Abstract
A conventional Proportional–Integral–Derivative (PID) controller is not able to adapt to the changes in the system of a plant having nonlinear dynamics. In this paper, a Neural Network PID (NN-PID) controller is designed based on Multi-layer Neural Network (MLN) technique for controlling of the liquid level in a nonlinear surge tank system. A separate MLN identifier is implemented to approximate the plant’s dynamics which operates in parallel to the controller with disturbance and parametric uncertainties in the system. The NN-PID controller works using backpropagation algorithm and weights are updated according to the gradient descent based learning rule. The simulation results show that as the variations occur in the plant, MLN identifier follows the plant’s dynamics by adjusting its parameters and the controller reads just the plant’s output to the desired level by adjusting its own parameters. In addition to this, NN-PID controller response is much accurate and faster than the conventional PID controller and an improvement of 97.35% was achieved in terms of ISE.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
K.J. Astrom, T. Hagglund, Advanced PID Control (Research T. Park, NC, ISA, 2005)
I.-L. Chien, P.S. Fruehauf, Consider IMC tuning to improve controller performance. Chem. Eng. Prog. 86, 33–41 (1990)
K.J. Astrom, B. Wittenmark, Adaptive Control (Dover Publications, Inc., Mineola, NY, USA, 2008)
P. Osburn, H. Whitaker, A. Kezer, New Developments in the Design of Model Reference Adaptive Control Systems (Institute of the Aerospace Sciences, Easton, PA, USA, 1961)
K.J. Astrom, B. Wittenmark, On self-tuning regulators. Automatica 9, 185–199 (1973)
B. Egardt, Stability of Adaptive Controllers (Springer, Berlin, Germany, 1979)
K.S. Narendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Netw. 1, 4–27 (1990). https://doi.org/10.1109/72.80202
L. Chen, K.S. Narendra, Identification and control of a nonlinear discrete-time system based on its linearization: a unified framework. IEEE Trans. Neural Netw. 15(3), 663–673 (2004). https://doi.org/10.1109/TNN.2004.826206
F.C. Chen, H.K. Khalil, Adaptive control of nonlinear systems using neural networks. Int. J. Control 55(6), 1299–1317 (1992). https://doi.org/10.1080/00207179208934286
S.L. Dai, C. Wang, F. Luo, Identification and learning control of ocean surface ship using neural networks. IEEE Trans. Industr. Inf. 8(4), 801–810 (2012). https://doi.org/10.1109/TII.2012.2205584
T. Hayakawa, W.M. Haddad, Neural network adaptive control for a class of nonlinear uncertain dynamical system with asymptotic stability guarantees. IEEE Trans. Neural Netw. 19(1), 80–89 (2008). https://doi.org/10.1109/tnn.2007.902704
V. Kumar, P. Gaur, A.P. Mittal, ANN based self tuned PID like adaptive controller design for high performance PMSM position control. Expert Syst. Appl. 41(17), 7995–8002 (2014). https://doi.org/10.1016/j.eswa.2014.06.040
Y. Zhao, X. Du, G. Xia, L. Wu, A novel algorithm for wavelet neural networks with application to enhanced PID controller design. Neuro Comput. 158(c), 257–267 (2015). https://doi.org/10.1016/j.neucom.2015.01.015
R. Kumar, S. Srivastava, J.R.P. Gupta, Modeling and control of one-link robotic manipulator using neural network based PID controller, in Proceedings of International Conference on Advances in Computing, Communications and Informatics (ICACCI), 21–24 Sept 2016, Jaipur, India
R. Kumar, S. Srivastava, J.R.P. Gupta, Modeling and adaptive control of nonlinear dynamical systems using radial basis function network. Soft. Comput. 21(15), 4447–4463 (2017). https://doi.org/10.1007/s00500-016-2447-9
L. Behera, I. Kar, Intelligent Systems and Control Principles and Applications (Oxford University Press Inc., Oxford, 2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Agrawal, A., Goyal, V., Mishra, P. (2019). Adaptive Control of a Nonlinear Surge Tank-Level System Using Neural Network-Based PID Controller. In: Malik, H., Srivastava, S., Sood, Y., Ahmad, A. (eds) Applications of Artificial Intelligence Techniques in Engineering. Advances in Intelligent Systems and Computing, vol 698. Springer, Singapore. https://doi.org/10.1007/978-981-13-1819-1_46
Download citation
DOI: https://doi.org/10.1007/978-981-13-1819-1_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-1818-4
Online ISBN: 978-981-13-1819-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)