This paper proposes an indirect adaptive control method based on recurrent neural networks. To achieve satisfactory closed-loop performances, a neural emulator (NE) and a neural controller (NC) adapting rates are established using the multiobjective particle swarm optimization (MOPSO) algorithm. The proposed MOPSO algorithm has been designed to minimize, simultaneously, two separated objective functions: the emulation and the tracking errors. The proposed approach guarantees that the NE tracks the system dynamics within a short time window. Consequently, it provides for the suggested control structure useful information to synthesize optimal adaptive rates of the NE and NC. To validate the effectiveness of the proposed MOPSO algorithm, a numerical example and an experimental validation on a chemical reactor are proposed.
AliTAnisSFaouziM (2014) Constrained multivariable predictive controller based on PSO algorithm and T-S fuzzy modeling approach. In: Proceedings of the 2014 15th international conference on sciences and techniques of automatic control and computer engineering (STA), Hammamet, 21–23 December, pp. 117–122. New York: IEEE.
2.
AtigADruauxFLefebvreD, et al. (2010) Neural emulator and controller with decoupled adaptive rates for nonlinear systems: Application to chemical reactors. International Journal on Sciences and Techniques of Automatic Control and Computer Engineering (IJ-STA)4(2): 1298–1319.
3.
AtigADruauxFLefebvreD, et al. (2012) Adaptive control design using stability analysis and tracking errors dynamics for nonlinear square MIMO systems. Engineering Applications of Artificial Intelligence25(7): 1450–1459.
4.
BouallègueSHaggègeJBenrejebM (2011) Particle swarm optimization-based fixed-structure control design. International Journal of Control, Automation and Systems9: 258–266.
5.
BouallègueSHaggègeJAyadiM, et al. (2012) PID-type fuzzy logic controller tuning based on particle swarm optimization. Engineering Applications of Artificial Intelligence25(3): 484–493.
6.
ChroutaJZaafouriAJemliM (2018) An improved heterogeneous multi-swarm PSO algorithm to generate an optimal TS fuzzy model of a hydraulic process. Transactions of the Institute of Measurement and Control40(6): 2039–2053.
7.
Dorado-SevillaDFPeluffo-OrdóñezDHLorente-LeyvaLL, et al. (2021) An interactive framework to compare multi-criteria optimization algorithms: Preliminary results on NSGA-II and MOPSO. In: BindhuVTavaresJMRSBoulogeorgosAAA, et al,. (eds) International Conference on Communication, Computing and Electronics Systems: Proceedings of ICCCES 2020. Cham: Springer, pp. 61–76.
8.
EllisMChristofidesPD (2014) Integrating dynamic economic optimization and model predictive control for optimal operation of nonlinear process systems. Control Engineering Practice22: 242–251.
9.
FreireHA (2017) Many-objective optimization with particle swarm optimization algorithm (Portugal). PhD Thesis, Universidade de Tras-os-Montes e Alto Douro, Vila Real.
10.
GanXPeiJWangW, et al. (2022) Application of a modified MOPSO algorithm and multi-layer artificial neural network in centrifugal pump optimization. Engineering Optimization55: 580–598.
11.
JúniorGANMartinsMAKalidR (2014) A PSO-based optimal tuning strategy for constrained multivariable predictive controllers with model uncertainty. ISA Transactions53(2): 560–567.
12.
LiangSLiBTianX, et al. (2021) Determining optimal parameter ranges of warm supply air for stratum ventilation using pareto-based MOPSO and cluster analysis. Journal of Building Engineering37: 102145.
13.
MadiouniRBouallègueSHaggègeJ, et al. (2016) Robust RST control design based on multi-objective particle swarm optimization approach. International Journal of Control, Automation and Systems14: 1607–1617.
14.
MejdiSMessaoudABen AbdennourR (2020) Fault tolerant multicontrollers for nonlinear systems: A real validation on a chemical process. International Journal of Applied Mathematics and Computer Science30(1): 61–74.
15.
NakisaBRastgooMNNasrudinMF, et al. (2015) A multi-swarm particle swarm optimization with local search on multi-robot search system. Journal of Theoretical and Applied Information Technology71(1): 129–136.
16.
Reyes-SierraMCoelloCC (2006) Multi-objective particle swarm optimizers: A survey of the state-of-the-art. International Journal of Computational Intelligence Research2(3): 287–308.
17.
RhiliFEAtigABen AbdennourR (2019) Fuzzy adapting rate for a neural emulator of nonlinear systems: Real application on a chemical process. Transactions of the Institute of Measurement and Control41(8): 2214–2222.
18.
RongHJSureshSZhaoGS (2011) Stable indirect adaptive neural controller for a class of nonlinear system. Neurocomputing74(16): 2582–2590.
19.
SalehpourMTabanM (2014) Two approaches on carrier frequency offset estimation in MIMO OFDM systems. Iranian Journal of Science and Technology Transactions of Electrical Engineering38(E2): 123–136.
20.
WuXYangYHanS, et al. (2021) Multi-objective optimization method for nuclear reactor radiation shielding design based on PSO algorithm. Annals of Nuclear Energy160: 108404.
21.
YassinFAliZAsmaA, et al. (2022) Enhancement neural control scheme performance using PSO adaptive rate: Experimentation on a transesterification reactor. Journal of Vibration and Control29: 3769–3782.
22.
ZerkaouiSDruauxFLeclercqE, et al. (2010) Indirect neural control for plant-wide systems: Application to the Tennessee eastman challenge process. Computers & Chemical Engineering34(2): 232–243.
23.
ZhangXWangYChenX, et al. (2018) Decentralized adaptive neural approximated inverse control for a class of large-scale nonlinear hysteretic systems with time delays. IEEE Transactions on Systems, Man, and Cybernetics: Systems49(12): 2424–2437.
24.
ZribiAChtourouMDjemelM (2018) A new PID neural network controller design for nonlinear processes. Journal of Circuits, Systems and Computers27(4): 1850065.
