Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network.
Saved in:
| Title: | Transformer Fault Diagnosis Based on Adaptive Boosting and Bidirectional Long Short-Term Memory Neural Network. |
|---|---|
| Authors: | Shang, Liqun1 851973009@qq.com, Ma, Chuang1 2643742102@qq.com, Li, Aolong1 1754797676@qq.com, Li, Jie1 2516935990@qq.com, Zhu, Yixuan1 3214318417@qq.com |
| Source: | IAENG International Journal of Computer Science. May2026, Vol. 53 Issue 5, p1846-1854. 9p. |
| Subjects: | Fault diagnosis, Boosting algorithms, Long short-term memory, Gas chromatography, Recurrent neural networks, Ensemble learning, Optimization algorithms, Principal components analysis |
| Abstract: | To enhance the performance of transformer fault diagnosis models based on Dissolved Gas Analysis (DGA), this paper proposes a method that optimizes a Bidirectional Long Short-Term Memory (BiLSTM) neural network using an Improved Sparrow Search Algorithm (ISSA) and Adaptive Boosting (AdaBoost). Initially, the Halton sequence and Lévy flight strategy are incorporated into the Sparrow Search Algorithm (SSA), and the resulting ISSA is employed to optimize the key parameters of the BiLSTM network, thereby constructing an ISSA-BiLSTM-based transformer fault diagnosis model. Subsequently, Kernel Principal Component Analysis (KPCA) is applied to the collected oil chromatography data for dimensionality reduction. The reduced-dimensional data are then fed into various transformer fault diagnosis models for simulation and validation. Finally, an ensemble learning model is developed using the AdaBoost algorithm to improve the diagnostic performance of the base classifiers. Experimental results demonstrate that the proposed method achieves excellent performance in terms of diagnostic accuracy and classification effectiveness, enabling accurate identification of fault types in power transformers. [ABSTRACT FROM AUTHOR] |
| Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
