ABSTRACT
As an important hub equipment of power system, the safe and stable operation of transformer is the top priority to ensure the continuous supply of high-quality electric energy and the normal operation of social life. The state estimation of the transformer is the key to the operation state maintenance method. The existing transformer state estimation methods mainly use gas content and other data, but can not use the massive transformer electrical quantity monitoring data accumulated in the monitoring system. Therefore, a k-means clustering method for transformer state anomaly detection based on voltage, current and power data of transformer is proposed. Firstly, based on the monitoring data of transformer with normal maintenance history, a state detection model based on K-means clustering is constructed. Then, according to the clustering results of historical normal data, the appropriate threshold is selected, and the distance between the new data and each cluster center is analyzed to judge the operation status of the transformer. Finally, the correctness of the model is verified by an example. The results show that the proposed method can make full use of the electrical data of the transformer and realize the real-time detection of the transformer state, which is convenient for engineering application.
- L. Zhang and J. Yang, "State assessment of power transformers based on multi-dimensional normal cloud model," Electrical Measurement & Instrumentation, vol. 57, pp. 129-135, 2020.Google Scholar
- Y. Liu, H. Yin, X. Zhang, S. Fan, L. Yan, and B. Gao, "Abnormal condition detection of power transformer based on dynamical threshold," Electrical Measurement & Instrumentation, vol. 54, pp. 61-66, 2017.Google Scholar
- J. Zhang, X. Xu, M. Ding, J. Li, J. Wang, and C. Wu, "A condition assessment method of power transformers based on fuzzy analytic hierarchy process," Power System Protection and Control, vol. 45, pp. 75-81, 2017.Google Scholar
- M. Li, S. Li, X. Xian, C. Hao, L. Zheng, and G. Wu, "Insulation condition assessment for power transformer based on intuitionistic normal cloud model and optimal variable weights," Electrical Measurement & Instrumentation, vol. 53, pp. 42-50, 2016.Google Scholar
- B. Hu, X. Deng, and S. Jia, " Transformer life estimation and state assessment based on ANFIS," Electrical Measurement & Instrumentation, pp. 1-9. [2020-06-17]. http://kns.cnki.net/kcms/ detail/23.1202.TH.20200617.1338.010.html.Google Scholar
- Z. Zhang, W. Zhao, Y. Zhu, Z. Wu, and J. Yang, "Power transformer condition evaluation based on support vector regression," Electric Power Automation Equipment, vol. 30, pp. 81-84, 2010.Google Scholar
- R. Xie, D. Zhang, F. Lin, L. Li, and X. Wu, "Transformer condition assessment using association rules and variable weight," High Voltage Apparatus, vol. 50, pp. 133-138, 2014.Google Scholar
- L. Li, D. Zhang, L. Xie, B. Yu, and F. Lin, "A condition assessment method of power transformers based on association rules and variable weight coefficients," Proceedings of the CSEE, vol. 33, pp. 152-159, 2013.Google Scholar
- L. Ruan, Q. Xie, S. Gao, D. Nie, W. Lu, and H. Zhang, "Application of artificial neural network and information fusion technology in power transformer condition assessment," High Voltage Engineering, vol. 40, pp. 822-828, 2014.Google Scholar
- T. Shen, and Q. Li, "A Transformer condition assessment based on support vector machine and DGA," Proceedings of the CSU-EPSA, vol. 24, pp. 47-50, 2008.Google Scholar
- B. Qi, P. Zhang, R. Xu, Z. Rong, H. Wang, and C. Li, "Calculation method on differentiated warning value of power transformer based on distribution model," High Voltage Engineering, vol. 42, pp. 2290-2298, 2016.Google Scholar
- R. Liao, Q. Wang, S. Luo, Y. Liao, and C. Sun, "Condition assessment model for power transformer in service based on fuzzy synthetic evaluation," Automation of Electric Power Systems, vol. 32, pp. 70-75, 2008.Google Scholar
- W. H. Tang, K. Spurgeon, Q. H. Wu and Z. J. Richardson, "An evidential reasoning approach to transformer condition assessments," in IEEE Transactions on Power Delivery, vol. 19, pp. 1696-1703, Oct. 2004.Google ScholarCross Ref
- H. Xie, and F. Lu, " Transformer condition evaluation based on information fusion," Journal of North China Electric Power University, vol. 33, pp. 8-11, 2006.Google Scholar
- Y. Liu, G. Li, K. Gao, Y. Du, Q. Zhang, X. Niu, and W. Sun, "Fundamental frame to draft guide for condition maintenance of electric power equipment," Power System Technology, vol. 27, pp. 64-67, 2003.Google Scholar
- S. Hao, J. Zhang, Y. Zhang, and X. Zhang, "State evaluation of transformer based on information fusion of on-line monitoring data," Electric Power Automation Equipment, vol. 37, pp. 176-181, 2017.Google Scholar
- R. Xie, C. Ma, L. Zhang, and J. Jin, "Power transformer abnormal state recognition model based on improved K-means clustering," Power Systems and Big Data, vol. 21, pp. 24-30, 2018.Google Scholar
- H. Cheng, J. Liu, J. Kang, and X. Wang, "Improved immune recognition method of transformer health," Journal of Electric Power Science and Technology, vol. 21, pp. 24-30, 2018.Google Scholar
- L. Wu, Q. Wu, Y. Feng, Z. Wang, Z. Wang, and L. Zhao, "State recognition of transformer based on SVM classification of vibration signals," High Voltage Apparatus, vol. 55, pp. 232-238, 2019.Google Scholar
- H. Tian, Y. Ji, C. Strict, H. Huang, and Y. Yao, "Application of ODS in state identification of transformers," Noise and Vibration Control, vol. 39, pp. 197-200, 2019.Google Scholar
Index Terms
- Anomalous State Detection of Power Transformer Based on K-Means Clustering Algorithm
Recommendations
An OPTICS clustering-based anomalous data filtering algorithm for condition monitoring of power equipment
DARE'15: Proceedings of the Third International Conference on Data Analytics for Renewable Energy IntegrationIn allusion to the widespread anomalous data in substation primary equipment condition monitoring, this paper proposes an OPTICS (Ordering Points To Identify the Clustering Structure) clustering-based condition monitoring anomalous data filtering ...
Fault Detection Method of Photovoltaic System Based on Power Change of Array
ACAI '21: Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial IntelligenceThe fault detection of photovoltaic power generation system is of great significance in photovoltaic plant management. The conventional fault detection method of photovoltaic power system requires additional sensors, and the fault detection scheme needs ...
Hybrid Bisect K-Means Clustering Algorithm
BCGIN '11: Proceedings of the 2011 International Conference on Business Computing and Global InformatizationIn this paper, we present a hybrid clustering algorithm that combines divisive and agglomerative hierarchical clustering algorithm. Our method uses bisect K-means for divisive clustering algorithm and Unweighted Pair Group Method with Arithmetic Mean (...
Comments