Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks
Hall thrusters function as power plants on spacecraft, and its development is crucial for the aerospace industry. The wall erosion of the on-orbit Hall thruster cannot be measured by the control center through ground measurement, but can obtain the discharge current low-frequency oscillation data. T...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022029048 |
| _version_ | 1798014451367018496 |
|---|---|
| author | Ke Han Fang Xie Yu Wang Lei Zhang Mengyao Yu Jianchun Wang Ying Wang Jie Wan |
| author_facet | Ke Han Fang Xie Yu Wang Lei Zhang Mengyao Yu Jianchun Wang Ying Wang Jie Wan |
| author_sort | Ke Han |
| collection | DOAJ |
| description | Hall thrusters function as power plants on spacecraft, and its development is crucial for the aerospace industry. The wall erosion of the on-orbit Hall thruster cannot be measured by the control center through ground measurement, but can obtain the discharge current low-frequency oscillation data. Therefore, this study proposes an inversion method to obtain the wall erosion information based on low-frequency oscillation signals and neural networks. Firstly, we use an improved one-dimensional quasi-neutral dynamic fluid mathematical model to build a low-frequency oscillation simulation platform which obtains the corresponding data by varying the cross-sectional area. Secondly, a nonlinear neural network model is established based on the obtained low-frequency oscillation data to invert the wall erosion information. The training function, transfer function, number of hidden layer nodes, and other parameters affecting the results are analyzed and the best model parameters are obtained. The Elman neural network is established and compared with the BP neural network and RBF neural network. The training results of the Elman neural network algorithm present small and stable errors, and the results of multiple predictions remain consistent. The root means square error, average absolute error, and average absolute percentage are 0.0084, 0.0637, and 0.045%, respectively. |
| first_indexed | 2024-04-11T15:18:27Z |
| format | Article |
| id | doaj.art-c62a54d530574ade93b3390f13b0c1a1 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-11T15:18:27Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-c62a54d530574ade93b3390f13b0c1a12022-12-22T04:16:26ZengElsevierHeliyon2405-84402022-11-01811e11616Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networksKe Han0Fang Xie1Yu Wang2Lei Zhang3Mengyao Yu4Jianchun Wang5Ying Wang6Jie Wan7School of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin 150028, ChinaLaboratory for Space Environment and Physical Sciences, Harbin Institute of Technology, Harbin, 150001, China; Corresponding author.Hall thrusters function as power plants on spacecraft, and its development is crucial for the aerospace industry. The wall erosion of the on-orbit Hall thruster cannot be measured by the control center through ground measurement, but can obtain the discharge current low-frequency oscillation data. Therefore, this study proposes an inversion method to obtain the wall erosion information based on low-frequency oscillation signals and neural networks. Firstly, we use an improved one-dimensional quasi-neutral dynamic fluid mathematical model to build a low-frequency oscillation simulation platform which obtains the corresponding data by varying the cross-sectional area. Secondly, a nonlinear neural network model is established based on the obtained low-frequency oscillation data to invert the wall erosion information. The training function, transfer function, number of hidden layer nodes, and other parameters affecting the results are analyzed and the best model parameters are obtained. The Elman neural network is established and compared with the BP neural network and RBF neural network. The training results of the Elman neural network algorithm present small and stable errors, and the results of multiple predictions remain consistent. The root means square error, average absolute error, and average absolute percentage are 0.0084, 0.0637, and 0.045%, respectively.http://www.sciencedirect.com/science/article/pii/S2405844022029048Hall thrusterLow-frequency oscillationNeural networkWall erosionInformation inversion |
| spellingShingle | Ke Han Fang Xie Yu Wang Lei Zhang Mengyao Yu Jianchun Wang Ying Wang Jie Wan Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks Heliyon Hall thruster Low-frequency oscillation Neural network Wall erosion Information inversion |
| title | Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks |
| title_full | Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks |
| title_fullStr | Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks |
| title_full_unstemmed | Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks |
| title_short | Study on inversion method of wall erosion information of on-orbit Hall thruster based on low-frequency oscillation signals and neural networks |
| title_sort | study on inversion method of wall erosion information of on orbit hall thruster based on low frequency oscillation signals and neural networks |
| topic | Hall thruster Low-frequency oscillation Neural network Wall erosion Information inversion |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022029048 |
| work_keys_str_mv | AT kehan studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT fangxie studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT yuwang studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT leizhang studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT mengyaoyu studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT jianchunwang studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT yingwang studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks AT jiewan studyoninversionmethodofwallerosioninformationofonorbithallthrusterbasedonlowfrequencyoscillationsignalsandneuralnetworks |