Aerodynamic design and optimization of blade end wall profile of turbomachinery based on series convolutional neural network

• Published in: Energy (Oxford) 2022-04, Vol.244, p.122617, Article 122617
• Main Authors: Du, Qiuwan, Yang, Like, Li, Liangliang, Liu, Tianyuan, Zhang, Di, Xie, Yonghui
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer architecture; Convolutional neural network; Deep learning; Design; Design improvements; Design optimization; End wall profile; Flow rates; Gaussian process; Low aspect ratio; Mass flow rate; Neural networks; Optimization; Performance prediction; Regression models; Sensitivity analysis; Stator blades; Stators; Training; Turbines; Turbomachinery
• ISSN: 0360-5442; 1873-6785
• DOI: 10.1016/j.energy.2021.122617

End wall contraction is an effective approach to reduce the substantial secondary loss in the cascade with low aspect ratio. This paper proposed a series convolutional neural network architecture (SCNN) to improve the design optimization problem of end wall profile of a turbine stator blade. The specific implementation of the architecture is discussed in detail. The effect of the train size and sensitivity analysis of design variables are carried out. Finally, the optimization is completed by the gradient descent method, and the aerodynamic performance of end wall profile before and after optimization is compared. It shows that the SCNN architecture performs outstandingly with 30% training data. It can quickly and accurately provide rich flow field information and performance parameters within 3 ms after training. When the train size is 0.3, the mean prediction errors of mass flow rate and efficiency of each sample are lower than 0.1%, which performs significantly better than the Artificial Neural Network and Gaussian Process Regression model. When the stator blade adopts optimized contracted end wall profile, the power and efficiency are raised by 4.43% and 1.39% respectively with the mass flow rate only changing by 1.48%, which verifies the feasibility of the SCNN architecture. •The SCNN model is established to reconstruct flow field and predict performance.•High prediction accuracy and fast solving speed are achieved by SCNN model.•The sensitivity analysis of the design variables is carried out.•The optimization of end wall profile is completed with gradient descent method.