Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation
Synthetic sensors enable flight data estimation without devoted physical sensors. Within modern digital avionics, synthetic sensors can be implemented and used for several purposes such as analytical redundancy or monitoring functions. The angle of attack, measured at air data system level, can be e...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2021/9982722 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546005563736064 |
|---|---|
| author | Angelo Lerro Piero Gili Mario Luca Fravolini Marcello Napolitano |
| author_facet | Angelo Lerro Piero Gili Mario Luca Fravolini Marcello Napolitano |
| author_sort | Angelo Lerro |
| collection | DOAJ |
| description | Synthetic sensors enable flight data estimation without devoted physical sensors. Within modern digital avionics, synthetic sensors can be implemented and used for several purposes such as analytical redundancy or monitoring functions. The angle of attack, measured at air data system level, can be estimated using synthetic sensors exploiting several solutions, e.g., model-based, data-driven, and model-free state observers. In the class of data-driven observers, multilayer perceptron neural networks are widely used to approximate the input-output mapping angle-of-attack function. Dealing with experimental flight test data, the multilayer perceptron can provide reliable estimation even though some issues can arise from noisy, sparse, and unbalanced training domain. An alternative is offered by regularization networks, such as radial basis function, to cope with training domain based on real flight data. The present work’s objective is to evaluate performances of a single-layer feed-forward generalized radial basis function network for AoA estimation trained with a sequential algorithm. The proposed analysis is performed comparing results obtained using a multilayer perceptron network adopting the same training and validation data. |
| format | Article |
| id | doaj-art-a648d456ed4243ed8d61db26ab4b5767 |
| institution | Kabale University |
| issn | 1687-5966 1687-5974 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj-art-a648d456ed4243ed8d61db26ab4b57672025-02-03T07:24:12ZengWileyInternational Journal of Aerospace Engineering1687-59661687-59742021-01-01202110.1155/2021/99827229982722Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack EstimationAngelo Lerro0Piero Gili1Mario Luca Fravolini2Marcello Napolitano3Department of Mechanical and Aerospace Engineering, Polytechnic University of Turin, C.so Duca degli Abruzzi 24, Turin 10129, ItalyDepartment of Mechanical and Aerospace Engineering, Polytechnic University of Turin, C.so Duca degli Abruzzi 24, Turin 10129, ItalyDepartment of Electronic and Information Engineering, University of Perugia, Via G. Duranti 93, Perugia 06125, ItalyDepartment of Mechanical and Aerospace Engineering, West Virginia University Morgantown, P.O. Box 6106, Morgantown, WV 26506, USASynthetic sensors enable flight data estimation without devoted physical sensors. Within modern digital avionics, synthetic sensors can be implemented and used for several purposes such as analytical redundancy or monitoring functions. The angle of attack, measured at air data system level, can be estimated using synthetic sensors exploiting several solutions, e.g., model-based, data-driven, and model-free state observers. In the class of data-driven observers, multilayer perceptron neural networks are widely used to approximate the input-output mapping angle-of-attack function. Dealing with experimental flight test data, the multilayer perceptron can provide reliable estimation even though some issues can arise from noisy, sparse, and unbalanced training domain. An alternative is offered by regularization networks, such as radial basis function, to cope with training domain based on real flight data. The present work’s objective is to evaluate performances of a single-layer feed-forward generalized radial basis function network for AoA estimation trained with a sequential algorithm. The proposed analysis is performed comparing results obtained using a multilayer perceptron network adopting the same training and validation data.http://dx.doi.org/10.1155/2021/9982722 |
| spellingShingle | Angelo Lerro Piero Gili Mario Luca Fravolini Marcello Napolitano Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation International Journal of Aerospace Engineering |
| title | Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation |
| title_full | Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation |
| title_fullStr | Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation |
| title_full_unstemmed | Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation |
| title_short | Experimental Analysis of Neural Approaches for Synthetic Angle-of-Attack Estimation |
| title_sort | experimental analysis of neural approaches for synthetic angle of attack estimation |
| url | http://dx.doi.org/10.1155/2021/9982722 |
| work_keys_str_mv | AT angelolerro experimentalanalysisofneuralapproachesforsyntheticangleofattackestimation AT pierogili experimentalanalysisofneuralapproachesforsyntheticangleofattackestimation AT mariolucafravolini experimentalanalysisofneuralapproachesforsyntheticangleofattackestimation AT marcellonapolitano experimentalanalysisofneuralapproachesforsyntheticangleofattackestimation |