Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

doi:10.23919/JSEE.2024.000008

Journal of Systems Engineering and Electronics ›› 2024, Vol. 35 ›› Issue (2): 451-462.doi: 10.23919/JSEE.2024.000008

• CONTROL THEORY AND APPLICATION • Previous Articles

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

Yuqi YUAN¹(), Di ZHOU¹^,*(), Junlong LI²(), Chaofei LOU²

¹ School of Astronautics, Harbin Institute of Technology, Harbin 150001, China
² Beijing Institute of Electronic System Engineering, Beijing 100854, China

Received:2022-08-24 Online:2024-04-18 Published:2024-04-18
Contact: Di ZHOU E-mail:994631152@qq.com;zhoud@hit.edu.cn;hit_szL@163.com
About author:
YUAN Yuqi was born in 1994. He received his B.E. and M.E. degrees from Harbin Engineering University in 2016 and 2019. He is now studying for a Ph.D. degree in Harbin Institute of Technology. His research interests include neural network, system identification, and nonlinear filtering. E-mail: 994631152@qq.com

ZHOU Di was born in 1969. He received his B.E. and Ph.D. degrees in automatic control from Harbin Institute of Technology, Harbin, China, in 1991 and 1996, respectively. He once worked as a postdoctoral fellow in the Automation Department, Tsinghua University, Beijing, China, and a research fellow in the Department of Mechanical Engineering, Sophia University, Japan. He is now a professor in School of Astronautics, Harbin Institute of Technology. His research interests include nonlinear control, nonlinear filtering, and missile guidance and control. E-mail: zhoud@hit.edu.cn

LI Junlong was born in 1964. He received his Ph.D. degree from Harbin Institute of technology and now works as a researcher in Beijing Institute of Electronic System Engineering. His research interests include the overall design of aircraft , the navigation, guidance, and control. E-mail: hit_szL@163.com

LOU Chaofei was born in 1974. He received his Ph.D. degree from Beijing Institute of Electronic System Engineering, Beijing, China, in 2007. He is now working as a senior engineer in Beijing Institute of Electronic System Engineering. His research interests include navigation, guidance, and control. E-mail: louchaofei@ yahoo.com.cn

Abstract

Abstract:

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory (LSTM) neural network is nested into the extended Kalman filter (EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states, an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF (AEKF) when there exist large uncertainties in the system model.

Key words: long-short-term memory (LSTM) neural network, extended Kalman filter (EKF), rolling training, time-varying parameters estimation, missile dual control system

Yuqi YUAN, Di ZHOU, Junlong LI, Chaofei LOU. Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system[J]. Journal of Systems Engineering and Electronics, 2024, 35(2): 451-462.

Figures/Tables 16

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Fig 6

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

Fig 12

Fig 13

Fig 14

Fig 15

Fig 16

References 31

1	RICCO R A, TEIXEIRA B. Least−squares parameter estimation for state−space models with state equality constraints. International Journal of Systems Science, 2021, 53(1): 1−13.
2	LU X J. Online identification of aircraft parameters using state-space model. Changsha: National University of Defense Technology, 2016. (in Chinese)
3	ZHOU S. Operational identification of time-varying model parameters for thermal structures of high-speed aerial vehicles. Acta Aeronautica ET Astronautica Sinica, 2015, 36(1): 373−380.
4	ARULAMPALAM M S, MASKELL S, GORDON N, et al A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. on Signal Processing, 2002, 50 (2): 174- 188. doi: 10.1109/78.978374
5	JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation. Proceedings of the IEEE, 2004, 92 (3): 401- 422.
6	ARASARATNAM I, HAYKIN S Cubature Kalman filters. IEEE Trans. on Automatic Control, 2009, 54 (6): 1254- 1269. doi: 10.1109/TAC.2009.2019800
7	JETTO L, LONGHI S, VENTURINI G. Development and experimental validation of an adaptive extended Kalman filter for the localization of mobile robots. IEEE Trans. on Robotics and Automation. 1999, 15(2): 219−229.
8	ROBLES J J, CARDENAS−MANSILLA G, LEHNERT R. Adaptive selection of anchors in the extended Kalman filter tracking algorithm. Proc. of the IEEE 11th Workshop on Positioning Navigation and Communication, 2014. DOI: 10.1109/WPNC.2014.6843294.
9	CHEN X. An identification method of fast time-varying parameters adapted to aircraft control systems. Acta Aeronautica ET Astronautica Sinica, 1990, 11(9): 474−479.
10	SUN Y, LIU Y Adaptive synchronization control and parameters identification for chaotic fractional neural networks with time-varying delays. Neural Processing Letters, 2021, 53 (4): 2729- 2745. doi: 10.1007/s11063-021-10517-7
11	WANG S, ZHAO X, YU Q, et al Identification of driver braking intention based on long short-term memory (LSTM) network. IEEE Access, 2020, 8, 180422- 180432. doi: 10.1109/ACCESS.2020.3027811
12	HERMANS M, SCHRAUWEN B Training and analyzing deep recurrent neural networks. Advances in Neural Information Processing Systems, 2013, 2013, (1): 190- 198.
13	BENGIO Y, SIMARD P Learning long-term dependencies with gradient descent is difficult. IEEE Trans. on Neural Networks, 1994, 5 (2): 157- 166. doi: 10.1109/72.279181
14	LO J T, BASSU D. Adaptive multilayer perceptrons with long-and short-term memories. IEEE Trans. on Neural Networks, 2002, 13(1): 22−33.
15	YU Y, SI X S, HU C H, et al. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 2019, 31(7): 1235−1270.
16	HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Computation, 1997, 9(8): 1735−1780.
17	XING Y, LYU C. Dynamic state estimation for the advanced brake system of electric vehicles by using deep recurrent neural networks. IEEE Trans. on Industrial Electronics, 2020, 67(11): 9536−9547.
18	ZHOU Z Y, ZHANG R X, ZHU Z F. Robust Kalman filtering with long short-term memory for image-based visual servo control. Multimedia Tools and Applications, 2019, 78(18): 26341−26371.
19	MA C Y, WANG A N, CHEN G, et al. Hand joints-based gesture recognition for noisy dataset using nested interval unscented Kalman filter with LSTM network. The Visual Computer, 2018, 34(6/8): 1053−1063.
20	ZHENG T Y, YAO Y, HE F H. An RNN-based learnable extended Kalman filter design and application. Proc. of the IEEE 18th European Control Conference, 2019. DOI: 10.23919/ECC.2019.8796088.
21	BAO T Z, ZHAO Y H A deep Kalman filter network for hand kinematics estimation using sEMG. Pattern Recognition Letters, 2021, 143, 88- 94. doi: 10.1016/j.patrec.2021.01.001
22	NI Z C, YANG Y, XIU X. Battery state of charge estimation using long short-term memory network and extended Kalman filter. Proc. of the IEEE 39th Chinese Control Conference, 2020. DOI: 10.23919/CCC50068.
23	HONG J, WANG Z, CHEN W, et al. Synchronous multi-parameter prediction of battery systems on electric vehicles using long short-term memory networks. Applied Energy, 2019, 254: 113648.
24	ZMITRI M, FOURATI H, PRIEUR C. Inertial velocity estimation for indoor navigation through magnetic gradient-based EKF and LSTM learning model. Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020. DOI: 10.1109/IROS45743.
25	NI Y, XIA Z L, ZHAO F T An online multistep-forward voltage-prediction approach based on an LSTM-TD model and KF algorithm. Computer, 2021, 54 (8): 56- 65. doi: 10.1109/MC.2021.3070314
26	ZHU X L, HAO K R, XIE R M, et al Soft sensor based on extreme gradient boosting and bidirectional converted gates long short-term memory self-attention network. Neurocomputing, 2021, 434, 126- 136. doi: 10.1016/j.neucom.2020.12.028
27	MENG Y, LIU L A deep learning approach for a source code detection model using self-attention. Complexity, 2020, 2020, 5027198.
28	BABAK A, ALIREZA G B, HAMID K, et al. A novel attention-based LSTM cell post-processor coupled with Bayesian optimization for streamow prediction. Journal of Hydrology, 2021, 601: 126526.
29	SAGE A P, HUSA G W. Algorithms for sequential adaptive estimation of prior statistics. Proc. of the IEEE 8th Symposium on Adaptive Processes Decision and Control, 1969. DOI: 10.1109/SAP.1969.269927.
30	CHEN Z, SHU X, LI G, et al Stage of charge estimation of lithium-ion battery packs based on improved cubature Kalman filter with long short-term memory model. IEEE Trans. on Transportation Electrification, 2020, 73 (3): 1271- 1284.
31	RIDGELY D B, DRAKE D, TRIPLETT L. Dynamic control allocation of a missile with tails and reaction jets. Proc. of the AIAA Guidance, Navigation and Control Conference and Exhibit, 2007. DOI: 10.2514/6.2007-6671.

[1]	Muhammad WASIM, Ahsan ALI, Mohammad Ahmad CHOUDHRY, Inam Ul Hasan SHAIKH, Faisal SALEEM. Robust design of sliding mode control for airship trajectory tracking with uncertainty and disturbance estimation [J]. Journal of Systems Engineering and Electronics, 2024, 35(1): 242-258.
[2]	Mahmoudreza HADAEGH, Hamid KHALOOZADEH. Modified switched IMM estimator based on autoregressive extended Viterbi method for maneuvering target tracking [J]. Journal of Systems Engineering and Electronics, 2018, 29(6): 1142-1157.
[3]	Halil Ersin S¨oken and Chingiz Hajiyev. REKF and RUKF for pico satellite attitude estimation in the presence of measurement faults [J]. Journal of Systems Engineering and Electronics, 2014, 25(2): 288-297.

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 16

References 31

Related Articles 3

Recommended Articles

Metrics

Comments