Aerodynamic Design Method of Low Pressure Turbine Blade Profile Based on Optimal Load Distribution Model Optimization

Abstract

The invention discloses a low-pressure turbine blade shape aerodynamic design method optimized based on an optimal load distribution model. The method generates blade geometry samples according to a given blade shape parameter value range and low-dimensional aerodynamic design parameters, and uses CFD Calculate the optimal load distribution when the total pressure loss of the blade is the smallest, and generate the blade database; build the optimal load distribution model based on the multi-output Gaussian process and the deep neural network, and according to the training samples in the blade database, by minimizing the margin The likelihood loss function is used to train the optimal load distribution model to obtain the hyperparameter group in the optimal load distribution model; according to the optimal load distribution model after training, the target optimal load distribution of the target low-dimensional aerodynamic design parameters is calculated, The optimal aerodynamic airfoil corresponding to the target optimal load distribution is calculated by using the airfoil inverse design model. The design method of the invention can improve the precision and efficiency of the aerodynamic design of the turbine blade shape, and shorten the design cycle of the turbine blade shape geometry.

Description

Technical field [0001] The present invention relates to the field of turbine blaming design, and in particular, a low pressure turbine pneumatic design method based on optimal load distribution model optimization. Background technique [0002] The turbine is a key component of the aerospace engine. It is an impeller mechanical device that transforms high temperature and high pressure gas into an impeller mechanical device, which has a very important impact on aerodynamic performance, economical and environmentally friendly of the entire engine. [0003] Turbo gas design is often facing complex design requirements, and aerodynamic performance is very sensitive to geometric changes, many design requirements and geometric variables together, constitute high-dimensional design space, making it difficult to obtain corresponding global optimal optimal optimal optimal analysis Solution, can only be based on test or computational fluid dynamics (CFD) values, simulate the evaluation of tu...

AI Technical Summary

Problems solved by technology

[0003] Turbine aerodynamic design usually faces complex design requirements, and aerodynamic performance is very sensitive to geometric changes. Many design requirements and geometric variables are coupled together to form a high-dimensional design space, making it difficult to obtain the corresponding global optimum from theoretical quantitative analysis. However, it can only simulate and evaluate the aerodynamic performance of turbine blades based on experiments or computational fluid dynamics (Computational Fluid Dynamics, CFD) values, and rely on experts or use gradient or stochastic optimization methods to iteratively optimize the geometric parameters of the blade.

[0004] However, the existing aerodynamic design methods usually require high-precision CFD iterative calculations. For example, in the patent application with the publication number CN112380794A, a multi-disciplinary parallel collaborative optimization design method for aero turbine engine blades is disclosed. This type of design method is computationally expensive. , The design cycle is long, and most of them are optimized based on the gradient method, which is easy to fall into the local minimum

[0005] Although the surrogate model based on neural network or Gaussian process regression can be used to reduce the time consumption of CFD calculation, the calculation accuracy of such surrogate model is relatively poor, and with the gradual increase of design variables in the surrogate model, such The surrogate model algorithm faces a serious dimensionality disaster problem, which makes it impossible to establish a general surrogate model between a wide range of design conditions and airfoil geometry and aerodynamic performance

Images