Performance Comparison of Machine Learning Approach for Dynamic System Identification and Control
Keywords:
Dynamic System, Control, Identification, RBF, FLANN, Artificial Neural Network.Abstract
Mostly the industrial control for dynamic system is the challenge in recent research. The problem is too complex due to non-linear and dynamic nature. To tackle this problem popular model is chosen as Functional link Artificial Neural Network (FLANN). However, the training is performed with kernel based least mean square (K-LMS) algorithm. Further three different kernels are experienced for the proposed model. Finally, the mixed kernel is proposed for LMS based training to the FLANN model. It is capable of performing at a higher level for faster convergence while maintaining its robust characteristics. However, because of its useful function approximation properties, it has been selected as an alternate method for identifying nonlinear systems. The proposed ANNs model has been demonstrated to be applicable to the modelling of complicated dynamical systems. A comparison is made among different kernel approached as well as with the earlier methods. The results of various strategies, such as Sliding Mode, RBFN, and k-LMS-based FLANN, have been compared in a performance analysis.
Downloads
References
L.Ljung, “Perspectives on system identification”. Annual Reviews in Control, vol-3, no.1, 2010, pp.1-12.
A. K. Tangirala, “Principles of system identification: theory and practice.” Crc Press.2018.
W. R. Cluett, “Principles of System Identification: Theory and Practice [Bookshelf].” IEEEControl Systems Magazine, Vol. 37, no-2, 2017, pp.181-184.
J. Benesty, & Y. Huang, “Adaptive signal processing: applications to real-world problems”, Springer Science & Business Media, 2013.
G. John, & M. R. Charles, “Algorithms for statistical signal processing,” Prentice Hall, London,2002.
A. Feuer, & E. Weinstein, “Convergence analysis of LMS filters with uncorrelated Gaussian data,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol-33, no.1,1985, pp-222-230.
Y. Zou, S. C. Chan, & T. S., Ng. “Least mean M-estimate algorithms for robust adaptive filtering in impulse noise,” IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, vol-47, no-12, 2000, pp-1564-1569.
Y.Zhou, S. C. Chan, & K. L. Ho, “New sequential partial-update least mean M-estimate algorithms for robust adaptive system identification in impulsive noise,” IEEE Transactions on Industrial Electronics, vol-58, no.9, 2010, pp- 4455-4470.
P. Song, & H. Zhao “Affine-projection-like M-estimate adaptive filter for robust filtering in impulse noise,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol-66, no.12, 2019, pp- 2087-2091.
G.Wang & H. Zhao, “Robust adaptive least mean M-estimate algorithm for censored regression,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021.
L. Lu, L. Chen, Z. Zheng, Y. Yu & X. Yang, “Behavior of the LMS algorithm with hyperbolic secant cost,” Journal of the Franklin Institute, vol-357, no.3, 2020, pp- 1943-1960.
W. Gao, J. Chen, C. Richard, J. C. M Bermudez, & J. Huang, Convergence analysis of the augmented complex klms algorithm with pre-tuned dictionary, IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP,2015, pp. 2006-2010. IEEE.
L. Lu, H. Zhao, & B. Champagne, “Distributed Nonlinear System Identification in $alpha $-Stable Noise.” IEEE Signal Processing Letters ,2018, vol-25, no-7, pp- 979-983.
S. Jain, & S. Majhi, “Zero-Attracting Kernel Maximum Versoria Criterion Algorithm for Nonlinear Sparse System Identification”. IEEE Signal Processing Letters,2022, vol-29, pp-1546-1550.
H. Sira-Ramirez, E.Colina-Morles, and E. Rivas- “Francklin 'Slidingmode-based adaptive learning in dynamical-filter-weights neurons', International Journal of Control,73:8,678-685, 2000.
B. Widrow, and M. A., Lehr, 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proceedings IEEE, vol-78, pp-1415-1442,1990.
H. Sira-Ramlirez and E. Colina-Morles, “A sliding mode strategy for adaptive learning in adalines.IEEE Transactions on Circuits and Systems Ð I: Fundamental Theory and Applications”, 1995.vol-42, pp-1001-1012.
D. Shang, X. Li, M. Yin, & F. Li, “Dynamic modeling and fuzzy compensation sliding mode control for flexible manipulator servo system. Applied Mathematical Modelling”, 2022, 107, 530-556.
X. Su, Y. Xu & X. Yang, “Neural network adaptive sliding mode control without overestimation for a maglev system. Mechanical Systems and Signal Processing, 2022, vol- 168, pp- 108661.
N. Wang & F. Hao, “Event-triggered sliding mode control with adaptive neural networks for uncertain nonlinear systems. Neurocomputing,” 2021, vol- 436, pp-184-197.
H. Rabiee, M. Ataei & M. Ekramian, “Continuous nonsingular terminal sliding mode control based on adaptive sliding mode disturbance observer for uncertain nonlinear systems”. Automatica, 2019, vol-109, pp-108515.
R. K. Pattanaik, & M. N. Mohanty, “Nonlinear system identification for speech model using linear predictive coefficients based radial basis function. Journal of Information and Optimization Sciences,” 2022. Vol-43no-5, 1139-1150.
R. K. Pattanaik, S. K. Mohapatra, M. N. Mohanty, & B. K. Pattanayak, “System identification using neuro fuzzy approach for IoT application.” Measurement: Sensors, 2022, pp- 100485.
R. K. Pattanaik, B. K. Pattanayak, & M. N. Mohanty, “Use of multilayer recursive model for non-linear dynamic system identification.” Journal of Statistics and Management Systems, vol-25, no-6,2022, pp-1479-1490.
A.G. Parlos, K.T. Chong, A.F. Atiya, “Application of recurrent multilayer perceptron in modelling of complex process dynamics,” IEEE Trans. Neural Networks, 2000, vol-5, pp. 255–266.
B. Prasad, R. Kumar, & M. Singh, “Performance Analysis of Heat Exchanger System Using Deep Learning Controller”. IJEER, 2022, vol-10, no-2, pp- 327-334.
Kasiselvanathan, M., Lakshminarayanan, S., Prasad, J., Gurumoorthy, K. B., & Devaraj, S. A, “performance Analysis of MIMO System Using Fish Swarm Optimization Algorithm’”. International Journal of Electrical and Electronics Research, 2022, Vol-10, no-2, pp- 167-170.
R. K. Pattanaik, M. Sarfraz, & M. N. Mohanty, “Nonlinear System Parameterization and Control using Reduced Adaptive Kernel Algorithm. International Journal of Industrial Engineering & Production Research,” 2022, Vol-33, no-4, pp- 1-16.
R. K., Pattanaik, & M. N. Mohanty, (2022, “Nonlinear System Identification Using Robust Fusion Kernel-Based Radial basis function Neural Network. International Conference on Emerging Smart Computing and Informatics (ESCI) IEEE,2022, pp. 1-5.
N. Sahu and P. K. Dash “Development and implementation of a novel adaptive filter for nonlinear dynamic system identification”. In International Journal of Automation and Control (IJAAC), 2011, Vol-5, No-2, pp-171-188.
A. H. Sayed, Fundamentals of Adaptive Filtering, John Wiley, New Jersey, 2003.
Simon S. Haykin, Adaptive Filter Theory, Prentice Hall, Upper Saddle River, NJ 07458, USA, fourth edition, 2002.
Martin T. Hagan, Howard B. Demuth, Mark H. Beale, Neural network design (2nd Edition), PWS Publishing Co. Boston, MA, USA©1996.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
