Back Propagation Neural Network for Controlling Coupled Water Tank


  • Halim Mudia Department of Electrical Engineering, State Islamic University of Sultan Syarif Kasim Riau



Backpropagation, Coupled Water Tank, Level Control, Neural Network, machine learning


A well-prepared abstract enables the reader to identify the basic content of the level and flow control in tanks is the heart of all chemical engineering systems. The control of liquid level in tanks and flow between tanks is a basic problem in the process industries. Many times the liquids will be processed by chemical or mixing treatment in the tanks, but always the level of fluid in the tanks must be controlled and the flow between tanks must be regulated in presence of non-linearity. Therefore, in this paper will use neural network based on backpropagation (BP) to control of level 2 in the tank 2 with the setpoint of 10 centimeters and can follow the setpoint changes to 8 centimeters given in 225 seconds. The results show that a neural network based on backpropagation can follow setpoint given with steady-state error is 0 cm, overshoot is 0%, the rising time is 49 seconds, settling time is 52 seconds and can follow setpoint changes in 51 seconds.


Download data is not yet available.


Konstantinos N, Charalampos G, Giannakakis, Ioannis K, Ilias S, Alex A. Nonlinear Control of a DC-Motor Based on Radial Basis Function Neural Networks. International Symposium on Innovations in Intelligent Systems and Applications. Turkey. 2011; 611-615.

Y. C. Liang et al., "Proper orthogonal decomposition and its application- Part II: Model reduction for MEMS dynamical analysis," J. Sound Vib., vol. 256, pp. 515-532, 2000.

C. G. Looney, Pattern Recognition Using Neural Networks. NewYork: Oxford Univ. Press, 1997.

K. Hornik, "Approximation capabilities of multilayer feedforward networks," Neural Netw., vol. 4, 1991.

M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken, "Multilayer feedforward networks with a nonpolynomial activation function can approximate any function," Neural Netw., vol. 6, 1993.

T. L. Fine and S. Mukherjee, "Parameter convergence and learning curves for neural networks," Neural Computat., vol. 11, pp. 747-769,1999.

M. Gori and M. Maggini, "Optimal convergence of on-line backpropagation," IEEE Trans. Neural Netw., pp. 251-254, 1996.

S. Mukherjee and T. L. Fine, "Online steepest descent yields weights with nonnormal limiting distribution," Neural Computat., vol. 8, pp. 1075-1084, 1996.

R. Battiti, "First- and second-order methods for learning: Between steepest sescent and Newton's method," Neural Netw., vol. 4, pp. 141-166, 1992.

Y. C. Liang et al., "Successive approximation training algorithm for feedforward neural networks," Neurocomput., vol. 42, pp. 311-322, 2002.

A. J. Shepherd, Second-Order Methods for Neural Networks (Fast and Reliable Training Methods for Multi-Layer Perceptrons). Berlin Germany: Springer-Verlag, 1996.

W. B. Liu and Y. H. Dai, "Minimization algorithms based on supervisor and searcher cooperation: I-fast and robust gradient algorithms for minminimization problems with strong noise," J. Optim. Theory Appl., vol. 111, pp. 359-379, 2001.

S. W. Ellacott and D. Bose, Neural Networks-Deterministic Methods of Analysis: Thomas Computer Press, 1996.

S.W. Ellacott, "The numerical analysis approach of neural networks," in Mathematical Approaches to Neural Networks, J. G. Taylor, Ed: North Holland, 1993, pp. 103-138.

S. Haykin, Neural Networks, 2nd ed. Englewood Cliffs, NJ: PrenticeHall, 1999.

Z. Luo, "On the convergence of the LMS algorithm with adaptive learning rate for linear feedforward networks," Neural Computat., vol. 3, pp. 226-245, 1991.

P. Sollich and D. Barber, "Online learning from finite training sets and robustness to input bias," Neural Computat., vol. 10, pp. 2201-2217, 1998.

W. Finnoff, "Diffusion approximations for the constant learning rate backpropagation algorithm and resistance to locol minima," Neural Computat., vol. 6, pp. 285-295, 1994.

S.-H. Oh, "Improving the error backpropagation algorithm with a modified error function," IEEE Trans. Neural Netw., vol. 8, no. 3, pp. 799-803, May 1997.

Z. Li, W. Wu, and Y. Tian, "Convergence of an online gradient method for feedforward neural networks with stochastic inputs," J. Computat. Appl. Math., vol. 163, no. 1, pp. 165-176, 2004.

W. Wu, G. R. Feng, and X. Li, "Training multylayer perceptrons via minimization of sum of ridge functions," Adv. Computat. Math., vol. 17, pp. 331-347, 2002.

Jiffy A. J, Jaffar, Riya. M. F. Modelling and Control of Coupled Tank Liquid Level System Using Backstepping Method. International Journal of Engineering Research & Technology (IJERT). 2015; 4(6): 667-671.

Abraham L, Senthilkumar, Selvakumar. Design of PI Controller Using Characteristics Ratio Assignment Method for Coupled Tank SISO Process. International Journal of Computer Application. 2011; 25(9): 49-53.

Hur A, Sajjad A, Shahid Q. Sliding Mode Control Of Coupled Tank Liquid Level Control System. IEEE 10th International Conference on Frontires of Information Technology. Islamabad. 2012; 325-330.

Mahyuddi N. M, Arshad R. M, Zaharuddin M. Simulation of Direct Model Reference Adaptive Control on a Coupled Tank System Using Non-linear Pant Model. International Conference on Control Instrumentation and Mechatronics Engineering. Johor. 2007; 569-576.

Saad M, Albagul A, Abueejela Y. Performance Comparison between PI and MRAC for Coupled Tank Rystem. Journal of Automation and control Engineering. 2014; 2 (3): 316-321.

Halim M. Comparative Study of Madani-type and Sugeno-type Fuzzy Inference System for Coupled Water Tank. Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM). 2020; 3(1): 39-44.




How to Cite

Mudia, H. (2020). Back Propagation Neural Network for Controlling Coupled Water Tank. Bulletin of Computer Science and Electrical Engineering, 1(1), 12–18.