Quick Access Recorder (QAR) data contains a large number of flight parameters used to record flight information during flight, and is increasingly utilized to analyze and evaluate flight safety. Feature extraction of QAR data is a prerequisite for further analysis in many applications and studies and therefore an important research topic. In this study, a sequence-parameter attention based convolutional autoencoder (SPA-CAE) model is proposed for feature extraction of QAR data. Data landed at Changshui Airport in Kunming were used as experimental data and the results show that our model is better able to perform feature extraction of QAR data and discover the distribution pattern of extracted features.
Feature Extraction of QAR Data via Sequence-Parameter Attention Based Convolutional Autoencoder Model
20.10.2021
1710625 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Autoencoder-based feature extraction for power time series data considering social information
British Library Conference Proceedings | 2023
|