State Estimation With Model Uncertainty Using Structure Variational Bayesian and Transfer Learning

Shuang Gao; Xiaoli Luan; Biao Huang; Shunyi Zhao; Fei Liu

doi:10.1109/JAS.2025.125825

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 19.2, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > In Press, Accepted Manuscript

S. Gao, X. Luan, B. Huang, S. Zhao, and F. Liu, “State estimation with model uncertainty using structure variational bayesian and transfer learning,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–13, Mar. 2026. doi: 10.1109/JAS.2025.125825

Citation:

S. Gao, X. Luan, B. Huang, S. Zhao, and F. Liu, “State estimation with model uncertainty using structure variational bayesian and transfer learning,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 3, pp. 1–13, Mar. 2026. doi: 10.1109/JAS.2025.125825

Citation:

PDF( 1542 KB)

State Estimation With Model Uncertainty Using Structure Variational Bayesian and Transfer Learning

doi: 10.1109/JAS.2025.125825

Funds: This work was supported by the National Natural Science Foundation of China (62503201), the Basic Research Program of Jiangsu (BK20251595), the China Postdoctoral Science Foundation (2025M771693), the Postdoctoral Fellowship Program of the China Postdoctoral Science Foundation (GZC20251168), and the Fundamental Research Funds for the Central Universities (JUSRP202501067)

More Information

Author Bio:
Shuang Gao (Member, IEEE) received the B.E. degree in automation from Jiangnan University in 2018 and the Ph.D. degree in control science and engineering from the Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University in 2024. From 2022 to 2024, She was a Visiting Scholar in the Department of Chemical and Materials Engineering, University of Alberta, Canada. In 2024, she joined Jiangnan University as a Lecturer. Her research interests include state estimation, Bayesian inference, transfer learning based estimation, and fault detection and diagnosis

Xiaoli Luan (Member, IEEE) received the B.S. degree in industrial automation from Jiangnan University in 2002, the M.S. degree in control theory and control engineering from Jiangnan University in 2006, and the Ph.D. degree in control theory and control engineering from Jiangnan University in 2010. Now she is a Professor of the Institute of Automation, Jiangnan University. In 2016, she was a Visiting Professor with the University of Alberta, Canada. Her research interests include robust control and optimization of complex industrial process. She has authored or coauthored more than 80 articles in professional journals, conference proceedings, and technical reports in these related areas. She hosted and participated several research programs funded by National Natural Science Foundation, and served as reviewer of a number of international journals

Biao Huang (Fellow, IEEE) received the M.S. and B.S. degrees in automatic contorl from the Beijing University of Aeronautics and Astronautics, in 1983 and 1986, respectively, the Ph.D. degree in process control from the University of Alberta, Canada, in 1997. He joined the University of Alberta in 1997 as an Assistant Professor in the Department of Chemical and Materials Engineering, and is currently a full Professor and Engineering Research Chair in Smart Automation with University of Alberta, Canada. He held positions of NSERC Industrial Research Chair in Control of Oil Sands Processes and AITF Industry Chair in Process Control. His research interests include data analytics, process control, system identification, control performance assessment, Bayesian methods and state estimation. He is a Fellow of the Canadian Academy of Engineering and Fellow of Chemical Institute of Canada. He is recipient of Germany’s Alexander von Humboldt Research Fellowship, Canadian Chemical Engineer Society’s R.S. Jane Memorial award, Bantrel award in Design and Industrial Practice, Syncrude Canada Innovation award and D.G. Fisher award, APEGAs Summit Research Excellence award, AsTech Outstanding Achievement in Science & Engineering award and a Best Paper award from Journal of Process Control. He has applied his expertise extensively in industrial practice

Shunyi Zhao (Senior Member, IEEE) received the Ph.D. degree in control theory and application from the Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University in 2015. From 2013 to 2014, he was a Visiting Student in the Department of Chemical and Materials Engineering, University of Alberta, Canada, where he was a Postdoctoral Fellow from 2015 to 2018. In 2015, he joined Jiangnan University as an Associate Professor, and is currently a Professor. His research interests include statistical signal processing, Bayesian estimation theory, and fault detection and diagnosis. Dr. Zhao is the recipient of Alexander von Humboldt Research Fellowship in Germany, the excellent Ph.D. thesis award (2016) in Jiangsu Province, China, and a nomination of excellent doctoral thesis from Chinese Association of Automation (CAA) in 2016

Fei Liu (Member, IEEE) received the B.S. degree in electrical technology from Wuxi Institute of Light Industry in 1987, the M.S. degree in industrial automation from Wuxi Institute of Light Industry in 1990, and the Ph.D. degree in control science and control engineering from Zhejiang University in 2002. From 1990 to 1999, he was an Assistant, Lecturer, and Associate Professor in Wuxi Institute of Light Industry. Since 2003, he has been a Professor of the Institute of Automation, Jiangnan University. From 2005 to 2006, he was a Visiting Professor with the University of Manchester, UK. His research interests include advanced control theory and applications, batch process control engineering, statistical monitoring and diagnosis in industrial process, and intelligent technique with emphasis on fuzzy and neural systems
Corresponding author: Shuang Gao, e-mail: sgao@jiangnan.edu.cn; Xiaoli Luan, e-mail: xlluan@jiangnan.edu.cn
Received Date: 2024-12-06
Revised Date: 2025-04-14
Accepted Date: 2025-08-06

Available Online: 2026-03-05

Abstract

Abstract

This paper proposes a novel approach to address parameter uncertainties for state estimation in Markovian jump linear systems by leveraging transfer learning. Assume that the source domain model is available and reliable, and the target domain model has significant model parameter uncertainties. To enhance estimation performance in the target domain, the proposed method transfers model knowledge from the source domain and adjusts it using a tuning factor before incorporating it into the target domain estimator. More specifically, this approach involves transferring the modified probability density functions of state prediction from the source domain to the target domain and determining the tuning factor via structure variational Bayesian inference using measurements in the target domain. Using numerical examples and a 1-DOF torsion system, we showcase the competitiveness of the proposed state estimator compared to the existing robust state estimation methods when dealing with parameter uncertainties. The results highlight its capability to improve estimation accuracy in practical scenarios, showcasing its potential for real-world applications.
- Markovian jump linear systems,
- parameter uncertainty,
- state estimation,
- structure variational inference,
- transfer learning

FullText(HTML)

References(45)

References

[1]	E. Mazor, A. Averbuch, Y. Bar-Shalom, and J. Dayan, “Interacting multiple model methods in target tracking: A survey,” IEEE Trans. Aerospace and Electronic Systems, vol. 34, no. 1, pp. 103–123, 1998. doi: 10.1109/7.640267
[2]	C. J. Kim, “Dynamic linear models with Markov-switching,” J. Econometrics, vol. 60, no. 1–2, pp. 1–22, 1994. doi: 10.1016/0304-4076(94)90036-1
[3]	A. Logothetis and V. Krishnamurthy, “Expectation maximization algorithms for map estimation of jump markov linear systems,” IEEE Trans. Signal Processing, vol. 47, no. 8, pp. 2139–2156, 1999. doi: 10.1109/78.774753
[4]	Y. Zhang, K. Lou, and Y. Ge, “New result on delay-dependent stability for Markovian jump time-delay systems with partial information on transition probabilities,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 6, pp. 1499–1505, 2016.
[5]	X. R. Li and V. Jilkov, “Survey of maneuvering target tracking,” IEEE Trans. Aerospace and Electronic Systems, vol. 41, no. 4, pp. 1255–1321, 2005. doi: 10.1109/TAES.2005.1561886
[6]	H. A. Blom, “An efficient filter for abruptly changing systems,” in Proc. 23rd IEEE Conf. Decision and Control, 1984, pp. 656–658.
[7]	H. A. Blom and Y. Bar-Shalom, “The interacting multiple model algorithm for systems with markovian switching coefficients,” IEEE Trans. Autom. Control, vol. 33, no. 8, pp. 780–783, 1988. doi: 10.1109/9.1299
[8]	X. Kong, X. Zhang, X. Zhang, C. Wang, H.-D. Chiang, and P. Li, “Adaptive dynamic state estimation of distribution network based on interacting multiple model,” IEEE Trans. Sustainable Energy, vol. 13, no. 2, pp. 643–652, 2021.
[9]	L. A. Johnston and V. Krishnamurthy, “An improvement to the interacting multiple model (IMM) algorithm,” IEEE Trans. Signal Processing, vol. 49, no. 12, pp. 2909–2923, 2001. doi: 10.1109/78.969500
[10]	O. L. Costa and S. Guerra, “Stationary filter for linear minimum mean square error estimator of discrete-time Markovian jump systems,” IEEE Trans. Autom. Control, vol. 47, no. 8, pp. 1351–1356, 2002. doi: 10.1109/TAC.2002.800745
[11]	F. Zhao, C. Chen, W. He, and S. S. Ge, “A filtering approach based on mmae for a SINS/CNS integrated navigation system,” IEEE/CAA J. Autom. Sinica, vol. 5, no. 6, pp. 1113–1120, 2018. doi: 10.1109/JAS.2017.7510445
[12]	A. Doucet, N. J. Gordon, and V. Krishnamurthy, “Particle filters for state estimation of jump Markov linear systems,” IEEE Trans. Signal Processing, vol. 49, no. 3, pp. 613–624, 2001. doi: 10.1109/78.905890
[13]	S. Seifzadeh, B. Khaleghi, and F. Karray, “Distributed soft-data-constrained multi-model particle filter,” IEEE Trans. Cybern., vol. 45, no. 3, pp. 384–394, 2014.
[14]	X. R. Li and Y. Bar-Shalom, “Multiple-model estimation with variable structure,” IEEE Trans. Autom. Control, vol. 41, no. 4, pp. 478–493, 1996. doi: 10.1109/9.489270
[15]	Y. S. Shmaliy, F. Lehmann, S. Zhao, and C. K. Ahn, “Comparing robustness of the Kalman, H_∞, and UFIR filters,” IEEE Trans. Signal Processing, vol. 66, no. 13, pp. 3447–3458, 2018. doi: 10.1109/TSP.2018.2833811
[16]	J. Wang, S. Ma, C. Zhang, and M. Fu, “Finite-time H_∞ filtering for nonlinear singular systems with nonhomogeneous Markov jumps,” IEEE Trans. Cybern., vol. 49, no. 6, pp. 2133–2143, 2018.
[17]	N. M. Alyazidi and M. S. Mahmoud, “Distributed H₂/H_∞ filter design for discrete-time switched systems,” IEEE/CAA J. Autom. Sinica, vol. 7, no. 1, pp. 158–168, 2019.
[18]	L. Zhang, “H_∞ estimation for discrete-time piecewise homogeneous Markov jump linear systems,” Automatica, vol. 45, no. 11, pp. 2570–2576, 2009. doi: 10.1016/j.automatica.2009.07.004
[19]	H. Liu, D. W. Ho, and F. Sun, “Design of H_∞ filter for Markov jumping linear systems with non-accessible mode information,” Automatica, vol. 44, no. 10, pp. 2655–2660, 2008. doi: 10.1016/j.automatica.2008.03.011
[20]	R. K. Boel, M. R. James, and I. R. Petersen, “Robustness and risk-sensitive filtering,” IEEE Trans. Autom. Control, vol. 47, no. 3, pp. 451–461, 2002. doi: 10.1109/9.989082
[21]	M. Zorzi and B. C. Levy, “On the convergence of a risk sensitive like filter,” in Proc. 54th IEEE Conf. Decision and Control, 2015, pp. 4990–4995.
[22]	B. C. Levy and R. Nikoukhah, “Robust least-squares estimation with a relative entropy constraint,” IEEE Trans. Infor. Theory, vol. 50, no. 1, pp. 89–104, 2004. doi: 10.1109/TIT.2003.821992
[23]	T. Başar, “Robust designs through risk sensitivity: An overview,” J. Systems Science and Complexity, vol. 34, no. 5, pp. 1634–1665, 2021. doi: 10.1007/s11424-021-1242-6
[24]	M. Zorzi, “Robust Kalman filtering under model perturbations,” IEEE Trans. Autom. Control, vol. 62, no. 6, pp. 2902–2907, 2016.
[25]	S. Gao, S. Zhao, X. Luan, and F. Liu, “Adaptive risk-sensitive filter for Markovian jump linear systems,” Automatica, vol. 151, p. 110897, 2023. doi: 10.1016/j.automatica.2023.110897
[26]	S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2009.
[27]	W. Zhang, L. Deng, L. Zhang, and D. Wu, “A survey on negative transfer,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 2, pp. 305–329, 2022.
[28]	F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, “A comprehensive survey on transfer learning,” Proc. IEEE, vol. 109, no. 1, pp. 43–76, 2020.
[29]	A. Karbalayghareh, X. Qian, and E. R. Dougherty, “Optimal Bayesian transfer learning,” IEEE Trans. Signal Processing, vol. 66, no. 14, pp. 3724–3739, 2018. doi: 10.1109/TSP.2018.2839583
[30]	A. Quinn, M. Kárnỳ, and T. V. Guy, “Fully probabilistic design of hierarchical bayesian models,” Infor. Sciences, vol. 369, pp. 532–547, 2016. doi: 10.1016/j.ins.2016.07.035
[31]	C. Foley and A. Quinn, “Fully probabilistic design for knowledge transfer in a pair of Kalman filters,” IEEE Signal Processing Letters, vol. 25, no. 4, pp. 487–490, 2017.
[32]	M. Papež and A. Quinn, “Robust bayesian transfer learning between kalman filters,” in Proc. IEEE 29th Int. Workshop on Machine Learning for Signal Processing, 2019, pp. 1–6.
[33]	M. Papež and A. Quinn, “Bayesian transfer learning between student-t filters,” Signal Processing, vol. 175, p. 107624, 2020. doi: 10.1016/j.sigpro.2020.107624
[34]	L. K. Pavelková, L. Jirsa, and A. Quinn, “Fully probabilistic design for knowledge fusion between bayesian filters under uniform disturbances,” Knowledge-Based Systems, vol. 238, p. 107879, 2022. doi: 10.1016/j.knosys.2021.107879
[35]	S. Gao, S. Zhao, X. Luan, and F. Liu, “Transfer state estimator for Markovian jump linear systems with multirate measurements,” IEEE Trans. Systems, Man, and Cybern.: Systems, vol. 53, no. 6, pp. 3440–3449, 2023. doi: 10.1109/TSMC.2022.3227534
[36]	S. Gao, X. Luan, B. Huang, S. Zhao, and F. Liu, “A transfer state estimator for uncertain parameters and noise statistics,” IFAC-PapersOnLine, vol. 58, no. 14, pp. 192–197, 2024. doi: 10.1016/j.ifacol.2024.08.335
[37]	Y. Bar-Shalom, X. R. Li, and T. Kirubarajan, Estimation With Applications to Tracking and Navigation: Theory Algorithms and Software. New York, USA: John Wiley & Sons, 2001.
[38]	S. Zhao, C. K. Ahn, P. Shi, Y. Shmaliy, and F. Liu, “Bayesian state estimation for Markovian jump systems: Employing recursive steps and pseudocodes,” IEEE Systems, Man, and Cybern. Magazine, vol. 5, no. 2, pp. 27–36, 2019. doi: 10.1109/MSMC.2018.2882145
[39]	R. Kulhavỳ, “Recursive nonlinear estimation: A geometric approach,” Automatica, vol. 26, no. 3, pp. 545–555, 1990. doi: 10.1016/0005-1098(90)90025-D
[40]	M. Toda and R. Patel, “Bounds on estimation errors of discrete-time filters under modeling uncertainty,” IEEE Trans. Autom. Control, vol. 25, no. 6, pp. 1115–1121, 1980. doi: 10.1109/TAC.1980.1102502
[41]	I. Hwang, C. E. Seah, and S. Lee, “A study on stability of the interacting multiple model algorithm,” IEEE Trans. Autom. Control, vol. 62, no. 2, pp. 901–906, 2016.
[42]	U. Orguner and M. Demirekler, “Risk-sensitive filtering for jump markov linear systems,” Automatica, vol. 44, no. 1, pp. 109–118, 2008. doi: 10.1016/j.automatica.2007.04.018
[43]	P. Takyi-Aninakwa, S. Wang, H. Zhang, X. Yang, and C. Fernandez, “An optimized long short-term memory-weighted fading extended kalman filtering model with wide temperature adaptation for the state of charge estimation of lithium-ion batteries,” Applied Energy, vol. 326, p. 120043, 2022. doi: 10.1016/j.apenergy.2022.120043
[44]	S. Yazdkhasti, D. Sabzevari, and J. Z. Sasiadek, “Adaptive h-infinity extended Kalman filtering for a navigation system in presence of high uncertainties,” Trans. Institute of Measurement and Control, vol. 45, no. 8, pp. 1430–1442, 2023. doi: 10.1177/01423312221136022
[45]	G. Fuchs, V. Šátek, V. Vopěnka, J. Kunovskỳ, and M. Kozek, “Application of the modern taylor series method to a multi-torsion chain,” Simulation Modelling Practice and Theory, vol. 33, pp. 89–101, 2013. doi: 10.1016/j.simpat.2012.10.002

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(16) / Tables(1)

Get Citation

PDF

XML

Article Metrics

Article views (15) PDF downloads(1)

State Estimation With Model Uncertainty Using Structure Variational Bayesian and Transfer Learning

doi: 10.1109/JAS.2025.125825

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content