期刊
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
卷 67, 期 7, 页码 5349-5359出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIE.2019.2931487
关键词
Generators; Eddy currents; Turbines; Rotors; Mathematical model; Finite element analysis; Predictive models; Deep Gaussian process regression (DGPR); eddy current loss; finite-element method (FEM) simulation; generator performance prediction; nuclear power generator
资金
- National Natural Science Foundation of China [61773087, 51907042]
- University Nursing Program for Young Scholars with Creative Talents in Heilongjiang Province [UNPYSCT-2018212]
- Fundamental Research Foundation for Universities of Heilongjiang Province [LGYC2018JC028]
- China Postdoctoral Science Foundation [2018T110270, 2017M620109]
- Postdoctoral Foundation of Heilongjiang Province of China [LBH-Z17041]
- Heilongjiang Science and Technology Achievement Conversion and Cultivation Project [TSTAU-C2018002]
- Foundation of Chinese Ministry of Education [18YJCZH040]
- National Natural Science Foundation of Liaoning [20170050, 2018401030]
Eddy current analysis is a key issue for large turbine generators. The finite-element method (FEM) is a computational tool for obtaining the electromagnetic characteristics of electrical machines. In this article, we propose a computer model of the eddy current losses of metal fasteners in the rotor slots of a large turbine generator. The electromagnetic properties of the rotor fasteners and the outer diameter of the rotor are taken as the input, and the eddy current loss of the rotor fasteners is taken as the output. A prediction model is constructed using the FEM and deep learning. The analysis results show that compared with the independent finite-element analysis, this method reduces the design cycle time and improves the design efficiency for a large-capacity turbine generator. Compared with other machine learning models, the error is smaller and the accuracy is higher. This method provides a new way to accurately predict the eddy current loss of a generator under complex nonlinear conditions.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据