Neural Network-based Approach for Modeling Electric Arc Furnace Load
碩士 === 國立中正大學 === 電機工程研究所 === 99 === This thesis addresses the development of an electric arc furnace (EAF) model for the steel plant power system, where a neural network-based method is proposed. To observe the actual phenomena of the power quality disturbances with EAF loads, the power quality...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/31270576998424094537 |
Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 99 === This thesis addresses the development of an electric arc furnace (EAF) model for the steel plant power system, where a neural network-based method is proposed. To observe the actual phenomena of the power quality disturbances with EAF loads, the power quality recorders are employed to provide the actual waveforms of the steel plant. It is known that artificial neural network (ANN) is a powerful scheme for function learning and nonlinear loads modeling. There are many different neural networks, and this thesis is using radial basis function neural network (RBFNN) to model the EAF loads. A combination of the ANN with the discrete wavelet transform is proposed in this thesis. Simulation results obtained by using the proposed model are compared with the actual measured data and the look-up table (LUT) models. In addition, the v-i characteristics of these loads are used to make better comparisons by simulations and measurements.
|
---|