Real-Time Hardware-in-the-Loop Evaluation of an RBFNN Controller for Water Level Control in an Uncertain Tripled-Tank System
DOI:
https://doi.org/10.15837/ijccc.2026.4.7460Keywords:
Tripled -Tank System, Opal-RT, HIL, RBFNN, intelligent controlAbstract
This paper addresses the problem of water-level regulation in a triple-tank system, where strong nonlinearities, dynamic coupling, external disturbances, and parameter uncertainties pose significant challenges for conventional model-based control methods. To overcome these limitations, a Radial Basis Function Neural Network (RBFNN)–based control strategy is proposed for regulating the water level in Tank 3 without requiring an accurate mathematical model of the system. The main contribution of this work lies in the real-time hardware-in-the-loop (HIL) implementation of an adaptive RBFNN-based control strategy using the OPAL-RT OP5707XG platform, enabling practical validation under realistic operating conditions. The proposed controller exploits the strong nonlinear approximation capability and fast learning characteristics of RBFNNs to enhance tracking accuracy, transient performance, and robustness under varying operating conditions. The effectiveness of the proposed method is evaluated through MATLAB/Simulink simulations and real-time HIL experiments. Two representative experimental scenarios are considered, including constant and continuously varying water level references, to comprehensively assess steady-state accuracy, transient response, adaptability, and real-time performance. Performance is quantitatively evaluated using standard error-based indices such as RMS, MAE, Mean Error, IAE, and ISE. Both simulation and real-time experimental results demonstrate that the proposed RBFNN controller enables the water level in Tank 3 to accurately track the desired reference trajectories with reduced overshoot, faster settling time, smoother responses, and lower cumulative tracking error compared with conventional PID and sliding mode control (SMC).
References
Kumar DD, Meenakshipriya B, Ram SS. Design of PSO based I-PD controller and PID controller for a spherical tank system. Indian J Sci Technol 2016;9(12):1-5. https://doi.org/10.17485/ijst/2016/v9i12/89926
Kumar DD, Meenakshipriya B. Design and implementation of nonlinear system using gain scheduled PI controller. Procedia Eng 2012;38:3105-3112. https://doi.org/10.1016/j.proeng.2012.06.361
Vincent AK, Nersisson R. Particle swarm optimization based PID controller tuning for level control of two tank system. In: Proceedings of the IOP Conference Series: Materials Science and Engineering. vol. 263. IOP Publishing; 2017. p. 052001. https://doi.org/10.1088/1757-899X/263/5/052001
Prasad GM, Rao AS. Evaluation of gap-metric based multi-model control schemes for nonlinear systems: an experimental study. ISA Trans 2019;94:246-254. https://doi.org/10.1016/j.isatra.2019.04.006
Rajesh P, Shajin FH, Rajani B, Sharma D. An optimal hybrid control scheme to achieve power quality enhancement in micro grid connected system. Int J Numer Model Electron Netw Devices Fields 2022:e3019. https://doi.org/10.1002/jnm.3019
Shajin FH, Rajesh P, Thilaha S. Bald eagle search optimization algorithm for cluster head selection with prolong lifetime in wireless sensor network. J Soft Comput Eng Appl 2020;1(1):7.
Rajesh P, Shajin FH, Cherukupalli K. An efficient hybrid tunicate swarm algorithm and radial basis function searching technique for maximum power point tracking in wind energy conversion system. J Eng Des Technol 2021. https://doi.org/10.1108/JEDT-12-2020-0494
Shajin FH, Rajesh P, Raja MR. An efficient VLSI architecture for fast motion estimation exploiting zero motion prejudgment technique and a new quadrant-based search algorithm in HEVC. Circuit Syst Signal Process 2022;41(3):1751-1774. https://doi.org/10.1007/s00034-021-01850-2
Liu SC, Lin SF. Robust sliding control for mismatched uncertain fuzzy time-delay systems using linear matrix inequality approach. J Chin Inst Eng 2013;36(5):589-597. https://doi.org/10.1080/02533839.2012.734557
Junyi C, Binggang C. Fractional-order control of pneumatic position servosystems. Math Probl Eng 2011;2011. https://doi.org/10.1155/2011/287565
Arunshankar J. Control of nonlinear two-tank hybrid system using sliding mode controller with fractional-order PI-D sliding surface. Comput Electr Eng 2018;71:953-965. https://doi.org/10.1016/j.compeleceng.2017.10.005
Fellani MA, Gabaj AM. PID controller design for two tanks liquid level control system using Matlab. Int J Electr Comput Eng 2015;5(3):436. https://doi.org/10.11591/ijece.v5i3.pp436-442
Demetriou MA. Spatial PID consensus controllers for distributed filters of distributed parameter systems. Syst Control Lett 2014;63:57-62. https://doi.org/10.1016/j.sysconle.2013.10.006
Carnevale C, Piazzi A, Visioli A. A methodology for integrated system identification, PID controller tuning and noncausal feedforward control design. IFAC Proc Vol 2008;41(2):13324-13329. https://doi.org/10.3182/20080706-5-KR-1001.02257
Ram AG, Lincoln SA. Real time implementation of fuzzy based adaptive PI controller for a spherical tank system. Int J Simul Syst Sci Technol 2013;14:1-8. https://doi.org/10.5013/IJSSST.a.14.06.01
Chandra IS, Gajpal T. Fuzzy logic controller based impedance source converter for PV grid connected system. 2016;5(8):149-154. https://doi.org/10.17577/IJERTV5IS080167
Abadi MR, Jalali AA. Fractional order PID controller tuning based on IMC. Int J Inf Technol Control Autom 2012;2:21-35. https://doi.org/10.5121/ijitca.2012.2403
Ram SS, Kumar DD, Meenakshipriya B. Designing of PID controllers for pH neutralization process. Indian J Sci Technol 2016;9(12). https://doi.org/10.17485/ijst/2016/v9i12/89940
Pandian BJ, Noel MM. Control of a bioreactor using a new partially supervised reinforcement learning algorithm. J Process Control 2018;69:16-29. https://doi.org/10.1016/j.jprocont.2018.07.013
Gurjar B, Chaudhari V, Kurode S. Parameter estimation based robust liquid level control of quadruple tank system-second order sliding mode approach. J Process Control 2021;104:1-10. https://doi.org/10.1016/j.jprocont.2021.05.009
Aksu IO, Coban R. Sliding mode PI control with backstepping approach for MIMO nonlinear cross-coupled tank systems. Int J Robust Nonlinear Control 2019;29(6):1854-1871. https://doi.org/10.1002/rnc.4469
Meng X, Yu H, Zhang J, Xu T, Wu H, Yan K. Disturbance observer-based feedback linearization control for a quadruple-tank liquid level system. ISA Trans 2021. https://doi.org/10.1016/j.isatra.2021.04.021
Bai T, Li S, Zou Y. Distributed MPC for reconfigurable architecture systems via alternating direction method of multipliers. IEEE/CAA J Autom Sin 2021;8(7):1336-1344. https://doi.org/10.1109/JAS.2020.1003195
Song SJ, Cai G, Liao BL, Lin XF. Real-time optimal control for three-tank level system via improved ADDHP method. In: 2009 IEEE International Conference on Control and Automation. 2009.
Hou Z, Liu S, Tian T. Lazy-learning-based data-driven model-free adaptive predictive control for a class of discrete-time nonlinear systems. IEEE Trans Neural Netw Learn Syst 2017;28(8):1914- 1928. https://doi.org/10.1109/TNNLS.2016.2561702
Radac MB, Precup RE, Roman RC. Data-driven model reference control of MIMO vertical tank systems with model-free VRFT and Q-learning. ISA Trans 2018;73:227-238. https://doi.org/10.1016/j.isatra.2018.01.014
Khan MK, Spurgeon SK. Robust MIMO water level control in interconnected twin-tanks using second order sliding mode control. Control Eng Pract 2006;14(4):375-386. https://doi.org/10.1016/j.conengprac.2005.02.001
Pan H, Wong H, Kapila V, de Queiroz MS. Experimental validation of a nonlinear backstepping liquid level controller for a state coupled two tank system. Control Eng Pract 2005;13(1):27-40. https://doi.org/10.1016/j.conengprac.2003.12.019
Almutair NB, Zribi M. Sliding mode control of coupled tanks. Mechatronics 2006;16(7):427-441. https://doi.org/10.1016/j.mechatronics.2006.03.001
Ng KC, Li Y, Murray-Smith DJ, Sharman KC. Genetic algorithms applied to fuzzy sliding mode controller design. In: First International Conference on Genetic Algorithms in Engineering Systems. 1995. https://doi.org/10.1049/cp:19951052
Moshiri B, Jalili-Kharaajoo M, Besharati F. Application of fuzzy sliding mode based on genetic algorithms to control of robotic manipulators. Emerg Technol Factory Autom 2003;2:169-172. https://doi.org/10.1109/ETFA.2003.1248691
Benayache R, Chrifi-Alaoui L, Bussy P, Castelain JM. Design and implementation of sliding mode controller with varying boundary layer for a coupled tanks system. In: 17th Mediterranean Conference on Control & Automation. 2009. p. 1215-1220. https://doi.org/10.1109/MED.2009.5164712
Levant A. Chattering analysis. IEEE Trans Autom Control 2010;55(6):1380-1389. https://doi.org/10.1109/TAC.2010.2041973
Floquet T, Spurgeon SK, Edwards C. An output feedback sliding mode control strategy for MIMO systems of arbitrary relative degree. Int J Robust Nonlinear Control 2010;21(2). https://doi.org/10.1002/rnc.1579
Derdiyok A, Basci A. The application of chattering-free sliding mode controller in coupled tank liquid-level control system. Korean J Chem Eng 2013;30(3):540-545. https://doi.org/10.1007/s11814-012-0177-y
Hou T. Experimental research on neural network PID control based on hydraulic pressure of 2 container water tank. J Lanzhou Jiaotong Univ 2009;28(3):41-43.
Evans JT, Gomm JB, Williams D, Lisboa PJG. Implementation and performance evaluation of an on-line neural network control scheme. In: International Conference on Control. 1994. https://doi.org/10.1049/cp:19940205
Ramli MS, Raja Ismail RMT, Ahmad MA, Mohamad Nawi S, Mat Hussin MA. Improved coupled tank liquid levels system based on swarm adaptive tuning of hybrid proportional-integral neural network controller. Am J Eng Appl Sci 2009;2. https://doi.org/10.3844/ajeassp.2009.669.675
Zhang TP, Ge SS. Adaptive neural control of MIMO nonlinear state time-varying delay systems with unknown dead-zones and gain signs. Automatica 2007;43:1021-1033. https://doi.org/10.1016/j.automatica.2006.12.014
Huang SJ, Chiou KC. An adaptive neural sliding mode controller for MIMO systems. J Intell Robot Syst 2006;46:285-301. https://doi.org/10.1007/s10846-006-9065-1
Tan KC, Li Y. Performance-based control system design automation via evolutionary computing. Eng Appl Artif Intell 2001;14(4):473-486. https://doi.org/10.1016/S0952-1976(01)00023-9
Krohling RA, Rey JP. Design of optimal disturbance rejection PID controllers using genetic algorithm. IEEE Trans 2001;5:78-82. https://doi.org/10.1109/4235.910467
Fang XL, Shen T, Feng XS. The bang-bang control of water tank system based on fuzzy decision. In: Ninth International Conference on Hybrid Intelligent Systems. IEEE Press; 2009. p. 127-131. https://doi.org/10.1109/HIS.2009.138
Khoei A, Hadidi Kh, Khorasani MR, Amirkhanzadeh R. Fuzzy level control of a tank with optimum valve movement. Fuzzy Sets Syst 2005;150:507-523. https://doi.org/10.1016/j.fss.2004.09.009
Yu J, Zhang T. Direct adaptive fuzzy control of nonlinear time-delay systems. Fuzzy Syst Math 2006;20(3):124-129.
Li Q, Fang Y, Song J, Wang J. The application of fuzzy control in liquid level system. Measur Technol Mech Autom 2010;3:776-778. https://doi.org/10.1109/ICMTMA.2010.200
Basci A, Derdiyok A. Real-time velocity and direction angle control of an automated guided vehicle. Int J Robot Autom 2014;29(3):227-233. https://doi.org/10.2316/Journal.206.2014.3.206-3838
Wang L, Mishra J, Zhu Y, Yu X. An improved sliding-mode current control of induction machine in presence of voltage constraints. IEEE Trans Ind Inform 2020;16(2):1182-1191. https://doi.org/10.1109/TII.2019.2944228
Wang Z, Zhu YZ, Xue H, Liang HJ. Neural networks-based adaptive event-triggered consensus control for a class of multi-agent systems with communication faults. Neurocomputing 2022;470:99-108. https://doi.org/10.1016/j.neucom.2021.10.059
Zhao X, Shi P, Zheng X, Zhang J. Intelligent tracking control for a class of uncertain high-order nonlinear systems. IEEE Trans Neural Netw Learn Syst 2019;21(9):1976-1982. https://doi.org/10.1109/TNNLS.2015.2460236
He W, Dong Y, Sun C. Adaptive neural impedance control of a robotic manipulator with input saturation. IEEE Trans Syst Man Cybern 2016;46(3):334-344. https://doi.org/10.1109/TSMC.2015.2429555
Ngo TQ, Duong MK, Pham DC, Nguyen DN. Adaptive Wavelet CMAC tracking control for induction servomotor drive system. J Electr Eng Technol 2019;14(1):209-218. https://doi.org/10.1007/s42835-018-00029-1
Yang R, Yang C, Chen M, Annamalai AS. Discrete-time optimal adaptive RBFNN control for robot manipulators with uncertain dynamics. Neurocomputing 2017;234:107-114. https://doi.org/10.1016/j.neucom.2016.12.048
Wang Z, Yuan J, Pan Y,Wei J. Neural network-based adaptive fault tolerant consensus control for a class of high order multi-agent systems with input quantization and time-varying parameters. Neurocomputing 2017;266:315-324. https://doi.org/10.1016/j.neucom.2017.05.043
Ngo TQ, Tran TH, Uyen HTT, Nguyen VT, Duong TD. Adaptive task-space control of five-bar parallel robot dynamic model with fully unknown using radial basis function neural networks for high-precision applications. J Robot Control 2025;6(4):1624-1635. https://doi.org/10.18196/jrc.v6i4.26537
Pham Q, Nguyen T, Tran T, Quynh B, Ngo T, Nguyen V, Le T. Raspberry Pi-based rapid control prototyping for PMSM drive system using RBFNN on OPAL-RT platform. Int J Robot Control Syst 2025;5(6):2669-2684. https://doi.org/10.31763/ijrcs.v5i6.2240
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Trung Nhan Nguyen, Thanh Quyen Ngo, Thanh Hai Tran, Ngoc Hoi Le, Van Sy Nguyen, Tong Tan Hoa Le
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
ONLINE OPEN ACCES: Acces to full text of each article and each issue are allowed for free in respect of Attribution-NonCommercial 4.0 International (CC BY-NC 4.0.
You are free to:
-Share: copy and redistribute the material in any medium or format;
-Adapt: remix, transform, and build upon the material.
The licensor cannot revoke these freedoms as long as you follow the license terms.
DISCLAIMER: The author(s) of each article appearing in International Journal of Computers Communications & Control is/are solely responsible for the content thereof; the publication of an article shall not constitute or be deemed to constitute any representation by the Editors or Agora University Press that the data presented therein are original, correct or sufficient to support the conclusions reached or that the experiment design or methodology is adequate.
