Data-Driven Reduced-Order Model for Efficient Temperature Prediction of Gas Turbine Blades

doi:10.16183/j.cnki.jsjtu.2024.284

Abstract

Abstract:

Turbine blades are key hot components of gas turbines, which operates in high temperature and harsh environment. Accurate and efficient prediction of turbine blade temperature field is of great significance for the safety and stability of gas turbine service. In this paper, first, a turbine blade fluid-thermal-solid coupling model is developed for different start-up conditions of gas turbines. Then, numerical simulations are conducted to form a dataset of turbine blade temperature field. Finally, an efficient prediction method for turbine blade temperature field is proposed by combining neural network with model order reduction technique, which can predict the temperature field of the turbine blade using on-site sensor data. The results show that compared with the high-fidelity fluid-thermal-solid numerical simulations, the proposed method can efficiently predict the temperature field of the turbine blade in milliseconds with a relative error less than 12%, which provides a feasible approach for real-time monitoring of three-dimensional temperature field of turbine blades.

Key words: turbine blade, reduced-order model, neural network, temperature prediction

CLC Number:

TK477

QIAO Lijie, DONG Han, FENG Keyun, LI Zizhou, HAO Chen, WANG Weizhe, ZHAO Xinbao. Data-Driven Reduced-Order Model for Efficient Temperature Prediction of Gas Turbine Blades[J]. Journal of Shanghai Jiao Tong University, 2026, 60(6): 1026-1033.

Figures/Tables 9

Fig.1

Fig.2

Tab.1

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

References 17

[1]	CHOWDHURY T S, MOHSIN F T, TONNI M M, et al. A critical review on gas turbine cooling performance and failure analysis of turbine blades[J]. International Journal of Thermofluids, 2023, 18: 100329. doi: 10.1016/j.ijft.2023.100329 URL
[2]	伍赛特. 燃气轮机技术应用与未来发展趋势展望[J]. 节能, 2024, 43(4): 118-122.
	WU Saite. Application and future development trends of gas turbine technology[J]. Energy Conservation, 2024, 43(4): 118-122.
[3]	杨晓明, 张丽, 焦腾, 等. 涡轮叶片三维温度场耦合计算[J]. 机械设计与制造, 2012(8): 18-20.
	YANG Xiaoming, ZHANG Li, JIAO Teng, et al. Three-dimensional temperature field of turbine blades based on coupling calculation[J]. Machinery Design & Manufacture, 2012(8): 18-20.
[4]	ZENG F, WANG K C, SHI Z, et al. Three-dimensional temperature reconstruction strategy for turbine blades using infrared thermography at simulated-engine conditions[J]. Experimental Thermal & Fluid Science, 2024, 155: 111201.
[5]	KIM K M, PARK J S, LEE D H, et al. Analysis of conjugated heat transfer, stress and failure in a gas turbine blade with circular cooling passages[J]. Engineering Failure Analysis, 2011, 18(4): 1212-1222. doi: 10.1016/j.engfailanal.2011.03.002 URL
[6]	GERANMAYEH A, MALEKAN M, FORGHANI F, et al. Microstructural and mechanical investigations on the heat treatment rejuvenation of a long-term service-exposed GTD-111 Ni-based superalloy[J]. Materials Science & Engineering: A, 2023, 862: 144381.
[7]	李宗全, 牛夕莹, 安仲玉, 等. 双层涡轮叶片应力计算与分析[J]. 热能动力工程, 2024, 39(2): 11-18.
	LI Zongquan, NIU Xiying, AN Zhongyu, et al. Strength calculation and analysis of double-layer turbine blade[J]. Journal of Engineering for Thermal Energy & Power, 2024, 39(2): 11-18.
[8]	WANG Y, MA H H, CAI W H, et al. A POD-Galerkin reduced-order model for two-dimensional Rayleigh-Bénard convection with viscoelastic fluid[J]. International Communications in Heat & Mass Transfer, 2020, 117: 104747.
[9]	BOCCIARELLI M, BULJAK V, MOY C K S, et al. An inverse analysis approach based on a POD direct model for the mechanical characterization of metallic materials[J]. Computational Materials Science, 2014, 95: 302-308. doi: 10.1016/j.commatsci.2014.07.025 URL
[10]	LI Z J, HU J X, TANG Z B. POD method for solving elastodynamics problems of functionally gradient materials based on radial integration boundary element method[J]. Engineering Analysis with Boundary Elements, 2024, 160: 173-186. doi: 10.1016/j.enganabound.2023.12.026 URL
[11]	JIANG G H, KANG M, CAI Z W, et al. Data-dri-ven temperature estimation of non-contact solids using deep-learning reduced-order models[J]. International Journal of Heat & Mass Transfer, 2022, 185: 122383.
[12]	BUI-THANH T, DAMODARAN M, WILLCOX K. Aerodynamic data reconstruction and inverse design using proper orthogonal decomposition[J]. AIAA Journal, 2004, 42(8): 1505-1516. doi: 10.2514/1.2159 URL
[13]	RAJARAM D, PERRON C, PURANIK T G, et al. Randomized algorithms for non-intrusive parametric reduced order modeling[J]. AIAA Journal, 2020, 58(12): 5389-5407. doi: 10.2514/1.J059616 URL
[14]	张志鑫, 曾武, 卞祥德, 等. 热障涂层对涡轮动叶温度及应力的影响研究[J]. 推进技术, 2023, 44(5): 225-238.
	ZHANG Zhixin, ZENG Wu, BIAN Xiangde, et al. Effects of thermal barrier coating on temperature and stress of turbine rotor blade[J]. Journal of Propulsion Technology, 2023, 44(5): 225-238.
[15]	CAI L X, HE Y, WANG S S, et al. Thermal-fluid-solid coupling analysis on the temperature and thermal stress field of a nickel-base superalloy turbine blade[J]. Materials, 2021, 14(12): 3315. doi: 10.3390/ma14123315 URL
[16]	FEUERSTEIN A, KNAPP J, TAYLOR T, et al. Technical and economical aspects of current thermal barrier coating systems for gas turbine engines by thermal spray and EBPVD: A review[J]. Journal of Thermal Spray Technology, 2008, 17(2): 199-213. doi: 10.1007/s11666-007-9148-y URL
[17]	JIANG G H, KANG M, CAI Z W, et al. Online reconstruction of 3D temperature field fused with POD-based reduced order approach and sparse sensor data[J]. International Journal of Thermal Sciences, 2022, 175: 107489. doi: 10.1016/j.ijthermalsci.2022.107489 URL

温度/K	热导率/ [W·(m·K)^-1]	比热容/ [J·(kg·K)^-1]
298.15	8.45	469
373.15	10	474
473.15	11.95	482
573.15	13.8	491
673.15	15.5	501
773.15	17.1	511
873.15	18.55	522
973.15	19.85	534
1073.15	21	547
1173.15	22	561
1273.15	22.8	575