Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process

doi:10.1016/j.cjche.2025.07.011

中国化学工程学报 ›› 2025, Vol. 88 ›› Issue (12): 321-334.DOI: 10.1016/j.cjche.2025.07.011

Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process

Qi Zhang^1,2, Fanda Pan³, Lei Xie⁴

1. State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
2. BYD Automobile Industry Co., Ltd., Shenzhen 518118, China;
3. Technical Center of Zhejiang China Tobacco Industrial Co. Ltd., Hangzhou 310000, China;
4. Institute of Intelligence Science and Engineering, Shenzhen Polytechnic University, Shenzhen 518055, China

收稿日期:2025-05-13 修回日期:2025-07-08 接受日期:2025-07-14 出版日期:2026-02-09 发布日期:2025-08-22
通讯作者: Fanda Pan,E-mail:panfanda@zjtobacco.com;Lei Xie,E-mail:lxie@zju.edu.cn
基金资助:
This work was supported by Jianbing Lingyan Foundation of Zhejiang Province, China (2023C01022), Major Project of Science and Technology of Yunnan Province (202402AD080001); Zhejiang University - China Tobacco Zhejiang Industrial Joint Laboratory Project.

Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process

Qi Zhang^1,2, Fanda Pan³, Lei Xie⁴

1. State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China;
2. BYD Automobile Industry Co., Ltd., Shenzhen 518118, China;
3. Technical Center of Zhejiang China Tobacco Industrial Co. Ltd., Hangzhou 310000, China;
4. Institute of Intelligence Science and Engineering, Shenzhen Polytechnic University, Shenzhen 518055, China

Received:2025-05-13 Revised:2025-07-08 Accepted:2025-07-14 Online:2026-02-09 Published:2025-08-22
Contact: Fanda Pan,E-mail:panfanda@zjtobacco.com;Lei Xie,E-mail:lxie@zju.edu.cn
Supported by:
This work was supported by Jianbing Lingyan Foundation of Zhejiang Province, China (2023C01022), Major Project of Science and Technology of Yunnan Province (202402AD080001); Zhejiang University - China Tobacco Zhejiang Industrial Joint Laboratory Project.

摘要/Abstract

摘要： The application of plant measurement data for system identification and model predictive control (MPC) has garnered significant interest. However, the pervasive presence of noise and contamination in industrial data often compromises data quality, thereby degrading performance and reliability of model. To address this challenge, this study proposes a nonlinear MPC method based on robust time delay particle filtering (RPF-MPC). This method is specifically designed to mitigate the impact of stochastic time delays and noise on both model learning and control. RPF-MPC utilizes robust particle filtering with a Laplace distribution to reliably estimate parameters and unknown time delays. In this way, the controller is able to efficiently handle noise and outliers even when the data deviates from a Gaussian distribution. The proposed algorithm is presented in detail, a nonlinear numerical case and a fuel cell water cooling control case are presented to validate the effectiveness of the RPF-MPC method. Simulation results validate the effectiveness and robustness of the RPF-MPC method in handling uncertainty and improving control performance in the PEMFC process.

关键词: System identification, Model predictive control, Particle filter, Bayesian inference, Time delay

Abstract: The application of plant measurement data for system identification and model predictive control (MPC) has garnered significant interest. However, the pervasive presence of noise and contamination in industrial data often compromises data quality, thereby degrading performance and reliability of model. To address this challenge, this study proposes a nonlinear MPC method based on robust time delay particle filtering (RPF-MPC). This method is specifically designed to mitigate the impact of stochastic time delays and noise on both model learning and control. RPF-MPC utilizes robust particle filtering with a Laplace distribution to reliably estimate parameters and unknown time delays. In this way, the controller is able to efficiently handle noise and outliers even when the data deviates from a Gaussian distribution. The proposed algorithm is presented in detail, a nonlinear numerical case and a fuel cell water cooling control case are presented to validate the effectiveness of the RPF-MPC method. Simulation results validate the effectiveness and robustness of the RPF-MPC method in handling uncertainty and improving control performance in the PEMFC process.

Key words: System identification, Model predictive control, Particle filter, Bayesian inference, Time delay

Qi Zhang, Fanda Pan, Lei Xie. Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process[J]. 中国化学工程学报, 2025, 88(12): 321-334.

Qi Zhang, Fanda Pan, Lei Xie. Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process[J]. Chinese Journal of Chemical Engineering, 2025, 88(12): 321-334.

参考文献

[1] F. Oldewurtel, A. Parisio, C.N. Jones, D. Gyalistras, M. Gwerder, V. Stauch, B. Lehmann, M. Morari, Use of model predictive control and weather forecasts for energy efficient building climate control, Energy Build. 45 (2012) 15-27.
[2] L. del Re, F. Allgower, L. Glielmo, C. Guardiola, I. Kolmanovsky, Automotive Model Predictive Control: Models, Methods and Applications. Springer London, 2010.
[3] G. Serale, M. Fiorentini, A. Capozzoli, D. Bernardini, A. Bemporad, Model predictive control (MPC) for enhancing building and HVAC system energy efficiency: problem formulation, applications and opportunities, Energies 11 (3) (2018) 631.
[4] M. Schwenzer, M. Ay, T. Bergs, D. Abel, Review on model predictive control: an engineering perspective, Int. J. Adv. Manuf. Technol. 117 (5) (2021) 1327-1349.
[5] R.Q. Chai, A. Tsourdos, A. Savvaris, S.C. Chai, Y.Q. Xia, C.L. Philip Chen, Review of advanced guidance and control algorithms for space/aerospace vehicles, Prog. Aerosp. Sci. 122 (2021) 100696.
[6] S. Vazquez, J. Rodriguez, M. Rivera, L.G. Franquelo, M. Norambuena, Model predictive control for power converters and drives: advances and trends, IEEE Trans. Ind. Electron. 64 (2) (2017) 935-947.
[7] J. B. Rawlings, D. Q. Mayne, M. Diehl, Model Predictive Control: Theory, Computation, and Design, Vol. 2, Nob Hill Publishing Madison, WI, 2017.
[8] J. Maciejowski, Predictive Control: With Constraints, Prentice Hall, 2002.
[9] K.P. Murphy, Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge, Mass. 2012.
[10] A.E. Ruano, Intelligent Control Systems using Computational Intelligence Techniques. Institution of Engineering and Technology, 2005.
[11] C. M. Bishop, Pattern Recognition and Machine Learning, Springer New York, 2006.
[12] A.X. Dong, A. Starr, Y.F. Zhao, Neural network-based parametric system identification: a review, Int. J. Syst. Sci. 54 (13) (2023) 2676-2688.
[13] O. Nelles, Nonlinear Dynamic System Identification, in: Nonlinear System Identification: From Classical Approaches to Neural Networks, Fuzzy Models, and Gaussian Processes, O. Nelles (Ed.), Springer International Publishing, Cham, 2020.
[14] M. Seeger, Gaussian processes for machine learning, Int. J. Neural Syst. 14 (2) (2004) 69-106.
[15] S.L. Brunton, J.N. Kutz, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control. Cambridge: Cambridge University Press, 2022.
[16] Z. Wu, P.D. Christofides, W.L. Wu, Y.J. Wang, F. Abdullah, A. Alnajdi, Y. Kadakia, A tutorial review of machine learning-based model predictive control methods, Rev. Chem. Eng. 41 (4) (2025) 359-400.
[17] L. Hewing, K.P. Wabersich, M. Menner, M.N. Zeilinger, Learning-based model predictive control: toward safe learning in control, Annu. Rev. Control Robot. Auton. Syst. 3 (2020) 269-296.
[18] W.R. Jacobs, T. Baldacchino, T. Dodd, S.R. Anderson, Sparse Bayesian nonlinear system identification using variational inference, IEEE Trans. Autom. Control 63 (12) (2018) 4172-4187.
[19] Q. Zhang, L. Wang, W.H. Xu, H.Y. Su, L. Xie, Nonlinear sparse variational Bayesian learning based model predictive control with application to PEMFC temperature control, Control Eng. Pract. 148 (2024) 105952.
[20] Z. Wu, D. Rincon, J.W. Luo, P.D. Christofides, Machine learning modeling and predictive control of nonlinear processes using noisy data, AIChE. J. 67 (4) (2021) e17164.
[21] M. Valipour, L.A. Ricardez-Sandoval, Constrained abridged Gaussian sum extended Kalman filter: constrained nonlinear systems with non-Gaussian noises and uncertainties, Ind. Eng. Chem. Res. 60 (47) (2021) 17110-17127.
[22] M. Valipour, L.A. Ricardez-Sandoval, Abridged Gaussian sum extended Kalman filter for nonlinear state estimation under non-Gaussian process uncertainties, Comput. Chem. Eng. 155 (2021) 107534.
[23] Q. Zhang, W.H. Xu, L. Xie, H.Y. Su, Dynamic fault detection and diagnosis for alkaline water electrolyzer with variational Bayesian Sparse principal component analysis, J. Process. Control 135 (2024) 103173.
[24] T. Baldacchino, K. Worden, J. Rowson, Robust nonlinear system identification: Bayesian mixture of experts using the t-distribution, Mech. Syst. Signal Process. 85 (2017) 977-992.
[25] X.Q. Yang, Y.J. Lu, Z.B. Yan, Robust global identification of linear parameter varying systems with generalised expectation-maximisation algorithm, IET Control Theory Appl. 9 (7) (2015) 1103-1110.
[26] T.B. Schon, A. Wills, B. Ninness, System identification of nonlinear state-space models, Automatica 47 (1) (2011) 39-49.
[27] R.B. Gopaluni, A particle filter approach to identification of nonlinear processes under missing observations, Can. J. Chem. Eng. 86 (6) (2008) 1081-1092.
[28] Simo Sarkka, Bayesian Filtering and Smoothing, Cambridge University Press, Cambridge, U.K. 2013.
[29] I. Askari, S. Zeng, H.Z. Fang, Nonlinear model predictive control based on constraint-aware particle filtering/smoothing,in: 2021 American Control Conference (ACC). New Orleans, LA, USA. IEEE, (2021) 3532-3537.
[30] K.G. Shin, X.Z. Cui, Computing time delay and its effects on real-time control systems, IEEE Trans. Control Syst. Technol. 3 (2) (1995) 218-224.
[31] W. Michiels, V. Van Assche, S.I. Niculescu, Stabilization of time-delay systems with a Controlled time-varying delay and applications, IEEE Trans. Autom. Control 50 (4) (2005) 493-504.
[32] J.P. Richard, Time-delay systems: an overview of some recent advances and open problems, Automatica 39 (10) (2003) 1667-1694.
[33] W.L. Wu, Y.J. Wang, M.Q. Zhang, M.S. Chiu, Z. Wu, Phased LSTM-based MPC for modeling and control of nonlinear systems using asynchronous and delayed measurement data, 2024 IEEE 63rd Conference on Decision and Control (CDC). Milan, Italy. IEEE, (2024) 132-139.
[34] L. Xie, H.Z. Yang, B. Huang, FIR model identification of multirate processes with random delays using EM algorithm, AIChE. J. 59 (11) (2013) 4124-4132.
[35] X.Q. Yang, S. Yin, Robust global identification and output estimation for LPV dual-rate systems subjected to random output time-delays, IEEE Trans. Ind. Inform. 13 (6) (2017) 2876-2885.
[36] J. Chen, B. Huang, F. Ding, Y. Gu, Variational Bayesian approach for ARX systems with missing observations and varying time-delays, Automatica 94 (2018) 194-204.
[37] T. Eltoft, T. Kim, T.W. Lee, On the multivariate Laplace distribution, IEEE Signal Process. Lett. 13 (5) (2006) 300-303.
[38] Z. Ghahramani, G. E. Hinton, Parameter estimation for linear dynamical systems, Technical Report CRG-TR-96-2, U. of Toronto, Department of Comp. Sci., 1996.
[39] B. Joergensen, Statistical Properties of the Generalized Inverse Gaussian Distribution. Springer New York, 1982.
[40] W.R.W. Daud, R.E. Rosli, E.H. Majlan, S.A.A. Hamid, R. Mohamed, T. Husaini, PEM fuel cell system control: a review, Renew. Energy 113 (2017) 620-638.
[41] B. Zhang, F. Lin, C.Z. Zhang, R.Y. Liao, Y.X. Wang, Design and implementation of model predictive control for an open-cathode fuel cell thermal management system, Renew. Energy 154 (2020) 1014-1024.
[42] X.H. Yuan, G. Wu, J.G. Zhou, X. Xiong, Y.P. Wang, MPC-based thermal management for water-cooled proton exchange membrane fuel cells, Energy Rep. 8 (2022) 338-348.

Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process

Robust particle filtering-based nonlinear model predictive control: Application to PEMFC process

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Qingmin Xu, Peng Li, Aimin Miao, Xun Lang, Hancheng Wang, Chuangyan Yang. Randomized autoregressive dynamic slow feature analysis method for industrial process fault monitoring[J]. 中国化学工程学报, 2025, 83(7): 298-314.
[2]	Zongyu Yao, Qingchao Jiang, Xingsheng Gu. Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference[J]. 中国化学工程学报, 2024, 73(9): 311-323.
[3]	Shan Liu, Wenqi Zhong, Li Sun, Xi Chen, Rafal Madonski. Uncertainty and disturbance estimator-based model predictive control for wet flue gas desulphurization system[J]. 中国化学工程学报, 2024, 67(3): 182-194.
[4]	Haokun Xiong, Lei Xie, Cheng Hu, Hongye Su. A fuzzy compensation-Koopman model predictive control design for pressure regulation in proten exchange membrane electrolyzer[J]. 中国化学工程学报, 2024, 76(12): 251-263.
[5]	Jiahui Liu, Nan Guo, Yixin Peng, Wenlu Li, Junfei Qiao, Xiaolong Gao, Wei Xiong. Adaptive sliding mode control of petrochemical flare combustion process based on radial basis function network[J]. 中国化学工程学报, 2024, 76(12): 318-326.
[6]	Shan Liu, Wenqi Zhong, Xi Chen, Li Sun, Lukuan Yang. Multiobjective economic model predictive control using utopia-tracking for the wet flue gas desulphurization system[J]. 中国化学工程学报, 2023, 54(2): 343-352.
[7]	Zhen Wang, Aimin An, Qianrong Li. Distributed model predictive control based on adaptive sampling mechanism[J]. 中国化学工程学报, 2021, 39(11): 193-204.
[8]	Lukuan Yang, Wenqi Zhong, Li Sun, Xi Chen, Yingjuan Shao. Dynamic optimization oriented modeling and nonlinear model predictive control of the wet limestone FGD system[J]. 中国化学工程学报, 2020, 28(3): 832-845.
[9]	Yaoyao Bao, Yuanming Zhu, Weimin Zhong, Feng Qian. A novel chemical composition estimation model for cement raw material blending process[J]. 中国化学工程学报, 2019, 27(11): 2734-2741.
[10]	Li Jia, Wendan Tan. Just-in-time learning based integrated MPC-ILC control for batch processes[J]. Chinese Journal of Chemical Engineering, 2018, 26(8): 1713-1720.
[11]	Jianxin Wang, Na Yu, Mengqi Chen, Lin Cong, Lanyi Sun. Composition control and temperature inferential control of dividing wall column based on model predictive control and PI strategies[J]. Chinese Journal of Chemical Engineering, 2018, 26(5): 1087-1101.
[12]	Pengfei Cao, Xionglin Luo, Xiaohong Song. Modeling and identification for soft sensor systems based on the separation of multi-dynamic and static characteristics[J]. Chinese Journal of Chemical Engineering, 2018, 26(1): 137-143.
[13]	Pengfei Cao, Xionglin Luo, Xiaohong Song. Feasibility analysis and online adjustment of constraints in model predictive control integrated with soft sensor[J]. , 2017, 25(9): 1230-1237.
[14]	Haokun Wang, Zuhua Xu, Jun Zhao, Aipeng Jiang. An optimal filter based MPC for systems with arbitrary disturbances[J]. , 2017, 25(5): 632-640.
[15]	Mahmoud M. Saafan, Mohamed M. Abdelsalam, Mohamed S. Elksas, Sabry F. Saraya, Fayez F. G. Areed. An adaptive neuro-fuzzy sliding mode controller for MIMO systems with disturbance[J]. , 2017, 25(4): 463-476.