The through-flow method still plays an important role in the design of modern aero-engine, and its accuracy depends on the loss and deviation model. The presence of tip clearance will impact the deviation distribution, while the retained lift is somewhat related to this effect. To achieve a more precise deviation model, this paper utilises the machine learning approach. The database comprises cascades with tip clearances in training, from which obtains a span-wise deviation model and executes its validation by comparing with experiment result. The database is obtained by calculating 16 different geometries of the cascades with tip clearance in different working conditions, introducing the geometrical parameters of the cascades and retained lift as feature engineering. The deviation and the retained lift follow the same trend with tip clearance size and operating conditions variation. We predict the span-wise distribution of the retained lift using the k-nearest neighbour regression, and then combine with the traditional model to get the distribution of the deviation. The results show that the coefficient of determination of the retained lift coefficient prediction in the test set reaches 81.02%, and the mean absolute error is around 1.32%. Moreover, the trend predictions of cascade deviation distribution for different tip clearance size are all in good agreement with the experimental results. The coefficient of determination of the prediction with the simulation is 75.23%, and the mean absolute error is 1.74%.
HU Haojie
,
JIN Donghai
. Analysis of Compressor Cascade Deviation and Surrogate Model Construction Based on Retained Lift[J]. Journal of Thermal Science, 2025
, 34(2)
: 567
-578
.
DOI: 10.1007/s11630-024-2069-y
[1] Liu X.H., Jin D.H., Gui X.M., Investigation and verification of the aerodynamic performance of a fan/booster with through-flow method. Journal of Thermal Science, 2018, 27(2): 103–110.
[2] Jin H.L., Jin D.H., Li X.J., et al., A time-marching through-flow model and its application in transonic axial compressor. Journal of Thermal Science, 2010, 19(6): 519–525.
[3] Yang C., Wu H., Yang J.G., et al., Time-marching through-flow analysis of multistage axial compressors based on a novel inviscid blade force model. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2019, 233(14): 5239–5252.
[4] Carter A.D.S., The low speed performance of related aerofoils in cascades. California Institute of Technology Mechaiaical, 1950.
[5] Cetin M., Uecer A.S., Hirsch C., et al., Application of modified loss and deviation correlations to transonic axial compressors. NASA Report, 1987, Report No. NASA-AGARD-745.
[6] Creveling H.F., Axial-flow compressor computer program for calculating off-design performance. NASA Report, 1968, NASA-CR-72472.
[7] Miller D.C., Wasdell D.L., Off-design prediction of compressor blade losses. Turbomachinery—Efficiency Prediction and Improvement, IMechE, London, UK, Paper No. C279/87, 1987.
[8] Roberts W.B., Serovy G.K., Sandercock D.M., Design point variation of 3-D loss and deviation for axial compressor middle stages. Proceedings of ASME, 1988, Paper No. 88-GT-57.
[9] Rains D.A., Tip clearance flows in axial flow compressors and pumps. California Institute of Technology Pasadena Mechanical Engineering Lab, 1954.
[10] Lakshminarayana B., Methods of predicting the tip clearance effects in axial flow turbomachinery. Journal of Basic Engineering, 1970, 92(3): 467–480.
[11] Williams R., Gregory-Smith D., He L., et al., Experiments and computations on large tip clearance effects in a linear cascade. Proceedings of the ASME, 2010, Paper No. 021018. DOI:10.1115/gt2008-50557.
[12] Bammert K., Kläukens H., Hartmann D., Der Einfluß des radialen Schaufelspaltes auf den Wirkungsgrad mehrstufiger Turbinen. VDI-Z., 1968, 110(10): 390–395.
[13] Willinger R., Haselbacher H., Axial turbine tip-leakage losses at off-design incidences. Proceedings of the ASME Turbo Expo: Power for Land, Sea, and Air, 2004, pp. 993–1002
[14] Brunton S.L., Noack B.R., Koumoutsakos P., Machine learning for fluid mechanics. Annual Review of Fluid Mechanics, 2020, 52: 477–508.
[15] Yukuan S., Zhijun L., Xin-Gen L., et al., Optimization of a lobed mixer with BP neural network and genetic algorithm. Journal of Thermal Science, 2023, 32(1): 387–400.
[16] Pierret S., Van den Braembussche R.A., Turbomachinery blade design using a Navier-Stokes solver and artificial neural network. Journal of Turbomachinery, 1999, 121(3): 326–332.
[17] Schmitz A., Aulich M., Nicke E., Novel approach for loss and flow-turning prediction using optimized surrogate models in two-dimensional compressor design. Proceedings of the ASME Turbo Expo: Power for Land, Sea, and Air, 2011, 54679: 1103–1114.
[18] Wu X., Liu B., Chen Z., Application of surrogate model in through-flow of axial compressor. Journal of Propulsion Technology, 2021, 42(1): 123–138. (in Chinese)
[19] Yue Z.X., Zhou C.H., Jin D.H., Gui X.M., A spanwise loss model for axial compressor stator based on machine learning. Chinese Journal of Aeronautics, 2022, 35(11): 74–84.
[20] Lieblein S., Schwenk F.C., Broderick R.L., Diffusion factor for estimating losses and limiting blade loadings in axial-flow-compressor blade elements. NACA Technical Report, 1953, No. RME53D01.
[21] Lakshminarayana B., Horlock J.H., Tip clearance flow and losses for an isolated compressor blade. British A.R.C. Report & Memorandum 3316, 1962.
[22] Lewis R.I., Yeung E.H.C., Vortex shedding mechanisms in relation to tip clearance flows and losses in an axial fan. British A.R.C. Report & Memorandum 3829, 1977.
