Online Sequential Extreme Learning Machine for Partial Discharge Pattern Recognition of Transformer

Traditional pattern recognition algorithms have limitations including slow training speed and low recognition accuracy in practical engineering applications. In this paper, a new method based on Online Sequential Extreme Learning Machine (OS-ELM) is proposed. Data samples have been obtained from PD experiment of real transformer based on Ultra High Frequency (UHF) detection method. In addition, OS-ELM is compared with Extreme Learning Machine (ELM), Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) in both recognition accuracy and performance aspects. The results show that OS-ELM is not only much faster in learning speed, but also more excellent in recognition accuracy, thus more suitable for engineering applications with large volume of data samples.

[1]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[2]  Johan J. Smit,et al.  Interpretation of recovery voltage measurements on power transformers , 1999 .

[3]  Wang Hui.  Optimization Method of Parameter for Fuzzy Clustering Algorithm and Application in the PD Pattern Recognition for GIS , 2010 .

[4]  Hasmat Malik,et al.  Extreme learning machine based fault diagnosis of power transformer using IEC TC10 and its related data , 2015, 2015 Annual IEEE India Conference (INDICON).

[5]  Stefan Tenbohlen,et al.  Application of UHF sensors for PD measurement at power transformers , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[6]  Martin D. Judd,et al.  Applying UHF partial discharge detection to power transformers , 2002 .

[7]  Jie Li,et al.  Short-term load forecasting based on improved extreme learning machine , 2017, 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(.

[8]  Chao Yu,et al.  Online ship rolling prediction using an improved OS-ELM , 2014, CCC 2014.

[9]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[10]  Jinho Lee,et al.  Developments in UHF PD monitoring system for switchgear and transformer paper title , 2016, 2016 Conference on Diagnostics in Electrical Engineering (Diagnostika).

[11]  Binu P Chacko,et al.  Online sequential extreme learning machine based handwritten character recognition , 2011, IEEE Technology Students' Symposium.