Detection of Transformer Winding Condition Based on Optimal K-Means Algorithm

被引：0
|
作者：
Yang X. [1 ]
Wang F. [2 ]
Duan R. [2 ]
He M. [2 ]
机构：
[1] Electric Power Research Institute, Guangdong Electric Power Company, Guangzhou
[2] Key Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai
来源：
Wang, Fenghua (fhwang7723@sjtu.edu.cn) | 2018年 / Science Press卷 / 44期
基金：
中国国家自然科学基金;
关键词：
Characteristic vector; Optimal K-Means; Transformer; Vibration signal; Winding condition;
D O I：
10.13336/j.1003-6520.hve.20180529040
中图分类号：
学科分类号：
摘要：
To detect the mechanical status of transformer winding more accurately, we propose that the optimal K-Means clustering al-gorithm is adopted to analyze the unstable and time-varying vibration signals of transformer under sudden short-circuit. Firstly, the characteristic vectors of each vibration signal are abstracted. Then the data density is introduced to optimize the K-means algorithm, which can more optimize the selection of initial centroids. The centroids of the characteristic vectors un-der different conditions can be calculated based on the optimized K-Means algorithm. The experimental results of vibration signals for a 110 kV transformer under sudden short-circuit show that the optimized K-Means algorithm has the advantage of high accuracy. The variation of centroid positions of characteristic vectors is capable of clearly reflecting the variation de-gree of winding deformation, which can provide the reference for the proposal of condition maintenance strategy. © 2018, High Voltage Engineering Editorial Department of CEPRI. All right reserved.
引用
收藏
页码：2027 / 2032
页数：5
相关论文
共 13 条
  • [1] Sun X., He W., Zhang J., Et al., Current status and development of test and diagnosis technique of transformer winding deformation, High Voltage Engineering, 42, 4, pp. 1207-1220, (2016)
  • [2] Yang Y., Wang F., Duan R., Et al., Detection of transformer winding condition based on self-adaptive sifting EMD and CFDC, Journal of Vibration and Shock, 36, 10, pp. 106-112, (2017)
  • [3] He M., Wang F., Qian G., Et al., Design and development of power transformer vibration and noise signals analysis system based on. NET framework, Automation of Electric Power Systems, 41, 1, pp. 150-154, (2017)
  • [4] Garcia B., Burgos J.C., Alonso A.M., Transformers tank vibration modelling as a method of detecting winding deformations, part I: theoretical foundation, IEEE Transactions on Power Delivery, 21, 1, pp. 157-163, (2006)
  • [5] Garcia B., Burgos J.C., Alonso A.M., Transformers tank vibration modelling as a method of detecting winding deformations, part II: experimental verification, IEEE Transactions on Power Delivery, 21, 1, pp. 164-169, (2006)
  • [6] Ibargiemgputia P.H., Linan R., Betancourt E., Transformer diagnosis using probabilistic vibration model, IEEE PES on Transmission and Distribution Conference and Exposition, pp. 1-8, (2010)
  • [7] Ma H., Geng Z., Chen K., Et al., A new fault diagnosis method for power transformer winding deformation based on vibration, Automation of Electric Power Systems, 37, 8, pp. 89-95, (2013)
  • [8] Yan J., Ma H., Li K., Et al., Vibration signal based diagnosis method for looseness fault of transformer winding, Automation of Electric Power Systems, 41, 3, pp. 122-128, (2017)
  • [9] Shao Y., Xu J., Rao Z., Et al., On-line diagnosis for a transformer winding's state under short-circuit shock, Journal of Vibration and Shock, 30, 2, pp. 173-176, (2011)
  • [10] Zhang K., Wang F., Liao T., Et al., Detection of transformer winding deformation under short-circuit impulse base on complex wavelet algorithm, Transactions of China Electrotechnical Society, 29, 8, pp. 327-332, (2014)
12