|
|
论文:2023,Vol:41,Issue(6):1033-1043 |
|
|
引用本文： |
|
|
张达, 高君宇, 丁腾欢, 谷士鹏, 李学龙. 基于时序二维化的航空传感器故障检测[J]. 西北工业大学学报 |
|
|
ZHANG Da, GAO Junyu, DING Tenghuan, GU Shipeng, LI Xuelong. Aircraft sensor fault detection based on temporal two-dimensionalization[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于时序二维化的航空传感器故障检测 |
|
| 张达1, 高君宇1, 丁腾欢2, 谷士鹏2, 李学龙1 |
|
1. 西北工业大学 光电与智能研究院, 陕西 西安 710072;
2. 中国飞行试验研究院, 陕西 西安 710089 |
| 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。 |
| 关键词:
航空传感器
故障检测
时间序列分析
分段聚合近似
格拉姆角场
|
|
| Aircraft sensor fault detection based on temporal two-dimensionalization |
|
| ZHANG Da1, GAO Junyu1, DING Tenghuan2, GU Shipeng2, LI Xuelong1 |
|
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 |
| 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. |
| Key words:
aircraft sensor
fault detection
time series analysis
piece-wise aggregate approximation
gramian angular field
|
|
| 收稿日期: 2023-07-14
修回日期:
|
| DOI: 10.1051/jnwpu/20234161033 |
| 基金项目: 中国飞行试验研究院项目(H2022129,H2022197)资助 |
| 通讯作者: 李学龙(1976-),西北工业大学教授,主要从事临地安防、图像和信号处理及成像研究。e-mail:li@nwpu.edu.cn
Email：li@nwpu.edu.cn |
| 作者简介: 张达(2000-),西北工业大学博士研究生,主要从事临地安防、人工智能及时序数据分析研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 李学龙. 临地安防[J]. 中国计算机学会通讯, 2022, 18(11): 44-52 LI Xuelong. Vicinagearth security[J]. Communications of the CCF, 2022, 18(11): 44-52 (in Chinese)
[2] 闫媞锦, 夏元清, 张宏伟, 等. 一种非规则采样航空时序数据异常检测方法[J]. 航空学报, 2021, 42(4): 525019 YAN Tijin, Xia Yuanqing, ZHANG Hongwei, et al. An anomaly detection method for irregularly sampled spacecraft time series data[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 525019 (in Chinese)
[3] YANG H, GAO J Y, YUAN Y, et al. Imbalanced aircraft data anomaly detection[J/OL]. (2023-05-17)[2023-07-05]. https://doi.org/10.48550/arXiv.2305.10082
[4] 高君宇, 张达, 李学龙. 基于多尺度表征的航空时序数据故障检测[C]//第六届中国航空科学技术大会, 2023 GAO Junyu, ZHANG Da, LI Xuelong. Fault detection of aircraft time series based on multi-scale representation[C]//The 6th China Aeronautical Science and Technology Conference, 2023 (in Chinese)
[5] 高君宇, 尹阁豪, 李学龙. 智能航空传感器故障诊断一体化架构设计[C]//第六届中国航空科学技术大会, 2023 GAO Junyu, YIN Gehao, LI Xuelong. Fault diagnosis of convolutional neural networks based on data of aeroplane sensors[C]//The 6th China Aeronautical Science and Technology Conference, 2023 (in Chinese)
[6] 于广伟, 闫莉. 基于多尺度迁移符号动力学熵和支持向量机的轴承诊断方法研究[J]. 西北工业大学学报, 2023, 41(2): 344-353 YU Guangwei, YAN Li. A novel bearing fault diagnosis method based on multi-scale transfer symbolic dynamic entropy and support vector machine[J]. Journal of Northwestern Polytechnical University, 2023, 41(2): 344-353 (in Chinese)
[7] CUI L, Zhang Q, SHI Y, et al. A method for satellite time series anomaly detection based on fast-DTW and improved-KNN[J]. Chinese Journal of Aeronautics, 2023, 36(2): 149-159
[8] WANG L, HU Z, TIAN A, et al. An inconsistency fault diagnosis method for lithium-ion cells in the battery pack based on piecewise dimensionality reduction and outlier identification[J]. Journal of Electrochemical Energy Conversion and Storage, 2023, 20(1): 011016
[9] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[C]//Proceedings of the 9th International Conference on Learning Representations, 2021
[10] 丁建立, 邹云开, 王静, 等. 基于深度学习的ADS-B异常数据检测模型[J]. 航空学报, 2019, 40(12): 167-177 DING Jianli, ZOU Yunkai, WANG Jing, et al. ADS-B anomaly data detection model based on deep learning[J]. Acta Aeronautics et Astronautica Sinica, 2019, 40(12): 167-177 (in Chinese)
[11] GOLAN I, EL-YANIV R. Deep anomaly detection using geometric transformations[C]//Proceedings of Advances in Neural Information Processing Systems, 2018
[12] 何家辉, 程志君, 郭波. 联合字典学习与OCSVM的遥测数据异常检测方法[J]. 航空学报, 2023, 44(8): 327931 HE Jiahui, CHENG Zhijun, GUO Bo. Telemetry anomaly detection method based on joint dictionary learning and OCSVM[J]. Acta Aeronautics et Astronautica Sinica, 2023, 44(8): 327931 (in Chinese)
[13] 杨昊, 高君宇, 李学龙. 基于自适应重采样的试飞数据异常检测[C]//第六届中国航空科学技术大会, 2023 YANG Hao, GAO Junyu, LI Xuelong. Anomaly detection of flight test data based on adaptive resampling[C]//The 6th China Aeronautical Science and Technology Conference, 2023 (in Chinese)
[14] 王志凯, 陈盛, 范玮. 神经网络宽度对燃烧室排放预测的影响[J]. 航空学报, 2023, 44(5): 126816 WANG Zhikai, CHEN Sheng, FAN Wei. Effect of neural network width on combustor emission prediction[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(5): 126816 (in Chinese)
[15] ZHANG Y M, ZHAO H, MA J Y, et al. A deep neural network-based fault detection scheme for aircraft IMU sensors[J]. International Journal of Aerospace Engineering, 2021, 2021: 1-13
[16] DONG Y Q. An application of deep neural networks to the in-flight parameter identification for detection and characterization of aircraft icing[J]. Aerospace Science and Technology, 2018, 77: 34-49
[17] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 3th International Conference on Learning Representations, 2015
[18] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778
[19] 李忠智, 马金毅, 艾剑良, 等. 拟VGG16网络的航空传感器故障检测分类研究[J]. 航空学报, 2023, 44(增刊1): 727615 LI Zhongzhi, MA Jinyi, AI Jianliang, et al. Fault detection and classification of aerospace sensors using deep neural networks fine-tuned from VGG16[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(suppl1): 727615 (in Chinese)
[20] MICJAIL T, ERIK C, STEFANOS Z. ViTs for SITS: vision transformers for satellite image time series[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2023
[21] KEOGH E J, PAZZANI M J. A simple dimensionality reduction technique for fast similarity search in large time series databases[C]//Proceedings of the 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Current Issues and New Applications, 2000: 122-133
[22] WANG Z, OATES T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[C]//AAAI Conference on Artificial Intelligence, 2015: 40-46
[23] WU H, XIAO B, CODELLA N, et al. CVT: introducing convolutions to vision transformers[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 22-31
[24] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125
[25] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C]//Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 1992: 144-152
[26] ROSENBLATT F. Principles of neurodynamics. Perceptrons and the theory of brain mechanisms[J]. Archives of General Psychiatry, 1962, 7(3): 218-219
[27] SHERSTINSKY A. Fundamentals of recurrent neural network(RNN) and long short-term memory(LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306
[28] ZHOU B, CUI Q, WEI X S, et al. BBN: Bilateral-Branch network with cumulative learning for long-tailed visual recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9719-9728
[29] PASZKE A, GROSS S, CHINTALA S, et al. Automatic differentiation in pytorch[J/OL](2017-10-28)[2023-07-05]. https://openreview.net/forum?id=BJJsrmfCZ
[30] VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579-2605 |
|
|
|
|
|
|
|
