlation analysis; correlation alignment
Subjects:	CAH10 - engineering and technology > CAH10-01 - engineering > CAH10-01-01 - engineering (non-specific)
Divisions:	Architecture, Built Environment, Computing and Engineering > Engineering
Depositing User:	Gemma Tonks
Date Deposited:	15 Aug 2025 15:31
Last Modified:	15 Aug 2025 15:31
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16595

Actions (login required)

View Item