Multi-parameter Overload Capacity Evaluation of Power Transformer Based on Improved Neural Network

DOI

10.2991/icaees-15.2015.123How to use a DOI?

Keywords

Transformers; Overloading Capacity; Modified BP Neural Network

Abstract

Normally, transformer overloading capacity is calculated using method in guide for loading mineral-oil-immersed transformers. However, the method is not so accurate for every transformer. Therefore, a modified BP neural network based on transformer overloading calculation model is proposed. With BP neural network, computers can learn history data of transformer overloading and compute overloading time. This model combines a conditions parameter of cooling devices to make the result more accurate. The calculation data of case study using modified BP neural network model reveal that this model can get reasonable overloading time. Moreover, the overloading time is based on transformer stabilized operation, which is very practical significance.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yufeng Chen
AU  - Hui Wang
AU  - Zhihong Guo
AU  - Xiumin Du
AU  - Yi Yang
AU  - Chuanshuang He
AU  - Gehao Sheng
PY  - 2015/07
DA  - 2015/07
TI  - Multi-parameter Overload Capacity Evaluation of Power Transformer Based on Improved Neural Network
BT  - Proceedings of the 3rd International Conference on Advances in Energy and Environmental Science 2015
PB  - Atlantis Press
SP  - 670
EP  - 677
SN  - 2352-5401
UR  - https://doi.org/10.2991/icaees-15.2015.123
DO  - 10.2991/icaees-15.2015.123
ID  - Chen2015/07
ER  -