Empirical Modeling of Cryogenic System for Hybrid SFCL Using Support Vector Regression
- PDF / 855,993 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 61 Downloads / 182 Views
O R I G I N A L PA P E R
Empirical Modeling of Cryogenic System for Hybrid SFCL Using Support Vector Regression In-Yong Seo · Ok-Bae Hyun · Heesun Kim · Bok-Nam Ha · Il-Keun Song · Wookyu Chae · Min-Jee Kim · Seong-Jun Kim
Received: 2 November 2012 / Accepted: 1 December 2012 / Published online: 28 December 2012 © Springer Science+Business Media New York 2012
Abstract The hybrid superconducting fault current limiter (SFCL) is now at the stage of practical use in a power grid in Korea. A cryogenic cooling system was designed, fabricated, and successfully tested for a prototype of 22.9 kV/630 A SFCL. The operation scheme of cryogenic system has been investigated in preparation for temporary loss of cryocooler power in hybrid SFCL (in Kim et al., IEEE Trans. Appl. Supercond. 21(3):1284–1287, 2011). In this paper, we investigated the empirical modeling of cryogenic cooling system for SFCL using principal components and auto-associative support vector regression (PCSVR) for the prediction and fault detection of the cryogenic cooling system. For empirical model, data were acquired during a blackout test of cryogenic cooling system. Blackout times of the test were 1 hour and 4 hours at two operation current levels. Three set of data were used for training and optimization of the model and the rest set of data was used for verification. Signals for the model are temperatures measured at copper band and cold head of cryocooler, system pressure and liquid temperatures measured at two locations in liquid-nitrogen pool. For optimization of the SVR parameters, the response surface method (RSM) and particle swarm optimization (PSO) were adopted in this paper. After I.-Y. Seo () · O.-B. Hyun · H. Kim · B.-N. Ha · I.-K. Song · W. Chae KEPCO Research Institute, 65 Munji-Ro Yuseong-Gu, 305-760, Daejeon, Korea e-mail: [email protected] M.-J. Kim Electrotechnology R&D Center of LSIS, 360-545, Cheongju, Korea S.-J. Kim Gangneung-Wonju National University, 210-702, Gangneung, Korea
developing the empirical model we analyzed the accuracy of the model. Also, these results were compared with that of auto-associative neural networks (AANN). RSM and PSO gave almost the same optimum point. PCSVR showed much better performance than AANN in accuracy aspects. Moreover, this model can be used for the prognosis of cryogenic cooling system for SFCL. Keywords Superconducting fault current limiter · Cryogenic cooling · Support vector regression · Response surface method · Particle swarm optimization
1 Introduction Development of hybrid superconducting fault current limiter (SFCL) in Korea is now at the final stage for practical use in power grid. An excellent cryogenic cooling system was designed, fabricated, and successfully tested for a prototype of 22.9 kV/630 A SFCL. Since 2009, the unmanned system has been operated stably in a test grid over several months with real-time remote monitoring. Operation scheme of cryogenic system is investigated in preparation for temporary loss of cryocooler power in hybrid SFCL [1]. The purpose of the SFCL con
Data Loading...
