Research Article
Study of Synthetic Airspeed Algorithm Based on Machine Learning for Lift Coefficient Curve Fitting
@INPROCEEDINGS{10.4108/eai.27-8-2020.2297157, author={Dianzhong Chen and Yue Xu and Lei Wang}, title={Study of Synthetic Airspeed Algorithm Based on Machine Learning for Lift Coefficient Curve Fitting}, proceedings={Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace}, publisher={EAI}, proceedings_a={MOBIMEDIA}, year={2020}, month={11}, keywords={airspeed calculation algorithm support vector regression (svr)}, doi={10.4108/eai.27-8-2020.2297157} }- Dianzhong Chen
Yue Xu
Lei Wang
Year: 2020
Study of Synthetic Airspeed Algorithm Based on Machine Learning for Lift Coefficient Curve Fitting
MOBIMEDIA
EAI
DOI: 10.4108/eai.27-8-2020.2297157
Abstract
Traditional air data system of airplane utilizes pitot probe for airspeed measurement. However, problems such as icing and bird strike will lead to failure of pitot probe. Airspeed display loss is rated as disastrous loss status. Airspeed calculation algorithm based on inertial data and movable surface positions (status of flaps and slats) has been studied by the Boeing Company and the Airbus Company and applied in airplane models of Boeing 787 and Airbus A350. Commercial Airplane of China has been dedicated in studying algorithm of airspeed calculation. Study indicates the importance of accurate lift coefficient identification for different flight configurations under certain attack angles. Theoretical analysis indicates the relationship of piecewise linearity between lift coefficient and attack angle. Based on the above relationship, machine learning algorithm of support vector regression (SVR) is applied to process air data. Furthermore, synthetic airspeed algorithm is proposed and verified.
