Improved Set-point Tracking Control of an Unmanned Aerodynamic MIMO System Using Hybrid Neural Networks

Year 2024, Volume: 6 Issue: 1, 51 - 62, 31.03.2024

David Mohammed Ezekiel Ravi Samikannu Oduetse Matsebe

https://doi.org/10.51537/chaos.1389409

Abstract

Artificial neural networks (ANN), an Artificial Intelligence (AI) technique, are both bio-inspired and nature-inspired models that mimic the operations of the human brain and the central nervous system that is capable of learning. This paper is based on a system that optimizes the performance of an uncertain unmanned nonlinear Multi-Input Multi-Output (MIMO) aerodynamic plant called Twin Rotor MIMO System (TRMS). The pitch and yaw angles which are challenging to control and optimize in practice, are being used as the input to the Nonlinear Auto-Regressive with eXogenous (NARX) model, and eventually trained. The training features use the Matlab Deep Learning Toolbox. The NARX structure has its core in the neural networks’ architecture. Data is collected from the TRMS testbed which is used to train the network. ANN as a Hybrid intelligent control strategy of ANN in combination with Pattern Search and Genetic Algorithm, is then utilized to optimize the parameters of the neural networks. At the end it was validated, tested and the optimized system run in simulation and compared with other intelligent and conventional controllers, with the proposed controller outperforming them, giving a very fast tracking control, stable and optimal performance that satisfactorily met all our design requirements.

Keywords

Artificial neural network, Nonlinear autoregressive with eXogenous, Twin rotor MIMO system, Multi-input multioutput, Aerodynamic, Unmanned helicopter model

Ethical Statement

Subject: Declaration of Conflict of Interest. We are submitting our paper Improved Set-point Tracking Control of an Unmanned Aerodynamic MIMO System Using Hybrid Neural Networks to publish in your journal. I acknowledge that this paper is the original research article of the authors. We have reviewed our paper carefully. The authors ensure that no contractual relations exist that would affect the publication of information submitted in the manuscript. There is no conflict of interest of any sort.

References

• Abbas, N. and X. Liu, 2022 A mixed dynamic optimization with μ- synthesis (dk iterations) via optimal gain for varying dynamics of decoupled twin-rotor mimo system based on the method of inequality (moi). Journal of Control Engineering and Applied Informatics 24: 13–23.
• Abdulwahhab, O.W. and N. H. Abbas, 2017 A new method to tune a fractional-order pid controller for a twin rotor aerodynamic system. Arabian Journal for Science and Engineering 42: 5179– 5189.
• Agand, P., M. A. Shoorehdeli, and A. Khaki-Sedigh, 2017 Adaptive recurrent neural network with lyapunov stability learning rules for robot dynamic terms identification. Engineering applications of artificial intelligence 65: 1–11.
• Ahmad, M., A. Ali, and M. A. Choudhry, 2016 Fixed-structure h∞ controller design for two-rotor aerodynamical system (tras). Arabian Journal for Science and Engineering 41: 3619–3630.
• Ahmad, S. M., A. J. Chipperfield, and M. O. Tokhi, 2000a Dynamic modelling and control of a 2-dof twin rotor multi-input multi-output system. In 2000 26th Annual Conference of the IEEE Industrial Electronics Society. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation. 21st Century Technologies, volume 2, pp. 1451–1456, IEEE.
• Ahmad, S. M., A. J. Chipperfield, and O. Tokhi, 2000b Dynamic modeling and optimal control of a twin rotor mimo system. In Proceedings of the IEEE 2000 National Aerospace and Electronics Conference. NAECON 2000. Engineering Tomorrow (Cat. No. 00CH37093), pp. 391–398, IEEE.
• Alam, M. S., F. M. Aldebrez, and M. O. Tokhi, 2004 Adaptive command shaping using genetic algorithms for vibration control. In Proceedings of IEEE SMC UK-RI Third Workshop on Intelligent Cybernetic Systems, pp. 7–8, IEEE.
• Bensidhoum, T., F. Bouakrif, and M. Zasadzinski, 2023 A high order p-type iterative learning control scheme for unknown multi input multi output nonlinear systems with unknown input saturation. International Journal of Computational and Applied Mathematics & Computer Science 3: 27–31.
• Castillo, E., B. Guijarro-Berdinas, O. Fontenla-Romero, A. Alonso- Betanzos, and Y. Bengio, 2006 A very fast learning method for neural networks based on sensitivity analysis. Journal of Machine Learning Research 7.
• Chu, S. R., R. Shoureshi, and M. Tenorio, 1990 Neural networks for system identification. IEEE Control systems magazine 10: 31–35.
• Coelho, J., R. Neto, D. Afonso, C. Lebres, H. Fachada, et al., 2007a Helicopter system modelling and control with matlab. CEE’07- 2nd INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING pp. 110–117.
• Coelho, J., R. M. Neto, C. Lebres, H. Fachada, N. M. Ferreira, et al., 2007b Application of fractional algorithms in the control of a helicopter system. In Symposium on Applied Fractional Calculus, pp. 1–12.
• Coelho, J., R. M. Neto, C. Lebres, V. Santos, N. M. Ferreira, et al., 2008 Application of fractional algorithms in the control of a twin rotor multiple input-multiple output system. ENOC 08 pp. 1–8.
• Darus, I. Z. M. and Z. A. Lokaman, 2010 Dynamic modelling of twin rotor multi system in horizontal motion. Jurnal Mekanikal . Demuth, H. B. and M. H. Beale, 2000 Neural Network Toolbox: For Use with MATLAB®. MathWorks.
• El-Fakdi, A. and M. Carreras, 2013 Two-step gradient-based reinforcement learning for underwater robotics behavior learning. Robotics and Autonomous Systems 61: 271–282.
• Ezekiel, D. M., R. Samikannu, and O. Matsebe, 2021 Pitch and yaw angular motions (rotations) control of the 1-dof and 2-dof trms: A survey. Archives of Computational Methods in Engineering 28: 1449–1458.
• Ezekiel, D. M., R. Samikannu, and M. Oduetse, 2020 Modelling of the twin rotor mimo system (trms) using the first principles approach. In 2020 International Conference on Computer Communication and Informatics (ICCCI), pp. 1–7, IEEE.
• Ghasemiyeh, R., R. Moghdani, and S. S. Sana, 2017 A hybrid artificial neural network with metaheuristic algorithms for predicting stock price. Cybernetics and systems 48: 365–392.
• Khishe, M., M. R. Mosavi, and A. Moridi, 2018 Chaotic fractal walk trainer for sonar data set classification using multi-layer perceptron neural network and its hardware implementation. Applied Acoustics 137: 121–139.
• Lin, S. and A. A. Goldenberg, 2001 Neural-network control of mobile manipulators. IEEE Transactions on Neural Networks 12: 1121–1133.
• Ljung, L. and S. Gunnarsson, 1990 Adaptation and tracking in system identification—a survey. Automatica 26: 7–21.
• Moness, M. and T. Diaa-Eldeen, 2017 Experimental nonlinear identification of a lab-scale helicopter system using mlp neural network. In 2017 13th International Computer Engineering Conference (ICENCO), pp. 166–171, IEEE.
• Mosbah, H. and M. E. El-Hawary, 2017 Optimization of neural network parameters by stochastic fractal search for dynamic state estimation under communication failure. Electric Power Systems Research 147: 288–301.
• Nasir, A. N. K. and M. O. Tokhi, 2014 A novel hybrid bacteriachemotaxis spiral-dynamic algorithm with application to modelling of flexible systems. Engineering Applications of Artificial Intelligence 33: 31–46.
• Palepogu, K. R. and S. Mahapatra, 2023 Pitch orientation control of twin-rotor mimo system using sliding mode controller with state varying gains. Journal of Control and Decision pp. 1–11.
• Patan, K. and M. Patan, 2023 Fault-tolerant design of non-linear iterative learning control using neural networks. Engineering Applications of Artificial Intelligence 124: 106501.
• Rahideh, A., A. H. Bajodah, and M. H. Shaheed, 2012a Real time adaptive nonlinear model inversion control of a twin rotor mimo system using neural networks. Engineering Applications of Artificial Intelligence 25: 1289–1297.
• Rahideh, A., A. H. Bajodah, and M. H. Shaheed, 2012b Real time adaptive nonlinear model inversion control of a twin rotor mimo system using neural networks. Engineering Applications of Artificial Intelligence 25: 1289–1297.
• Rahideh, A., M. H. Shaheed, and H. J. C. Huijberts, 2008 Dynamic modelling of a trms using analytical and empirical approaches. Control Engineering Practice 16: 241–259.
• Rere, L. R., M. I. Fanany, and A. M. Arymurthy, 2016 Metaheuristic algorithms for convolution neural network. Computational intelligence and neuroscience .
• Salimi, H., 2015 Stochastic fractal search: a powerful metaheuristic algorithm. Knowledge-based systems 75: 1–18.
• Sivadasan, J. and J. R. J. Shiney, 2023 Modified nondominated sorting genetic algorithm-based multiobjective optimization of a cross-coupled nonlinear pid controller for a twin rotor system. Journal of Engineering and Applied Science 70: 133.
• Sjöberg, J., H. Hjalmarsson, and L. Ljung, 1994 Neural networks in system identification. IFAC Proceedings Volumes 27: 359–382.
• Tavakolpour, A. R., M. Mailah, I. Z. M. Darus, and O. Tokhi, 2010 Self-learning active vibration control of a flexible plate structure with piezoelectric actuator. Simulation Modelling Practice and Theory 18: 516–532.
• Tijani, I. B., R. Akmeliawati, A. Legowo, and A. Budiyono, 2014 Nonlinear identification of a small scale unmanned helicopter using optimized narx network with multiobjective differential evolution. Engineering Applications of Artificial Intelligence 33: 99–115.
• Toha, S. F. and M. O. Tokhi, 2009 Dynamic nonlinear inverse-model based control of a twin rotor system using adaptive neuro-fuzzy inference system. In 2009 Third UKSim European Symposium on Computer Modeling and Simulation, pp. 107–111, IEEE.
• Toha, S. F. and M. O. Tokhi, 2010 Augmented feedforward and feedback control of a twin rotor system using real-coded moga. In IEEE Congress on Evolutionary Computation, pp. 1–7, IEEE.
• TRahman, T. A., A. As’arry, N. A. Jalil, and R. Kamil, 2019 Dynamic modelling of a flexible beam structure using feedforward neural networks for active vibration control. International Journal of Automotive and Mechanical Engineering 16: 6263–6280.
• Wai, R. J., 2003 Tracking control based on neural network strategy for robot manipulator. Neurocomputing 51: 425–445.
• Widrow, B. and M. E. Hoff, 1960 Adaptive switching circuits. In IRE WESCON convention record, volume 4, pp. 96–104.
• Wu, H., Y. Zhou, Q. Luo, and M. A. Basset, 2016 Training feedforward neural networks using symbiotic organisms search algorithm. Computational intelligence and neuroscience .
• Xia, Y. and J. Wang, 2001 A dual neural network for kinematic control of redundant robot manipulators. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 31: 147– 154.
• Yaghini, M., M. M. Khoshraftar, and M. Fallahi, 2013 A hybrid algorithm for artificial neural network training. Engineering Applications of Artificial Intelligence 26: 293–301.
• Yoo, S. J., Y. H. Choi, and J. B. Park, 2006 Generalized predictive control based on self-recurrent wavelet neural network for stable path tracking of mobile robots: adaptive learning rates approach. IEEE Transactions on Circuits and Systems I: Regular Papers 53: 1381–1394.