Classification of Pattern Partial Discharge (PD) in High Voltage Equipment by Multilayer Perceptron Method
Article Sidebar
Main Article Content
Abstract
This paper proposes a statistical classification based on an application of neural networks by Multilayer Perceptron (MLP) to classify Partial Discharge (PD) patterns into four categories in corona: high voltage side in air, corona at low voltage side in air, internal discharge and surface in air. There are 9 independent variables from fingerprint analysis which mainly are skewness, kurtosis, asymmetry and cross correlation following Phi - q - n PD patterns. PD patterns were used for classification which consists of statistical attribute calculation values. This is calculated from the Hqn() distribution (average PD size distribution based on the voltage phase angle) and Hn() distribution (the number of PD repeat distributions based on the voltage phase angle) distribution calculated from the Hqn() distribution. (It was calculated from the relationship distribution between the magnitude of the PD(q) , the phase angle of the test voltage () , and the number of PD repetitions (n)). All 9 variables were then used in the neural network simulation for partial discharge pattern identification. The approach for constructing the network divides the data into two groups for training data and testing data. The forms for training the model and the pattern for testing the model. The architecture of artificial neural networks in this paper is selected to below complexity as possible using multiple layers of perceptron. The results show that only a hidden layer in the model has a good performance to classify PD pattern with the classification accuracy of 100%. The proposed method can be used to analyze and classify partial discharge patterns and it can be developed to test the partial discharge of high voltage equipment.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in the article published in Journal of Rajamangala University of Technology Srivijaya It is the opinion and responsibility of the author of the article. The editorial journals do not need to agree. Or share any responsibility.
References
Chatpattananan, V. 2006. Linear Discriminant Analysis for Partial Discharge Classification on High Voltage Equipment, pp. 627- 630. In Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP). IEEE, Kansas City, MO, USA.
Chatpattananan, V., Pattanadech, N. and Vicetjindavat, K. 2006a. PCA-LDA for Partial Discharge Classification on High voltage Equipment, pp. 479-481. In Proceedings of 8th International Conference on Properties and applications of Dielectric Materials. IEEE, Bali, Indonesia.
Chatpattananan, V., Pattanadech, N. and Vicetjindavat, K. 2006b. Quest Tree Model for Partial Discharge Classification on High voltage Equipment, pp.476-478. In Proceedings of 8th International Conference on Properties and applications of Dielectric Materials. IEEE, Bali, Indonesia.
Chatpattananan, V., Pattanadech, N. and Yutthagowith, P. 2006c. Partial Discharge Classification on High Voltage Equipment with K-Means, pp. 191-194. In Proceedings of 8th International Conference on Properties and applications of Dielectric Materials. IEEE, Bali, Indonesia.
Cho, K.B. and Oh, J.Y. 1997. An Overview of Application of Artificial Neural Network to Partial Discharge Pattern Classification, pp.326-330. In Proceedings of 5th International Conference on Properties and Applications of Dielectric Materials. IEEE, Seoul, Korea (South).
Gopal, S., Karthikeyan, B. and Kavitha, D. 2004. Partial discharge pattern classification using fuzzy expert system, pp. 653-656. In Proceedings of the 2004 IEEE International Conference on Solid Dielectrics. IEEE, Toulouse, France.
Gulski, E. and Krivda, A. 1993. Neural Networks as a Tool for Recognition of Partial Discharges. IEEE Transactions on Electrical Insulation 28(6): 984-1001.
IEC. 2000. IEC 60270 International Standard High-voltage test techniques - Partial discharge measurements. 3rd ed. IEC, Geneva, Switzerland.
Ludpa, S., Pattanadech, N., Leelajindakrairerk, M. and Yutthagowith, P. 2008. Pattern Classification of Partial Discharge in High Voltage Equipment by Regression Analysis, pp. 921-924. In 5th International Conference on Electrical Engineering / Electronics,Computer,Telecommunications and Information Technology 2. IEEE, Krabi, Thailand.
Pattanadech, N. and Nimsanong, P. 2014. Partial discharge classification using principal component analysis combined with self-organizing map, pp. 1-5. In TENCON 2014 - 2014 IEEE Region 10 Conference. IEEE, Bangkok, Thailand.
Pattanadech, N., Nimsanong, P., Potivejkul, S., Yuthagowith, P. and Polmai, S. 2015a. Partial discharge classification using probabilistic neural network model, pp. 1176-1180. In 18th International Conference on Electrical Machines and Systems (ICEMS). IEEE, Pattaya, Thailand.
Pattanadech, N., Nimsanong, P., Potivejkul, S., Yuthagowith, P. and Polmai, S. 2015b. Generalized regression networks for partial discharge classification, pp. 1165-1169. In 18th International Conference on Electrical Machines and Systems (ICEMS). IEEE, Pattaya, Thailand.
Tomsovic, K., Tapper, M. and Ingvarsson, T.T. 1993. A Fuzzy Information Approach to Integrating Different Transformer Diagnostic methods. IEEE Transactions on Power Delivery 8: 1638-1643.
Vicetjindavat, K. 2001. Pattern Recognition of Partial Discharge in High Voltage Equipment. Master Thesis of Engineering, Department of Electrical Engineering, Chulalongkorn University.
Zhang, H., Lee, W.J., Kwan, C., Ren, Z., Chen, H. and Sheeley, J. 2005. Artificial Neural Network Based On-Line Partial Discharge Monitoring System for Motors, pp. 125-132. In IEEE Systems Technical Conference on Industrial and Commercial Power 2005. IEEE, Saragota Springs, NY, USA.