The Analysis of Magnetic and Thermal Characteristics for the Three Gorges' 840MVA Evaporative Cooling Hydrogenerator on the Basis of Ansys Software

The calculation of large hydrogenerator's magnetic and thermal fields is very complicated due to the complexity of their construction, different properties of their materials and nonlinearity of core B-H curve. Finite Element analysis tools are relatively convenient for solving these problems. In this paper, Ansys software is adopted in analysis of the Three Gorges' 840MVA evaporative cooling hydrogenerator. Magnetic analysis and thermal analysis are made respectively. By doing that we got satisfying results and the results also show the advantage of the evaporative cooling technology.

[1]  Philip Doble,et al.  Classification of premium and regular gasoline by gas chromatography/mass spectrometry, principal component analysis and artificial neural networks. , 2003, Forensic science international.

[2]  M. Ichikawa,et al.  Mass Spectrometric Analysis for Distinction between Regular and Premium Motor Gasolines , 1993 .

[3]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[4]  A. Kai Qin,et al.  Evolutionary extreme learning machine , 2005, Pattern Recognit..

[5]  Gu Guobiao,et al.  The Simulation and the Experimental Research of the Stator Bars' Evaporative Cooling System in the Three Gorges' Hydrogenerator , 2006, 2006 CES/IEEE 5th International Power Electronics and Motion Control Conference.

[6]  Barry K. Lavine,et al.  Genetic algorithm for fuel spill identification , 2001 .

[7]  Lin Ruan,et al.  Numerical simulation for circulating systems and experimental comparison of the closed-loop, self-circulating evaporative cooling of hydrogenerators , 2004 .

[8]  RUAN LIN,et al.  Research of the Temperature Distribution of the Hollow Conductor in the Evaporative Cooling Hydro-Generators , 2005 .

[9]  Narasimhan Sundararajan,et al.  Fully complex extreme learning machine , 2005, Neurocomputing.

[10]  Chee Kheong Siew,et al.  Can threshold networks be trained directly? , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[11]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[12]  J. K. Hardy,et al.  Accelerant classification by gas chromatography/mass spectrometry and multivariate pattern recognition , 2000 .