Education, Science, Technology, Innovation and Life
Open Access
Sign In

Transformer Fault Diagnosis Based on Stacking-Ensemble Meta-Algorithms

Download as PDF

DOI: 10.23977/acss.2021.050106 | Downloads: 34 | Views: 1209

Author(s)

Yan Wang 1, Liguo Zhang 2

Affiliation(s)

1 Dept. of Computer, North China Electric Power University, Hebei Baoding, China
2 College of Information Science & Technology, Agricultural University of Hebei, Baoding, China

Corresponding Author

Yan Wang

ABSTRACT

Compared with the method of establishing a single classifier for diagnosis, ensemble learning can combine multiple classifiers to achieve stronger generalization ability. This paper proposed a transformer fault diagnosis method based on Stacking Ensemble multiple classifiers, which can detect the transformer’s internal fault by using its DGA data. The proposed model is consisted of two sections. The first section includes five diagnosis models: Random Forest Classifier, AdaBoost Classifier, Gradient Boosting Classifier, SVM and Extra Trees Classifier. The second section use XGB Classifier as final Meta-Classifier model to classify the faults of transformers by using all the base level model diagnosis results as input. The diagnosis accuracy of the proposed method is 83.3%, which is better than other single Classification method. 

KEYWORDS

Dissolved gas analysis; transformer fault diagnosis; Stacking-Ensemble; classification algorithm

CITE THIS PAPER

Yan Wang, Liguo Zhang. Transformer Fault Diagnosis Based on Stacking-Ensemble Meta-Algorithms. Advances in Computer, Signals and Systems (2021) 5: 42-47. DOI: http://dx.doi.org/10.23977/acss.2021.050106

REFERENCES

[1] J. Dai, H. Song, G. Sheng and X. Jiang, "Dissolved gas analysis of insulating oil for power transformer fault diagnosis with deep belief network," in IEEE Transactions on Dielectrics and Electrical Insulation, vol. 24, no. 5, pp. 2828-2835, Oct. 2017.
[2] Chaolong Zhang, Yigang He, Bolun Du, Lifen Yuan, Bing Li, Shanhe Jiang, Transformer fault diagnosis method using IoT based monitoring system and ensemble machine learning, Future Generation Computer Systems, Volume 108, 2020,Pages 533-545
[3] J. Faiz and M. Soleimani, "Assessment of computational intelligence and conventional dissolved gas analysis methods for transformer fault diagnosis," in IEEE Transactions on Dielectrics and Electrical Insulation, vol. 25, no. 5, pp. 1798-1806, Oct. 2018.
[4] Xiaohui Yang, Wenkai Chen, Anyi Li, Chunsheng Yang, Zihao Xie, Huanyu Dong, BA-PNN-based methods for power transformer fault diagnosis,Advanced Engineering Informatics, Volume 39,2019,Pages 178-185.
[5] T. Kari et al., "An integrated method of ANFIS and Dempster-Shafer theory for fault diagnosis of power transformer," in IEEE Transactions on Dielectrics and Electrical Insulation, vol. 25, no. 1, pp. 360-371, Feb. 2018, doi: 10.1109/TDEI.2018.006746.
[6] Xue Wang, Tao Han.”Transformer Fault Diagnosis Based on Stacking Ensemble Learning,” in IEEJ Transactions on Electrical and Electronic Engineering,Volume15, Issue12, Pages 1734-1739,December 2020
[7] Y. Wang and L. Zhang, "Transformer fault diagnosis based on back-propagation neural network optimized by cuckoo search algorithm," 2017 3rd IEEE International Conference on Control Science and Systems Engineering (ICCSSE), 2017, pp. 383-386, doi: 10.1109/CCSSE.2017.8087962.
[8] Archana Chaudhary, Savita Kolhe, Raj Kamal,An improved random forest classifier for multi-class classification, Information Processing in Agriculture, Volume 3, Issue 4,2016,Pages 215-222.
[9] Chen, Siji et al. “A Strong Machine Learning Classifier and Decision Stumps Based Hybrid AdaBoost Classification Algorithm for Cognitive Radios.” Sensors (Basel, Switzerland) vol. 19,23 5077. 20 Nov. 2019, doi: 10.3390/s19235077

Downloads: 11338
Visits: 240399

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.