A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation
Accurate component maps, which can significantly affect the efficiency, reliability and availability of aero-engines, play a critical role in aero-engine performance simulation. Unfortunately, the information of component maps is insufficient, leading to substantial limitations in practical applicat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/9/8/442 |
| _version_ | 1797440234753884160 |
|---|---|
| author | Wenxiang Zhou Sangwei Lu Jinquan Huang Muxuan Pan Zhongguang Chen |
| author_facet | Wenxiang Zhou Sangwei Lu Jinquan Huang Muxuan Pan Zhongguang Chen |
| author_sort | Wenxiang Zhou |
| collection | DOAJ |
| description | Accurate component maps, which can significantly affect the efficiency, reliability and availability of aero-engines, play a critical role in aero-engine performance simulation. Unfortunately, the information of component maps is insufficient, leading to substantial limitations in practical application, wherein compressors are of particular interest. Here, a data-driven-based compressor map generation approach for transient aero-engine performance adaptation is investigated. A multi-layer perceptron neural network is utilized in simulating the compressor map instead of conventional interpolation schemes, and an adaptive variable learning rate backpropagation (ADVLBP) algorithm is employed to accelerate the convergence and improve the stability in the training process. Aside from that, two different adaptation strategies designed for steady state and transient conditions are implemented to adaptively retrain the compressor network according to measurement deviations until the accuracy requirements are satisfied. The proposed method is integrated into a turbofan component-level model, and simulations reveal that the ADVLBP algorithm has the capability of more rapid convergence compared with conventional training algorithms. In addition, the maximum absolute measurement deviation decreased from 6.35% to 0.44% after steady state adaptation, and excellent agreement between the predictions and benchmark data was obtained after transient adaptation. The results demonstrate the effectiveness and superiority of the proposed component map generation method. |
| first_indexed | 2024-03-09T12:05:14Z |
| format | Article |
| id | doaj.art-ef776c076f154327813b4ef8d5197cca |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-09T12:05:14Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-ef776c076f154327813b4ef8d5197cca2023-11-30T23:00:02ZengMDPI AGAerospace2226-43102022-08-019844210.3390/aerospace9080442A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance AdaptationWenxiang Zhou0Sangwei Lu1Jinquan Huang2Muxuan Pan3Zhongguang Chen4Jiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaAECC Shenyang Engine Design Institute, Shenyang 110066, ChinaAccurate component maps, which can significantly affect the efficiency, reliability and availability of aero-engines, play a critical role in aero-engine performance simulation. Unfortunately, the information of component maps is insufficient, leading to substantial limitations in practical application, wherein compressors are of particular interest. Here, a data-driven-based compressor map generation approach for transient aero-engine performance adaptation is investigated. A multi-layer perceptron neural network is utilized in simulating the compressor map instead of conventional interpolation schemes, and an adaptive variable learning rate backpropagation (ADVLBP) algorithm is employed to accelerate the convergence and improve the stability in the training process. Aside from that, two different adaptation strategies designed for steady state and transient conditions are implemented to adaptively retrain the compressor network according to measurement deviations until the accuracy requirements are satisfied. The proposed method is integrated into a turbofan component-level model, and simulations reveal that the ADVLBP algorithm has the capability of more rapid convergence compared with conventional training algorithms. In addition, the maximum absolute measurement deviation decreased from 6.35% to 0.44% after steady state adaptation, and excellent agreement between the predictions and benchmark data was obtained after transient adaptation. The results demonstrate the effectiveness and superiority of the proposed component map generation method.https://www.mdpi.com/2226-4310/9/8/442aero-enginecomponent map generationtransient performanceadaptation strategyneural network |
| spellingShingle | Wenxiang Zhou Sangwei Lu Jinquan Huang Muxuan Pan Zhongguang Chen A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation Aerospace aero-engine component map generation transient performance adaptation strategy neural network |
| title | A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation |
| title_full | A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation |
| title_fullStr | A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation |
| title_full_unstemmed | A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation |
| title_short | A Novel Data-Driven-Based Component Map Generation Method for Transient Aero-Engine Performance Adaptation |
| title_sort | novel data driven based component map generation method for transient aero engine performance adaptation |
| topic | aero-engine component map generation transient performance adaptation strategy neural network |
| url | https://www.mdpi.com/2226-4310/9/8/442 |
| work_keys_str_mv | AT wenxiangzhou anoveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT sangweilu anoveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT jinquanhuang anoveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT muxuanpan anoveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT zhongguangchen anoveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT wenxiangzhou noveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT sangweilu noveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT jinquanhuang noveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT muxuanpan noveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation AT zhongguangchen noveldatadrivenbasedcomponentmapgenerationmethodfortransientaeroengineperformanceadaptation |