An Intellectual Aerodynamic Design Method for Compressors Based on Deep Reinforcement Learning

Xu, Xiaohan; Huang, Xudong; Bi, Dianfang; Zhou, Ming

doi:10.3390/aerospace10020171

Cited by 4 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compressor design plays an important role in overall engine performance. For this reason, artificial intelligence methods are already widely used by modern compressor design teams [5].…”

Section: Introductionmentioning

confidence: 99%

Upgrading the Compressor Stage of the CAT250TJ Micro Gas Turbine Engine

van Eck,

van der Spuy

2024

Aerotec. Missili Spaz.

View full text Add to dashboard Cite

Due to their simplicity and relative ease of manufacture, single-stage centrifugal and mixed flow micro gas turbine (MGT) engines are preferred in thrust-based remotely piloted aerial vehicles. A single-stage mixed-flow compressor upgrade for the 200 N CAT250TJ MGT engine is numerically evaluated and presented. An in-house developed mean line application and commercial CFD software is used for the design and performance evaluation of the proposed upgrade configurations. The CAT250TJ – Gen1 engine features a single-stage centrifugal compressor, annular combustor, and single stage axial turbine. Apart from an upgraded impeller, a new crossover diffuser configuration is introduced to replace the wedge-type, straight outlet diffuser configuration of the Gen1 engine. The new single vane crossover diffuser configuration provides a design point total-to-total efficiency and pressure ratio increase of 8.3% and 12.1%, respectively. A disadvantage of a single-vaned crossover diffuser compared to legacy diffusers is a narrower operating range. To alleviate this issue, various combinations of tandem and splitter vane crossover diffuser configurations are proposed. These provide an enhanced operating range, comparable with the operating range displayed by the Gen1 configuration. A turbine power matching analysis is additionally completed to ensure proper compressor integration. Gas turbine cycle software is used to evaluate the on-engine performance of the upgraded compressor configurations. It is shown that the new baseline, single vane crossover diffuser configuration provides a 10.74% increase in design point static thrust.

show abstract

“…Compressor design plays an important role in overall engine performance. For this reason, artificial intelligence methods are already widely used by modern compressor design teams [5].…”

Section: Introductionmentioning

confidence: 99%

Upgrading the Compressor Stage of the CAT250TJ Micro Gas Turbine Engine

van Eck,

van der Spuy

2024

Aerotec. Missili Spaz.

View full text Add to dashboard Cite

show abstract

Aerodynamic force prediction of compressor blade surfaces based on machine learning

Niu,

Zhao,

Yao

et al. 2024

Physics of Fluids

View full text Add to dashboard Cite

The flow field distribution of compressor blades is critical to the performance of aero-engine. To efficiently obtain the aerodynamic loads on the blades, this study employs machine learning models to predict the aerodynamic characteristics of compressor blade surfaces. The predictive performances of these models are evaluated by applying random forest, multi-layer perceptron (MLP), one-dimensional convolutional neural network, and long short-term memory network based on simulation data of computational fluid dynamics (CFD). The results indicate that the MLP model performs exceptionally well among all test metrics, with its predictions closely matching the CFD simulation results. Further analysis using SHapley Additive exPlanations methods is performed to interpret the MLP model and reveal the importance of various input features. The research demonstrates the significant potential of machine learning methods in predicting the aerodynamics of compressor blades and providing accurate and reliable results.

show abstract

Integration of deep learning and computational fluid dynamics for rapid aerodynamic force prediction of compressor blades

Niu,

Zhao,

Yang

et al. 2024

Physics of Fluids

View full text Add to dashboard Cite

The distribution of flow fields around compressor blades is crucial for the performance and reliability of aircraft engines. To effectively obtain aerodynamic loads, this study combines deep learning with computational fluid dynamics (CFD) to develop an efficient aerodynamic prediction model. Initially, CFD is used to acquire detailed flow field data for the blade surface and its surrounding environment. Subsequently, a distance field parameterization method is applied to process the blade geometry, and deep learning models are used to capture the complex relationship between blade geometry and aerodynamic parameters with high precision. The results indicate that the proposed model can predict aerodynamic loads within seconds with a mean squared error of less than 2%. Compared to traditional parameterization methods and other deep learning approaches, this model exhibits higher accuracy. The findings highlight the effectiveness of integrating deep learning with CFD to enhance aerodynamic predictions and provide a promising approach for future aerodynamic modeling research.

show abstract

An Intellectual Aerodynamic Design Method for Compressors Based on Deep Reinforcement Learning

Cited by 4 publications

References 39 publications

Upgrading the Compressor Stage of the CAT250TJ Micro Gas Turbine Engine

Upgrading the Compressor Stage of the CAT250TJ Micro Gas Turbine Engine

Aerodynamic force prediction of compressor blade surfaces based on machine learning

Integration of deep learning and computational fluid dynamics for rapid aerodynamic force prediction of compressor blades

Contact Info

Product

Resources

About