To study the feasibility of using machine learning technology to solve the forward problem (prediction of aerodynamic parameters) and the inverse problem (prediction of geometric parameters) of turbine blades, this paper built a forward problem model based on backpropagation artificial neural networks (BP-ANNs) and an inverse problem model based on radial basis function artificial neural networks (RBF-ANNs). The S2 (a stream surface obtained by extending a radial curve in turbo blades) calculation program was used to generate the dataset for single-stage turbo blades, and the back propagation algorithm was used to train the model. The parameters of five blade sections in a single-stage turbine were selected as inputs of the forward problem model, including stagger angle, inlet geometric angle, outlet geometric angle, wedge angle of leading edge pressure side, wedge angle of leading edge suction side, wedge angle of trailing edge, rear bending angle, and leading edge diameter. The outputs are efficiency, power, mass flow, relative exit Mach number, absolute exit Mach number, relative exit flow angle, absolute exit flow angle and reaction degree, which are eight aerodynamic parameters. The inputs and outputs of the inverse problem model are the opposite of that of the forward problem model. The models can accurately predict the aerodynamic parameters and geometric parameters, and the mean square errors (MSEs) of the forward problem test set and the inverse problem test set are 0.001 and 0.000 35, respectively. This study shows that machine learning technology based on neural networks can be flexibly applied to the design of forward and inverse problems of turbine blades, and the models built by this method have practical application value in regression prediction problems.
ZHOU Haimeng
,
YU Kaituo
,
LUO Qiao
,
LUO Lei
,
DU Wei
,
WANG Songtao
. Design Methods and Strategies for Forward and Inverse Problems of Turbine Blades Based on Machine Learning[J]. Journal of Thermal Science, 2022
, 31(1)
: 82
-95
.
DOI: 10.1007/s11630-022-1544-6
[1] Daneshkhah K., Ghaly W., Aerodynamic inverse design for viscous flow in turbomachinery blading. Journal of Propulsion and Power, 2015, 23(4): 814–820.
[2] Brynjolfsson E., Mitchell T., Rock D., What can machines learn, and what does it mean for occupations and the economy? Social Science Electronic Publishing, 2018, 108: 43–47.
[3] Müller S., Milano M., Koumoutsakos P., Application of machine learning algorithms to flow modeling and optimization. Annual Research Brief, 1999, pp. 169–178.
[4] Sekar V., Jiang Q., Shu C., Fast flow field prediction over airfoils using deep learning approach. Physics of Fluids, 2019, 31(5): 057103.
[5] Peifeng L.I., Zhang B., Yingchun C., Aerodynamic design methodology for blended wing body transport. Chinese Journal of Aeronautics, 2012, 25(4): 508–516.
[6] Guo X., Li W., Iorio F., Convolutional neural networks for steady flow approximation. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp. 481–490.
[7] Du W., Luo L., Yinghou J., Heat transfer in the trailing region of gas turbines-a state-of-the-art review. Applied Thermal Engineering, 2021, 119: 117614.
[8] Du W., Luo L., Wang S., Film cooling in the trailing edge cutback with different land shapes and blowing ratios. International Communications in Heat and Mass Transfer, 2021, 125: 105311.
[9] Dávalos J.O., García J.C., Urquiza G., Prediction of film cooling effectiveness on a gas turbine blade leading edge using ANN and CFD. International Journal of Turbo and Jet-Engines, 2018, 35(2): 101–111.
[10] Yang L., Dai W., Rao Y., Optimization of the hole distribution of an effusively cooled surface facing non-uniform incoming temperature using deep learning approaches. International Journal of Heat and Mass Transfer, 2019, 145: 118749.
[11] Renganathan S.A., Maulik R., Ahuja J., Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization. Aerospace Science and Technology, 2021, 111: 106522.
[12] Ren L H., Ye Z.F., Zhao Y.P., A modeling method for aero-engine by combining stochastic gradient descent with support vector regression. Aerospace Science and Technology, 2020, 99: 105775.
[13] Yan X., Zhu J., Kuang M., Aerodynamic shape optimization using a novel optimizer based on machine learning techniques. Aerospace Science and Technology, 2019, 86: 826–835.
[14] Joly M., Sarkar S., Mehta D., Machine learning enabled adaptive optimization of a transonic compressor rotor with precompression. Journal of Turbomachinery, 2019, 141(5): 051011.
[15] Campobasso M.S., Cavazzini A., Minisci E., Rapid estimate of wind turbine energy loss due to blade leading edge delamination using artificial neural networks. Journal of Turbomachinery, 2020, 142(7): 071002.
[16] Gharehghani A., Abbasi H.R., Alizadeh P., Application of machine learning tools for constrained multi-objective optimization of an HCCI engine. Energy, 2021, 233: 121106.
[17] Sun R., Shi L., Yang X., A coupling diagnosis method of sensors faults in gas turbine control system. Energy, 2020, 205: 117999.
[18] Nielson J,, Bhaganagar K., Meka R., Using atmospheric inputs for Artificial Neural Networks to improve wind turbine power prediction. Energy, 2020, 190: 116273.
[19] Pritchard L.J., An eleven parameter axial turbine airfoil geometry model. Turbo Expo: Power for Land, Sea, and Air. American Society of Mechanical Engineers, 1985. DOI: 10.1115/85-GT-219.
[20] Gan X.S., Yang C., Gao H.L., Optimization design of structure and parameters for RBF neural network using hybrid hierarchy genetic algorithm. Advanced Materials Research, 2014, 951: 274–277.
[21] Sun Y., Deep learning face representation by joint identification-verification. The Chinese University of Hong Kong, 2015.
[22] Milani P.M., Ling J., Eaton J.K., Generalization of machine-learned turbulent heat flux models applied to film cooling flows. Journal of Turbomachinery, 2019, 142(1): 011007.
