Abstract
The performance of conventional nonlinear model predictive control \(\left( {{\text{NMPC}}} \right)\) system relies heavily on the accuracy of the prediction model. In cases of significant plant-model mismatch, non-desirable responses may be observed in the controlled outputs. This paper proposes a parameter adaptation technique for tackling this problem. In the proposed approach, the output disturbance is selected as the adaptation parameter while the adaptation law is modelled as a function of the tracking error using a first-order difference equation. The adaptation law is integrated into a \(\mathrm{NMPC}\) algorithm to achieve offset-free tracking. The effectiveness of the proposed scheme is demonstrated on two simulation case studies—a pH system and a continuously stirred tank reactor (CSTR); and an experimental cascaded two tank process. The simulation results obtained showed that the proposed scheme achieves zero offset in the face of significant plant-model mismatch arising from uncertainties in model parameters, unmeasured disturbances, and measurement noise and compared favourably with existing methods. The experimental results obtained during real-time implementation of the proposed control scheme corroborate this assertion and show its industrial applicability.
Similar content being viewed by others
References
Hunt L, Sbarbaro D, Zbibowski A, Gawthrop P (1992) Neural networks for control system—a survey Automatica, 286(6): 1083–1111.
Hornik K, Stinchcombe M, White H (1989) Multilayer feedfoward networks are universal approximators. Neural Netw 2:359
Chu JZ, Tsai PF, Tsai WY, Jang SS, Shieh SS, Lin PH, Jiang SJ (2003) Multistep model predictive control based on artificial neural networks. Ind Eng Chem Res 32:5215–5228
Dang DQ, Wang Y, Cai W (2012) Offset-free predictive control for variable speed wind turbines. IEEE Trans Sustain Energy 4(1):2–10
Huang R, Biegler LT, Patwardhan SC (2010) Fast offset-free nonlinear model predictive control based on moving horizon estimation. Ind Eng Chem Res 49(17):7882–7890
Pannochia G, Rawlings JB (2003) Disturbance models for offset-free model predictive control. AIChE J 49(2):426–437
Zhang T, Feng G, Zeng XJ (2009) Output tracking of constrained nonlinear processes with offset-free input to state stable fuzzy predictive control. Automatica 45:900–909
Qin SJ, Badgwell TA (2003) A survey of industrial model predictive control technology. Control Eng Pract 11(7):733–764
Tian X, Wang P, Huang D, Chen S (2014) Offset-free multistep nonlinear model predictive control under plant–model mismatch. Int J Adapt Control Sign Process 28:444–463
Akesson M, Toivonen HT, Waller JB, Nystrom RH (2005) Neural network approximation of a nonlinear model predictive controller applied to a pH neutralization process. Comput Chem Eng 29(2):323–335
Kuure-Kinsey M, Cutright R, Bequette BW (2006) Computationally efficient neural predictive control based on a feedback architecture. Ind Eng Chem Res 45:8575–8582
Kuure-Kinsey M, Bequette BW (2008) Improved nonlinear model predictive control performance using recurrent neural network. American control conference, Westin Seattle Hotel, Seattle Washington, USA, pp 4197–4202
Jazayeri A, Fatehi A, Sadjadian H, Khaki-Sedigh K (2008) Disturbance rejection in neural network model predictive control, Proc. of the 17th IFAC World Congress, Korea
Akpan VA, Hassapis GD (2011) Nonlinear model identification and adaptive model predictive control using neural networks. ISA Trans 50:177–194
Hsu CF (2009) Adaptive recurrent neural network control using a structure adaptation algorithm. Neural Comput Appl 18:115–125
Cheng L,. Wang Z, Jiang F, Li J (2020): Adaptive neural network control of nonlinear systems with unknown dynamics, Advances in Space Research. (In press)
Yang YY, Linkens DA (1994) Adaptive neural-network-based approach for the control of continuously stirred tank reactor. IEE Proc-Control Theory Appl 141(3):341–349
Hussain MA (1999) Review of the applications of neural networks in chemical process control-simulation and online implementation. Artif Intell Eng 13:55–68
Rajchakit G, Sriraman R (2021) Robust passivity and stability analysis of uncertain complex-valued impulsive neural networks with time-varying delays. Neural Process Lett. https://doi.org/10.1007/s11063-020-10401-w
Rajchakit G, Chanthorn P, Niezabitowski M, Raja R, Baleanu D, Pratap A (2020) Impulsive effects on stability and passivity analysis of memristor-based fractional-order competitive neural networks. Neurocomputing 417:290–301
Chanthorn P, Rajchakit G, Ramalingam S, Lim CP, Raja R (2020) Robust Dissipativity analysis of hopfield-type complex-valued neural networks with time-varying delays and linear fractional uncertainties. Mathematics 8:595. https://doi.org/10.3390/math8040595
Rangaiah GP, Saha P, Tade MO (2002) Nonlinear model predictive control of an industrial four-stage evaporator system via simulation. Chem Eng J 87:285–299
Al seyab, RKS (2006) Nonlinear model predictive control using automatic differentiation. Ph.D. Thesis, Cranfield University.
Bamimore, A. (2016). Applications of selected model-based control methods to some selected industrial processes. Ph.D. Thesis, Obafemi Awolowo University, Ile-Ife, Nigeria.
Kiselak J, Lu Y, Sˇvihra J, Sze´pe, P., Stehlı`k M. (2020) ‘“SPOCU”’: scaled polynomial constant unit activation function. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05182-1
Huberman BA, Lumer E (1990) Dynamics of adaptive systems. IEEE Trans Circuits Syst 37(4):547–550
Sobowale NB (2019) Offset-free Nonlinear Model Predictive Control based on Feedforward Neural Network Models. Thesis (Unpublished), Obafemi Awolowo University, Ile-Ife, Nigeria, B.Sc
Henson MA, Seborg DE (1994) Adaptive nonlinear control of a pH neutralization process. IEEE Trans Control Syst Technol 2(3):169–181
Chen H, Kremling A, Allgöwer F (1995) Non-linear predictive control of a benchmark, CSTR. In: Proceeding of 3rd European control conference, Rome, Italy, September 5–8, pp 3247–3252
Acknowledgements
The authors gratefully acknowledge Hezekiah Babajide Bamidele and Atinuke Temidayo Alabi for helping in collecting some useful data. The authors are also very grateful to the many constructive comments from the anonymous Associate Editor and reviewers.
Funding
Not Applicable
Author information
Authors and Affiliations
Contributions
Not applicable.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest.
Availability of data and material
This will be made available via email upon request.
Code availability
This will be made available via email upon request.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bamimore, A., Sobowale, N.B., Osunleke, A.S. et al. Offset-free neural network-based nonlinear model predictive controller design using parameter adaptation. Neural Comput & Applic 33, 10235–10257 (2021). https://doi.org/10.1007/s00521-021-05788-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05788-z