THERMAL SCIENCE

International Scientific Journal

Yiwei Ding

,

Jian Ai

,

Jinxiu Chen

,

Lin Ruan

PHYSICS-GUIDED FEATURE SELECTION FOR TEMPERATURE PREDICTION OF STATOR WINDING'S HOLLOW CONDUCTORS IN EVAPORATIVE COOLING HYDROGENERATORS

ABSTRACT
Accurate temperature prediction for hollow conductors in evaporative cooling hydrogenerators is critical for design optimization but hampered by the high cost of experiments and simulations. To address this, this paper proposes a physics-guided surrogate modeling framework using experimental data from 12 conductor designs. An optimized Gaussian Process Regression (GPR) model is shown to outperform Random Forest and XGBoost, reducing RMSE by 16.2% and 9.7%, respectively. The framework identifies two physically distinct feature subsets for complementary use cases. A six-feature (6D) monitoring model that achieves ?2=0.893 and RMSE =1.770 ∘? under random 5-fold cross-validation, and a four-feature (4D) design model that obtains pooled ?2=0.616 and RMSE =3.200 ∘? under rigorous Leave-One-Group-Out (LOGO) validation, sufficient for ranking candidate designs. The analysis further identifies outlet measurements as information-leaking features that inflate within-design accuracy but degrade extrapolation to unseen geometries, highlighting the importance of causal feature selection for robust design-stage surrogate models.
KEYWORDS
hydrogenerator, evaporative cooling, Surrogate modeling, feature selection, Gaussian process regression, particle swarm optimization
PAPER SUBMITTED: 2026-01-26
PAPER REVISED: 2026-03-27
PAPER ACCEPTED: 2026-04-03
PUBLISHED ONLINE: 2026-06-20
DOI REFERENCE: https://doi.org/10.2298/TSCI260126072D
REFERENCES
[1] Gu, G., Ruan, L., Applications And Developments Of The Evaporative Cooling Technology In The Field Of Hydrogenerators, Proc. CSEE, 34 (2014), 29, pp. 5112-5119
[2] Yuan, J., et al., Applied engineering design of three gorges' 840MVA hydro-generator with close loop self circulating evaporative cooling system, Proceedings, Proceedings of the 11th international conference on electrical machines and systems (ICEMS), 2008, pp. 1-6
[3] Lin, R., et al., The evaluation of the design and operation of the 400MW evaporative cooling hydrogenerator in lijiaxia hydropower station, Proceedings, Proceedings of the 2015 18th international conference on electrical machines and systems (ICEMS), 2015, pp. 1-5
[4] Kurul, N., Podowski, M.Z., MULTIDIMENSIONAL EFFECTS IN FORCED CONVECTION SUBCOOLED BOILING, Proceedings, Proceeding of International Heat Transfer Conference 9, Jerusalem, Israel, 1990, pp. 21-26
[5] Krepper, E., et al., CFD Modelling Of Subcooled Boiling—Concept, Validation And Application To Fuel Assembly Design, Nucl. Eng. Des., 237 (2007), 7, pp. 716-731
[6] Krepper, E., Rzehak, R., CFD For Subcooled Flow Boiling: Simulation Of DEBORA Experiments, Nucl. Eng. Des., 241 (2011), 9, pp. 3851-3866
[7] Yang, J., Wang, Z., A Simple And Accurate Method For Estimating The Stator Winding Real-Time Temperature Of Air-Cooled Hydrogenerator, Therm. Sci., 27 (2023), 1A, pp. 167-177
[8] Ruan, L., et al., Different Influence Of Cooling Method To Stator Bar Insulation Characteristics In Pumped Storage Units, Trans. China Electrotech. Soc., 32 (2017), 14, pp. 246-251
[9] Ebbs-Picken, T., et al., Hierarchical Thermal Modeling And Surrogate-Model-Based Design Optimization Framework For Cold Plates Used In Battery Thermal Management Systems, Appl. Therm. Eng., 253 (2024), pp. 123599
[10] Santiago Galicia, E., et al., Machine Learning-Driven Prediction Of Heat Transfer Coefficients For Pure Refrigerants In Diverse Heat Exchangers Types, J. Exp. Theor. Anal., 3 (2025), 4, pp
[11] Qiu, Y., et al., An Artificial Neural Network Model To Predict Mini/Micro-Channels Saturated Flow Boiling Heat Transfer Coefficient Based On Universal Consolidated Data, Int. J. Heat Mass Transf., 149 (2020), pp. 119211
[12] Hughes, M.T., et al., Status, Challenges, And Potential For Machine Learning In Understanding And Applying Heat Transfer Phenomena, J. Heat Transf., 143 (2021), 12, pp. 120802
[13] Saltelli, A., et al., Global Sensitivity Analysis. The Primer, Proceedings, December 18
[14] Sobol′, I.M., Global Sensitivity Indices For Nonlinear Mathematical Models And Their Monte Carlo Estimates, Math. Comput. Simul., 55 (2001), 1-3, pp. 271-280
[15] Pudil, P., et al., Floating Search Methods In Feature Selection, Pattern Recognit. Lett., 15 (1994), 11, pp. 1119-1125
[16] Wei, P., et al., Variable Importance Analysis: A Comprehensive Review, Reliab. Eng. Syst. Saf., 142 (2015), pp. 399-432
[17] Sudret, B., Global Sensitivity Analysis Using Polynomial Chaos Expansions, Reliab. Eng. Syst. Saf., 93 (2008), 7, pp. 964-979
[18] Rohsenow, W.M., et al., Handbook Of Heat Transfer, McGraw-Hill, New York
[19] Mckay, M.D., et al., A Comparison Of Three Methods For Selecting Values Of Input Variables In The Analysis Of Output From A Computer Code, Technometrics, 42 (2000), 1, pp. 55-61
[20] Standardization Administration of China, Glass-fiber wound winding wires. Part 1: Glass-fiber wound rectangular copper wire. General requirements, Report No. GB/T 7672.1-2008, Standards Press of China
[21] Rasmussen, C.E., Williams, C.K.I., Gaussian Processes For Machine Learning, MIT Press, Cambridge, MA
[22] Breiman, L., Random Forests, Mach. Learn., 45 (2001), 1, pp. 5-32
[23] Chen, T., Guestrin, C., XGBoost: a scalable tree boosting system, Proceedings, Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 785-794
PDF VERSION [DOWNLOAD]
Physics-guided feature selection for temperature prediction of stator winding's hollow conductors in evaporative cooling hydrogenerators

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 International licence