Distribution transformer mechanical faults diagnosis method incorporating cross-domain feature extraction and recognition of unknown-type faults

•An improved CAE algorithm is introduced, which integrates frequency spectral sequences into the output reconstruction phase. This innovative approach allows the model to dynamically extract information from the vibration signals across both the time and frequency domains, thereby providing a more c...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Measurement : journal of the International Measurement Confederation Jg. 238; S. 115270
Hauptverfasser:	Huang, Haiyan, Gao, Wei, Yang, Gengjie
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.10.2024
Schlagworte:	Cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) Distribution transformer Mechanical faults Open-set domain adaptation classifier(OSDA-C) Vibration signals Cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) Open-set domain adaptation classifier(OSDA-C) Distribution transformer Vibration signals Mechanical faults
ISSN:	0263-2241
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	•An improved CAE algorithm is introduced, which integrates frequency spectral sequences into the output reconstruction phase. This innovative approach allows the model to dynamically extract information from the vibration signals across both the time and frequency domains, thereby providing a more comprehensive analysis.•The problem of difficult selection of multi-scale convolutional kernel size in CFMS-CAE is solved using the crayfish optimization algorithm(COA) to improve the speed of model training.•The OSDA will be incorporated in the CNN classifier to accurately differentiate even for UTF samples. The complexity and uncertainty of vibration signals from distribution transformers pose significant challenges for diagnosing mechanical faults. To address this, this paper proposes a novel fault diagnosis model for distribution transformers, which combines a cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) with an open-set domain adaptation classifier (OSDA-C). Specifically, in order to extract more comprehensive features, a convolutional autoencoder (CAE) model based on multi-output objectives is constructed to extract the time-frequency domain characteristics of transformer vibration signals. Multiple-scale convolutional layers are incorporated into the convolutional autoencoder to enable multi-range feature extraction. Additionally, parameter optimization is achieved using the crayfish optimization algorithm (COA). Subsequently, an open-set domain adaptation module is integrated into the convolutional neural network classifier to establish boundaries for each category and facilitate the identification of transformer fault categories, including unknown-type faults. The experimental results demonstrate that the proposed method is effective for fault identification in both dry-type and oil-immersed transformers, with average accuracy reaching 99.35% and 99.62%, respectively. For unknown-type faults, the accuracy also achieved 100% and 97.5%, respectively.
ISSN:	0263-2241
DOI:	10.1016/j.measurement.2024.115270