Numerical investigation and modeling of sweep effects on inlet flow field of axial compressor cascades

Swept blades are widely utilized in transonic compressors/fans and provide high load,high through-flow,high efficiency,and adequate stall margin.However,there is limited quantitative research on the mechanism of the effect of swept blades on the flow field,resulting in a lack of direct quantitative guidance for the design and analysis of swept blades in fans/compressors.To better understand this mechanism,this study employs a reduced-dimensional force equilibrium method to analyze more than 1500 swept cascades data.Results verify that circumferential fluctuation terms are responsible for inducing radial migration in the inlet airflow field of the swept blade,resulting in variations in the incidence angle and consequently leading to changes in the characteristics of the swept blade.Thus,a combination of simple functions and machine learning is utilized to model the circumferential fluctuation terms and quantify the sweep mechanism.The prediction accuracy of the model is high,with coefficient of determination greater than 0.95 on the test set.When the model is applied in a meridional flow analysis program,the calculation accuracy of the program for the incidence angle is improved by 0.4°and 0.6°at the design and off-design conditions respectively,compensating for the program’s original deficiencies.Meanwhile,the model can also provide quantitative guidance for the design of swept blades,thereby reducing the number of design iterations and improving design efficiency.

A spanwise loss model for axial compressor stator based on machine learning

In the early stage of aircraft engine design, the through-flow method is an important tool for designers. The accuracy of the through-flow method depends heavily on the accuracy of the loss model. However, most existing models cannot(or cannot well) provide the spanwise loss distribution. To construct an effective spanwise loss model, both turbomachinery knowledge and machine learning skills were used in this paper. A large number of numerical simulations were carried out to build a database containing more than 1000 compressor cascade numerical samples. Secondary flow intensity was introduced as the independent variable to carry out feature engineering. A model containing a selector based on support vector machine regression and estimators based on K-nearest neighbor regression was constructed. Numerical test set and design data of two former highpressure core compressors were used for validation. Results suggest that the spanwise loss model show good consistency with both numerical test set and data of two former compressors. It can reflect the influence of secondary flow and can also predict both value and trend of total pressure loss coefficient well, with mean absolute error general around or less than 1% and R^(2)(coefficient of determination) more than 0.8 on the test set. Especially when dealing with loss coefficient at midspan position, the model shows even better performance, with R^(2)over 0.97 on the test set. And the selector of the model can well classify the samples, predict the intensity of secondary flow and help estimators to capture the phenomenon that end-wall secondary flow extends to the mid-span.