A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors
A new fault detection scheme for aircraft Inertial Measurement Unit (IMU) sensors is developed in this paper. This scheme adopts a deep neural network with a CNN-LSTM-fusion architecture (CNN: convolution neural network; LSTM: long short-term memory). The fault detection network (FDN) developed in t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2021/3936826 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545902680604672 |
|---|---|
| author | Yiming Zhang Hang Zhao Jinyi Ma Yunmei Zhao Yiqun Dong Jianliang Ai |
| author_facet | Yiming Zhang Hang Zhao Jinyi Ma Yunmei Zhao Yiqun Dong Jianliang Ai |
| author_sort | Yiming Zhang |
| collection | DOAJ |
| description | A new fault detection scheme for aircraft Inertial Measurement Unit (IMU) sensors is developed in this paper. This scheme adopts a deep neural network with a CNN-LSTM-fusion architecture (CNN: convolution neural network; LSTM: long short-term memory). The fault detection network (FDN) developed in this paper is irrelative to aircraft model or flight condition. Flight data is reformed into a 2D format for FDN input and is mapped via the net to fault cases directly. We simulate different aircrafts with various flight conditions and separate them into training and testing sets. Part of the aircrafts and flight conditions appears only in the testing set to validate robustness and scalability of the FDN. Different architectures of FDN are studied, and an optimized architecture is obtained via ablation studies. An average detecting accuracy of 94.5% on 20 different cases is achieved. |
| format | Article |
| id | doaj-art-11c60613475445338e94da20c6b5d76a |
| institution | Kabale University |
| issn | 1687-5966 1687-5974 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj-art-11c60613475445338e94da20c6b5d76a2025-02-03T07:24:24ZengWileyInternational Journal of Aerospace Engineering1687-59661687-59742021-01-01202110.1155/2021/39368263936826A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU SensorsYiming Zhang0Hang Zhao1Jinyi Ma2Yunmei Zhao3Yiqun Dong4Jianliang Ai5Department of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaDepartment of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaDepartment of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaDepartment of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaDepartment of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaDepartment of Aeronautics and Astronautics, Fudan University, Shanghai 200433, ChinaA new fault detection scheme for aircraft Inertial Measurement Unit (IMU) sensors is developed in this paper. This scheme adopts a deep neural network with a CNN-LSTM-fusion architecture (CNN: convolution neural network; LSTM: long short-term memory). The fault detection network (FDN) developed in this paper is irrelative to aircraft model or flight condition. Flight data is reformed into a 2D format for FDN input and is mapped via the net to fault cases directly. We simulate different aircrafts with various flight conditions and separate them into training and testing sets. Part of the aircrafts and flight conditions appears only in the testing set to validate robustness and scalability of the FDN. Different architectures of FDN are studied, and an optimized architecture is obtained via ablation studies. An average detecting accuracy of 94.5% on 20 different cases is achieved.http://dx.doi.org/10.1155/2021/3936826 |
| spellingShingle | Yiming Zhang Hang Zhao Jinyi Ma Yunmei Zhao Yiqun Dong Jianliang Ai A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors International Journal of Aerospace Engineering |
| title | A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors |
| title_full | A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors |
| title_fullStr | A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors |
| title_full_unstemmed | A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors |
| title_short | A Deep Neural Network-Based Fault Detection Scheme for Aircraft IMU Sensors |
| title_sort | deep neural network based fault detection scheme for aircraft imu sensors |
| url | http://dx.doi.org/10.1155/2021/3936826 |
| work_keys_str_mv | AT yimingzhang adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT hangzhao adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT jinyima adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT yunmeizhao adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT yiqundong adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT jianliangai adeepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT yimingzhang deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT hangzhao deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT jinyima deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT yunmeizhao deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT yiqundong deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors AT jianliangai deepneuralnetworkbasedfaultdetectionschemeforaircraftimusensors |