Imbalanced Flight Test Sensor Temporal Data Anomaly Detection
- 7 October 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 61 (2) , 2466-2476
Abstract
The functioning of flight test sensors is crucial for aviation safety, but previous methods often overlooked the impact of data imbalance on model performance while exploring anomalies in aviation data. Imbalances in aviation time-series data can lead to the following issues: 1) Varying sizes of feature spaces lead to the majority class overshadowing the minority class; 2) Small inter-class differences in the model result in a bias towards predicting the majority class; 3) Imbalanced algorithms causes the model to lack learning of general features. To alleviate these problems, this paper proposes the Imbalanced Flight test sensor temporal data Anomaly Detection (IFAD) model. Firstly, a dual-branch network is designed where one branch is trained on original data distribution for general feature learning, and the other on resampled data to enhance learning of anomalous aviation data features. Secondly, a normalization module is introduced to standardize feature and weight vectors for a quantifiable decision boundary, along with an angle constraint for greater class differentiation. Finally, an adaptive reweighting algorithm (CVLoss) is implemented to balance the loss between different categories using cosine sample variance. Extensive ablation studies demonstrate that each proposed module enhances model performance. The IFAD model, when benchmarked against the baseline network, notably excels in the Flights dataset, achieving improvements in accuracy, recall, and F1 score by 18.93%, 27.16%, and 12.43% respectively, affirming its efficacy and superiority in detecting anomalies in flight test data.Keywords
Funding Information
- National Natural Science Foundation of China (62306241, 61871470)
This publication has 39 references indexed in Scilit:
- Learning from Temporal Aviation Data to Detect Anomaly Events2023
- A hybrid data-driven framework for satellite telemetry data anomaly detectionActa Astronautica, 2023
- Congested crowd instance localization with dilated convolutional swin transformerNeurocomputing, 2022
- An end-to-end framework for flight trajectory data analysis based on deep autoencoder networkAerospace Science and Technology, 2022
- Short-term Transmission Line load and State Evaluation method based on improved gradient lifting Stochastic Forest algorithmIOP Conference Series: Earth and Environmental Science, 2021
- K-Means-based isolation forestKnowledge-Based Systems, 2020
- Space event detection method based on cluster analysis of satellite historical orbital dataActa Astronautica, 2019
- Outlier Detection and Missing Value in Seasonal ARIMA Model Using Rainfall Data*Materials Today: Proceedings, 2018
- Convolutional Neural Network Based Fault Detection for Rotating MachineryJournal of Sound and Vibration, 2016
- Cluster-based under-sampling approaches for imbalanced data distributionsExpert Systems with Applications, 2009