Intelligent active fault-tolerant system for multi-source integrated navigation system based on deep neural network
- 44 Downloads
This paper proposes an intelligent active fault-tolerant system based on deep neural network. That is, an active fault-tolerant integrated navigation system is established by adding neural network to the fault-tolerant integrated navigation system based on one-class support vector machine fault detection algorithm. When there is no fault, the neural network trains each sub-filter; when there is a fault, the neural network which has been in the training state will predict the fault time data and use the neural network prediction data to replace the fault data into the main filter for fusion. It can be seen from the simulation analysis that the system can detect the fault of the navigation sub-filtering system well, and when the fault occurs, the prediction data of the neural network is used for information fusion. Simulation results show that the system can provide stable and reliable navigation under the condition of time-varying system and observation noise and complex environment.
KeywordsActive fault-tolerant One-class SVM Fault detection Deep neural network State estimation
The authors would like to thank Prof. Jingdong Yu at National Key Laboratory of Science and Technology on Communications of UESTC for help, and Prof. Long Jin and Prof. Yonglun Luo at Research Institute of Electronic Science and Technology of UESTC for the assistance. The author also wants to thank Research Institute of Electronic Science and Technology and Key Laboratory of Integrated Electronic System, Ministry of Education, for their support for this research. However, the opinions expressed in this paper are solely those of the authors.
Compliance with ethical standards
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work; there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.
- 3.Liu L, Fu J (2010) Improved state-χ2 fault detection of navigation systems based on neural network. In: Control and decision conference (CCDC), 2010 Chinese. IEEE, pp 3932–3937Google Scholar
- 4.Liu HY, Feng CT, Wang HN (2011) Method of inertial aided satellite navigation and its integrity monitoring. J Astronaut 32(4):775–780Google Scholar
- 5.Zhenlu S (1999) Optimal fault detection filter design. J Beijing Univ Aeronaut AstronautGoogle Scholar
- 6.Tao H (2008) Application of BP neural network in sensor fault diagnosis for flight control system. Comput Meas Control 16(5):613–615Google Scholar
- 7.Wei-Guang G (2008) Neural network aided GPS/INS integrated navigation fault detection algorithms. Acta Geod Cartogr Sin 80(2):186–192Google Scholar
- 8.Zhang J, Zhang T, Jiang X et al (2012) Tightly coupled GPS/INS integrated navigation algorithm based on Kalman filter. In: International conference on business computing & global informatization. IEEE, pp 588–591Google Scholar
- 9.Zhang Y, Wang H, Wang H (2017) Integrated navigation positioning algorithm based on improved Kalman filter. In: International conference on smart grid and electrical automation. IEEE, pp 255–259Google Scholar
- 10.Hongxin J, Tao Y, Xiaogang W et al (2017) Unmanned aerial vehicle relative navigation method based on robust high degree cubature filtering. J Natl Univ Def Technol 39(4):139–143Google Scholar
- 11.Li-Jia XU, Yang-Zhou C, Ping-Yuan C (2004) State estimation of integrated navigation system based on neural network. J Chin Inert Technol 12(2):40–46Google Scholar
- 12.Wang M, Fu Y (2008) State estimation of ALV integrated navigation system based on BP neural network. In: Eighth international conference on intelligent systems design & applications. IEEEGoogle Scholar
- 16.Li YC, Lu XL, Wang HX, Bao Z (2007) Research on positioning and measuring speed in the high speed sar system based on high precision map matching. Syst Eng ElectronGoogle Scholar
- 18.Guo C, Yan J, Tian Z (2018) Analysis and design of an attitude calculation algorithm based on Elman neural network for SINS. Clust Comput 6:1–6Google Scholar