Aircraft sensor fault detection based on temporal two-dimensionalization

基于时序二维化的航空传感器故障检测

¹ School of Artificial Intelligence, OPtics and ElectroNics(iOPEN), Northwestern Polytechnical University, Xi'an 710072, China
² Chinese Flight Test Establishment, Xi'an 710089, China

Received: 14 July 2023

Abstract

Aerial sensor fault detection is of great importance in flight missions. However, the dimensionality of sensor time-series data is extremely high and the time span is extremely long, which lead to poor detection performance of existing methods. To address these problems, this paper proposes a time-series to 2D fault detection (T2D) method for aerial sensor fault detection based on time-series. Firstly, the information entropy is applied to the classification and aggregation approximation algorithm to achieve effective compression of the data while fully retaining the time-series features. Secondly, the gramian angular field is introduced to encode the reduced-dimensional data into two-dimensional images, maintaining the long-range dependence of the original sequence. Finally, a flexible convolution block is designed and inserted into the encoder of the detection network Vision Transformer to improve the detection accuracy of the model. Experimental results show that the T2D model performs significantly better than other models on a simulated time-series dataset of a civilian aircraft test flight, indicating the effectiveness and superiority of the proposed method.

摘要

航空传感器故障检测在航空飞行任务中具有重要意义。然而传感器时序数据长度极长、时间跨度极广导致目前大多数方法检测性能较差。针对上述问题, 提出基于时序二维化的航空传感器故障检测(time-series to 2D fault detection, T2D)方法。将信息熵应用到分段聚合近似算法中, 充分保留时序特征的同时实现对数据的有效压缩；引入格拉姆角场将降维后的一维数据编码为二维图像, 维持原始序列的长程依赖性；设计一种灵活的卷积映射模块并插入检测网络Vision Transformer的编码器中, 提高模型的检测精度。实验结果表明, T2D模型在某民机试飞仿真时序数据集上, 性能显著优于其他模型, 验证了所提方法的有效性和优越性。