ACTA AERONAUTICAET ASTRONAUTICA SINICA >
Fault detection and classification of aerospace sensors using deep neural networks finetuned from VGG16
Received date: 2022-06-01
Revised date: 2022-06-15
Accepted date: 2022-06-22
Online published: 2022-06-24
Supported by
Shanghai Sailing Program(20YF1402500);Natural Science Foundation of Shanghai(22ZR1404500)
Following the research advances in machine vision， a concept defined as imagification-based intelligence has been proposed. A fault detection and classification method of fault detection and classification was developed using a deep neural network finetuned from VGG16， which originally was designed for image detection and classification problems. Firstly， a database corresponding to 4 aerospace vehicles and 5 flight conditions were constructed via both flight simulations and real-vehicle tests. Faults of aerospace sensors and inertial measurement unit are included in the database. Secondly， we proposed to stack the measurement data of aerospace sensors into a grayscale image， which was used to transfer the fault detection and classification problem into abnormal regions detection problem on the image. Thirdly， the size of the grayscale image was augmented to match the input size of VGG16， and the fault detection neural network was developed via finetuning the VGG16 directly. The experimental results on several aircraft show that the average test accuracy of the network reaches 97.6%. Following the explainability analysis methods in machine vision， Class Activation Mapping （CAM） results of different layers of the fault detection neural network were plotted， which solidifies the performance of the proposed neural network.
Zhongzhi LI , Jinyi MA , Jianliang AI , Yiqun DONG . Fault detection and classification of aerospace sensors using deep neural networks finetuned from VGG16[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023 , 44(S1) : 727615 -727615 . DOI: 10.7527/S1000-6893.2022.27615
| 1 | GOUPIL P. AIRBUS state of the art and practices on FDI and FTC in flight control system［J］. Control En-gineering Practice， 2011， 19（6）： 524-539. |
| 2 | GOUPIL P， BOADA-BAUXELL J， MARCOS A，et al. AIRBUS efforts towards advanced real-time fault diagnosis and fault tolerant control［J］. IFAC Proceedings Volumes， 2014， 47（3）： 3471-3476. |
| 3 | YEH Y C. Triple-triple redundant 777 primary flight computer［C］∥1996 IEEE Aerospace Applications Conference. Piscataway： IEEE Press， 1996： 293-307. |
| 4 | COLLINSON R P G. Fly-by-wire flight control［M］∥Introduction to Avionics Systems. Dordrecht： Springer， 2011： 179-253. |
| 5 | DANGUT M D， SKAF Z， JENNIONS I K. An integrated machine learning model for aircraft components rare failure prognostics with log-based dataset［J］. ISA transactions， 2021， 113： 127-139. |
| 6 | CRUZ B， OLIVEIRA D M. Crashed boeing 737-MAX： Fatalities or malpractice［J］. Global Scientific Journals， 2020， 8（1）： 2615-2624. |
| 7 | DONG Y Q， TAO J， ZHANG Y M， et al. Deep learning in aircraft design， dynamics， and control： Review and prospects［J］. IEEE Transactions on Aerospace and Electronic Systems， 2021， 57（4）： 2346-2368. |
| 8 | ZHAO R， YAN R Q， CHEN Z H，et al. Deep learning and its applications to machine health monitoring［J］. Mechanical Systems and Signal Processing， 2019， 115： 213-237. |
| 9 | VAN EYKEREN L， CHU Q P. Sensor fault detection and isolation for aircraft control systems by kinematic relations［J］. Control Engineering Practice， 2014， 31： 200-210. |
| 10 | LU P， VAN EYKEREN L， VAN KAMPEN E， et al. Adaptive three-step Kalman filter for air data sensor fault detection and diagnosis［J］. Journal of Guidance， Control， and Dynamics， 2016， 39（3）： 590-604. |
| 11 | LU P， VAN EYKEREN L， VAN KAMPEN E J， et al. Air data sensor fault detection and diagnosis with application to real flight data： AIAA-2015-1311［R］. Reston： AIAA， 2015. |
| 12 | WAN Y M， KEVICZKY T. Real-time fault-tolerant moving horizon air data estimation for the reconfigure benchmark［J］. IEEE Transactions on Control Systems Technology， 2018， 27（3）： 997-1011. |
| 13 | CASTALDI P， MIMMO N， SIMANI S. Avionic air data sensors fault detection and isolation by means of singular perturbation and geometric approach［J］. Sensors， 2017， 17（10）： 2202. |
| 14 | CASTALDI P， GERI W， BONFE M， et al. Design of residual generators and adaptive filters for the FDI of aircraft model sensors［J］. Control Engineering Practice， 2010， 18（5）： 449-459. |
| 15 | 马亚杰， 任好， 姜斌. 基于自适应多设计融合航天器近距离操作的执行器故障补偿技术研究［J］. 飞控与探测， 2020， 3（3）： 25-32. |
| MA Y J， REN H， JIANG B. Multi-design integration based adaptive fault-tolerant control of spacecraft proximity operations［J］. Flight Control & Detection， 2020， 3（3）： 25-32 （in Chinese）. | |
| 16 | YU X， FU Y， PENG X Y. Fuzzy logic aided fault-tolerant control applied to transport aircraft subject to actuator stuck failures［J］. IEEE Transactions on Fuzzy Systems， 2018， 26（4）： 2050-2061. |
| 17 | WANG B， ZHANG Y M， ZHANG W. A composite adaptive fault-tolerant attitude control for a quadrotor UAV with multiple uncertainties［J］.Journal of Systems Science and Complexity， 2022， 35（1）： 81-104. |
| 18 | YU Y S， DONG Y Q. Global fault-tolerant control of underactuated aerial vehicles with redundant actuators［J］. International Journal of Aerospace Engineering， 2019， 2019： 1-12. |
| 19 | GURURAJAN S， FRAVOLINI M L， CHAO H Y， et al. Performance evaluation of neural network based approaches for airspeed Sensor Failure Accommodation on a small UAV［C］∥21st Mediterranean Conference on Control and Automation. Piscataway： IEEE Press， 2013： 603-608. |
| 20 | HUSSAIN S， MOKHTAR M， HOWE J M. Sensor failure detection， identification， and accommodation using fully connected cascade neural network［J］. IEEE Transactions on Industrial Electronics， 2015， 62（3）： 1683-1692. |
| 21 | HUSSAIN S， MOKHTAR M， HOWE J M. Aircraft sensor estimation for fault tolerant flight control system using fully connected cascade neural network［C］∥The 2013 International Joint Conference on Neural Networks （IJCNN）. Piscataway： IEEE Press， 2013： 1-8. |
| 22 | FRAVOLINI M L， RHUDY M， GURURAJAN S， et al. Experimental evaluation of two pitot free analytical redundancy techniques for the estimation of the airspeed of an UAV［J］. SAE International Journal of Aerospace， 2014， 7（1）： 109-116. |
| 23 | REDDY K K， SARKAR S， VENUGOPALAN V， et al. Anomaly detection and fault disambiguation in large flight data： A multi-modal deep auto-encoder approach［C］∥Annual Conference of the PHM Society， 2018. |
| 24 | GAO Z H， MA C B， SONG D，et al. Deep quantum inspired neural network with application to aircraft fuel system fault diagnosis［J］. Neurocomputing， 2017， 238： 13-23. |
| 25 | FRAVOLINI M L， DEL CORE G， PAPA U， et al. Data-driven schemes for robust fault detection of air data system sensors［J］. IEEE Transactions on Control Systems Technology， 2019， 27（1）： 234-248. |
| 26 | 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. |
| 27 | YAN W Z， YU L J. On accurate and reliable anomaly detection for gas turbine combustors： A deep learning approach［DB/OL］. arXiv preprint： 1908. 09238， 2019. |
| 28 | DONG Y Q. Implementing deep learning for compre-hensive aircraft icing and actuator/sensor fault detec-tion/identification［J］. Engineering Applications of Ar-tificial Intelligence， 2019， 83： 28-44. |
| 29 | EROGLU B， SAHIN M C， URE N K. Autolanding control system design with deep learning based fault estimation［J］. Aerospace Science and Technology， 2020， 102： 105855. |
| 30 | CHENG B Y， SHI S， HUANG K， et al. Fault diagnosis of aircraft power system based on long short-term memory network［C］∥2021 IEEE 5th Information Technology， Networking， Electronic and Automation Control Conference （ITNEC）. Piscataway： IEEE Press， 2021： 1438-1442. |
| 31 | 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. |
| 32 | DONG Y Q， WEN J R， ZHANG Y M， et al. Deep neural networks-based air data sensors fault detection for aircraft［C］∥2021 33rd Chinese Control and Decision Conference （CCDC）. Piscataway： IEEE Press， 2021： 442-447. |
| 33 | YAZICI I， BEYCA O F， DELEN D. Deep-learning-based short-term electricity load forecasting： A real case application［J］. Engineering Applications of Arti-ficial Intelligence， 2022， 109： 104645.. |
| 34 | ZHAO Y M， ZHAO H， AI J L， et al. Robust data-driven fault detection：An application to aircraft air data sensors［J］. International Journal of Aerospace Engineering， 2022（3）： 1-17. |
| 35 | MEYES R， LU M， DE PUISEAU C W， et al. Ablation studies in artificial neural networks［DB/OL］. arXiv preprint： 1901. 08644， 2019. |
| 36 | CHATTOPADHYAY A， SARKAR A， HOWLADER P， et al. Grad-CAM++： Improved visual explanations for deep convolutional networks［DB/OL］.arXiv preprint： 1710. 11063， 2017. |
| 37 | LONG M S， CAO Y， WANG J M， et al. Learning transferable features with deep adaptation networks［C］∥Proceedings of the 32nd International Conference on Machine Learning. Lille： ACM， 2015： 97-105. |
| 38 | SIMONYAN K， ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［DB/OL］. arXiv preprint： 1409. 1556， 2014. |
| 39 | DENG J， DONG W， SOCHER R， et al. ImageNet： A large-scale hierarchical image database［C］∥2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2009： 248-255. |
/
| 〈 |
|
〉 |
CJA