Research Article
BibTex RIS Cite

A Hybrid Algorithm for Adaptive Neuro-controllers

Year 2023, , 87 - 97, 01.04.2023
https://doi.org/10.34248/bsengineering.1238543

Abstract

In this study, a novel hybrid algorithm consisting of the least mean square and backpropagation neural network is proposed to auto-adjust adaptive proportional integral derivative (PID) controller gains for improving the transient response of linear systems. The hybrid approach comprises the scheme of the two algorithms running in parallel and updates PID gains simultaneously. All algorithms are implemented on the same linear system and present a general framework for different scenarios such as initial PID gains, learning rates, and target functions. The results show that the presented hybrid algorithm has better accuracy, precision, F1-score, adaptability, and robustness than origin algorithms, and significantly improves the controllability in most of the system scenarios. It also exhibits better performance in periodic incremental and decremental targets compared to origin algorithms. Different hybridization levels are also simulated and are highlighted as significant features of their performance. This work can be expanded to the combination of other well-known algorithms, paving the way to significant improvements in control system applications.

References

  • Adar NG. 2021. Real time control application of the robotic arm using neural network based inverse kinematics solution. Sakarya Univ J Sci, 25(3): 849-857.
  • Akhyar S, Omatu S. 1993. Self-tuning PID control by neural networks. IJCNN '93-Nagoya: Proceedings of 1993 International Joint Conference on Neural Networks, October 25-29, 1993, New York, US, pp: 2749-2752.
  • Alkrwy A, Hussein AA, Atyia TH, Khamees M. 2021. Adaptive tuning of PID controller using crow search algorithm for DC motor. Mater Sci Eng, 1076: 012001.
  • Ang K. H., Chong G., Li Y. 2005. PID control system analysis, design, and technology, IEEE Trans. Control Syst. Technol., vol. 13, no. 4, pp: 559-576.
  • Antony Dhas MM, Chandrasekara S. 2019. Particle swarm intelligence based univariate parameter tuning of recursive least square algorithm for optimal heart sound signal filtering. Gazi Univ J Sci, 32(3): 928-943.
  • Bai C, Zhang Z. 2018. A least mean square based active disturbance rejection control for an inertially stabilized platform. Optik, 174: 609-622.
  • Bolton W. 2015. Instrumentation and Control Systems. Newness-Elsevier, New York, US, pp: 99-121.
  • Carvalho G, Guedes I, Pinto M, Zachi A, Almeida L, Andrade F, Melo AG. 2021. Hybrid PID-Fuzzy controller for autonomous UAV stabilization. 14th IEEE International Conference on Industry Applications, August 15-18, 2021, São Paulo, Brazil, pp: 1296-1302.
  • Chen C, Gu GX. 2020. Generative deep neural networks for inverse materials design using backpropagation and active learning. Adv Sci, 7(5): 1-10.
  • Conker C, Baltacioglu MK. 2020. Fuzzy self-adaptive PID control technique for driving HHO dry cell systems. Int J Hydrogen Ener, 45(49): 26059-26069.
  • Dogo EM, Afolabi OJ, Nwulu NI, Twala B, Aigbavboa CO. 2018. A comparative analysis of gradient descent-based optimization algorithms on convolutional neural networks. International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS), December 21-22, 2018, Belagavi, India, pp: 92-99.
  • El-Nagar AM, Zaki AM, Soliman FAS, El-Bardini M. 2022. Hybrid deep learning controller for nonlinear systems based on adaptive learning rates. Int J Control, DOI: 10.1080/00207179.2022.2067080.
  • Guo B, Liu H, Luo Z, Wang F. 2009. Adaptive PID controller based on BP neural network. First IITA International Joint Conference on Artificial Intelligence, April 25-26, 2009, Hainan Island, China, pp: 148.
  • Haykin S, Widrow B. 2003. Least-mean-square adaptive filters. John Wiley & Sons, New York, US, pp: 175-241.
  • Haykin S. 2005. Adaptive filter theory. Pearson Education, Lahor, India, pp: 365-438.
  • Hernández-Alvarado R, García-Valdovinos LG, Salgado-Jiménez T, Gómez-Espinosa A, Fonseca-Navarro F. 2016. Neural network-based self-tuning PID control for underwater vehicles. Sensors, 16: 1429.
  • Hou Z, Xiong S. 2019. On model-free adaptive control and its stability analysis. IEEE Transact Auto Control, 64(11): 4555-4569.
  • Jaleel JA, Thanvy N. 2013. A comparative study between PI, PD, PID and lead-lag controllers for power system stabilizer. International Conference on Circuits, Power and Computing Technologies, March 20-21i 2013, New York, US, pp: 456-460.
  • Karchi N, Kulkarni DB. 2021. Development and analysis of adaptive PID controller using LMS algorithm for distribution generation-inverter. Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT), September 15-17, 2021, Tamil Nadu, India, pp: 1-7.
  • Mahmoodabadi MJ, Soleimani T, Sahnehsaraei MA. 2018. A hybrid optimal controller based on the robust decoupled sliding mode and adaptive feedback linearization. J Info Tech Control, 47(2): 295-309.
  • Moayedi H, Bui DT, Gör M, Pradhan B, Jaafari A. 2019. The feasibility of three prediction techniques of the artificial neural network, adaptive neuro-fuzzy inference system, and hybrid particle swarm optimization for assessing the safety factor of cohesive slopes. ISPRS Int J Geo-Inf, 8(9): 391.
  • Orozco-Tupacyupanqui W, Nakano-Miyatake M, Perez-Meana H. 2016. A new step-size searching algorithm based on fuzzy logic and neural networks for LMS adaptive beamforming systems. Turk J Electr Eng Comput Sci, 24(5): 4322-4338.
  • Öztekin E, Ozgan K. 2012. Analysis of thick plates on elastic foundation by back-propagation artificial neural network using one parameter foundation model. Int J Eng Appl Sci, 4(1): 67-76.
  • Pandey D, Pandey BK, Wairya S. 2021. Hybrid deep neural network with adaptive galactic swarm optimization for text extraction from scene images. Soft Comput, 25: 1563-1580.
  • Patel VV. 2020. Ziegler-Nichols tuning method. Resonance, 25: 1385-1397.
  • Qiao J, Han G, Han H, Yang C, Li W. 2017. A hybrid intelligent optimal control system design for wastewater treatment process. J Info Tech Control, 46(3): 382-394.
  • Spelta MJM, Martins WA. 2020. Normalized LMS algorithm and data-selective strategies for adaptive graph signal estimation. Signal Proces, 167: 107326.
  • Tamer A, Zellouma L, Benchouia MT, Krama A. 2021. Adaptive linear neuron control of three-phase shunt active power filter with anti-windup PI controller optimized by particle swarm optimization. Comput Elect Eng, 96: 107471.
  • Verma B, Padhy PK. 2020. Robust fine tuning of optimal PID controller with guaranteed robustness. IEEE Transact Indust Electr, 67(6): 4911-4920.
  • Zayyani H, Javaheri A. 2021. A robust generalized proportionate diffusion LMS algorithm for distributed estimation. IEEE Transact Circuits Syst II, 68(4): 1552-1556.

A Hybrid Algorithm for Adaptive Neuro-controllers

Year 2023, , 87 - 97, 01.04.2023
https://doi.org/10.34248/bsengineering.1238543

Abstract

In this study, a novel hybrid algorithm consisting of the least mean square and backpropagation neural network is proposed to auto-adjust adaptive proportional integral derivative (PID) controller gains for improving the transient response of linear systems. The hybrid approach comprises the scheme of the two algorithms running in parallel and updates PID gains simultaneously. All algorithms are implemented on the same linear system and present a general framework for different scenarios such as initial PID gains, learning rates, and target functions. The results show that the presented hybrid algorithm has better accuracy, precision, F1-score, adaptability, and robustness than origin algorithms, and significantly improves the controllability in most of the system scenarios. It also exhibits better performance in periodic incremental and decremental targets compared to origin algorithms. Different hybridization levels are also simulated and are highlighted as significant features of their performance. This work can be expanded to the combination of other well-known algorithms, paving the way to significant improvements in control system applications.

References

  • Adar NG. 2021. Real time control application of the robotic arm using neural network based inverse kinematics solution. Sakarya Univ J Sci, 25(3): 849-857.
  • Akhyar S, Omatu S. 1993. Self-tuning PID control by neural networks. IJCNN '93-Nagoya: Proceedings of 1993 International Joint Conference on Neural Networks, October 25-29, 1993, New York, US, pp: 2749-2752.
  • Alkrwy A, Hussein AA, Atyia TH, Khamees M. 2021. Adaptive tuning of PID controller using crow search algorithm for DC motor. Mater Sci Eng, 1076: 012001.
  • Ang K. H., Chong G., Li Y. 2005. PID control system analysis, design, and technology, IEEE Trans. Control Syst. Technol., vol. 13, no. 4, pp: 559-576.
  • Antony Dhas MM, Chandrasekara S. 2019. Particle swarm intelligence based univariate parameter tuning of recursive least square algorithm for optimal heart sound signal filtering. Gazi Univ J Sci, 32(3): 928-943.
  • Bai C, Zhang Z. 2018. A least mean square based active disturbance rejection control for an inertially stabilized platform. Optik, 174: 609-622.
  • Bolton W. 2015. Instrumentation and Control Systems. Newness-Elsevier, New York, US, pp: 99-121.
  • Carvalho G, Guedes I, Pinto M, Zachi A, Almeida L, Andrade F, Melo AG. 2021. Hybrid PID-Fuzzy controller for autonomous UAV stabilization. 14th IEEE International Conference on Industry Applications, August 15-18, 2021, São Paulo, Brazil, pp: 1296-1302.
  • Chen C, Gu GX. 2020. Generative deep neural networks for inverse materials design using backpropagation and active learning. Adv Sci, 7(5): 1-10.
  • Conker C, Baltacioglu MK. 2020. Fuzzy self-adaptive PID control technique for driving HHO dry cell systems. Int J Hydrogen Ener, 45(49): 26059-26069.
  • Dogo EM, Afolabi OJ, Nwulu NI, Twala B, Aigbavboa CO. 2018. A comparative analysis of gradient descent-based optimization algorithms on convolutional neural networks. International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS), December 21-22, 2018, Belagavi, India, pp: 92-99.
  • El-Nagar AM, Zaki AM, Soliman FAS, El-Bardini M. 2022. Hybrid deep learning controller for nonlinear systems based on adaptive learning rates. Int J Control, DOI: 10.1080/00207179.2022.2067080.
  • Guo B, Liu H, Luo Z, Wang F. 2009. Adaptive PID controller based on BP neural network. First IITA International Joint Conference on Artificial Intelligence, April 25-26, 2009, Hainan Island, China, pp: 148.
  • Haykin S, Widrow B. 2003. Least-mean-square adaptive filters. John Wiley & Sons, New York, US, pp: 175-241.
  • Haykin S. 2005. Adaptive filter theory. Pearson Education, Lahor, India, pp: 365-438.
  • Hernández-Alvarado R, García-Valdovinos LG, Salgado-Jiménez T, Gómez-Espinosa A, Fonseca-Navarro F. 2016. Neural network-based self-tuning PID control for underwater vehicles. Sensors, 16: 1429.
  • Hou Z, Xiong S. 2019. On model-free adaptive control and its stability analysis. IEEE Transact Auto Control, 64(11): 4555-4569.
  • Jaleel JA, Thanvy N. 2013. A comparative study between PI, PD, PID and lead-lag controllers for power system stabilizer. International Conference on Circuits, Power and Computing Technologies, March 20-21i 2013, New York, US, pp: 456-460.
  • Karchi N, Kulkarni DB. 2021. Development and analysis of adaptive PID controller using LMS algorithm for distribution generation-inverter. Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT), September 15-17, 2021, Tamil Nadu, India, pp: 1-7.
  • Mahmoodabadi MJ, Soleimani T, Sahnehsaraei MA. 2018. A hybrid optimal controller based on the robust decoupled sliding mode and adaptive feedback linearization. J Info Tech Control, 47(2): 295-309.
  • Moayedi H, Bui DT, Gör M, Pradhan B, Jaafari A. 2019. The feasibility of three prediction techniques of the artificial neural network, adaptive neuro-fuzzy inference system, and hybrid particle swarm optimization for assessing the safety factor of cohesive slopes. ISPRS Int J Geo-Inf, 8(9): 391.
  • Orozco-Tupacyupanqui W, Nakano-Miyatake M, Perez-Meana H. 2016. A new step-size searching algorithm based on fuzzy logic and neural networks for LMS adaptive beamforming systems. Turk J Electr Eng Comput Sci, 24(5): 4322-4338.
  • Öztekin E, Ozgan K. 2012. Analysis of thick plates on elastic foundation by back-propagation artificial neural network using one parameter foundation model. Int J Eng Appl Sci, 4(1): 67-76.
  • Pandey D, Pandey BK, Wairya S. 2021. Hybrid deep neural network with adaptive galactic swarm optimization for text extraction from scene images. Soft Comput, 25: 1563-1580.
  • Patel VV. 2020. Ziegler-Nichols tuning method. Resonance, 25: 1385-1397.
  • Qiao J, Han G, Han H, Yang C, Li W. 2017. A hybrid intelligent optimal control system design for wastewater treatment process. J Info Tech Control, 46(3): 382-394.
  • Spelta MJM, Martins WA. 2020. Normalized LMS algorithm and data-selective strategies for adaptive graph signal estimation. Signal Proces, 167: 107326.
  • Tamer A, Zellouma L, Benchouia MT, Krama A. 2021. Adaptive linear neuron control of three-phase shunt active power filter with anti-windup PI controller optimized by particle swarm optimization. Comput Elect Eng, 96: 107471.
  • Verma B, Padhy PK. 2020. Robust fine tuning of optimal PID controller with guaranteed robustness. IEEE Transact Indust Electr, 67(6): 4911-4920.
  • Zayyani H, Javaheri A. 2021. A robust generalized proportionate diffusion LMS algorithm for distributed estimation. IEEE Transact Circuits Syst II, 68(4): 1552-1556.
There are 30 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Research Articles
Authors

Mustafa Demirtaş 0000-0001-6832-4341

Publication Date April 1, 2023
Submission Date January 18, 2023
Acceptance Date March 11, 2023
Published in Issue Year 2023

Cite

APA Demirtaş, M. (2023). A Hybrid Algorithm for Adaptive Neuro-controllers. Black Sea Journal of Engineering and Science, 6(2), 87-97. https://doi.org/10.34248/bsengineering.1238543
AMA Demirtaş M. A Hybrid Algorithm for Adaptive Neuro-controllers. BSJ Eng. Sci. April 2023;6(2):87-97. doi:10.34248/bsengineering.1238543
Chicago Demirtaş, Mustafa. “A Hybrid Algorithm for Adaptive Neuro-Controllers”. Black Sea Journal of Engineering and Science 6, no. 2 (April 2023): 87-97. https://doi.org/10.34248/bsengineering.1238543.
EndNote Demirtaş M (April 1, 2023) A Hybrid Algorithm for Adaptive Neuro-controllers. Black Sea Journal of Engineering and Science 6 2 87–97.
IEEE M. Demirtaş, “A Hybrid Algorithm for Adaptive Neuro-controllers”, BSJ Eng. Sci., vol. 6, no. 2, pp. 87–97, 2023, doi: 10.34248/bsengineering.1238543.
ISNAD Demirtaş, Mustafa. “A Hybrid Algorithm for Adaptive Neuro-Controllers”. Black Sea Journal of Engineering and Science 6/2 (April 2023), 87-97. https://doi.org/10.34248/bsengineering.1238543.
JAMA Demirtaş M. A Hybrid Algorithm for Adaptive Neuro-controllers. BSJ Eng. Sci. 2023;6:87–97.
MLA Demirtaş, Mustafa. “A Hybrid Algorithm for Adaptive Neuro-Controllers”. Black Sea Journal of Engineering and Science, vol. 6, no. 2, 2023, pp. 87-97, doi:10.34248/bsengineering.1238543.
Vancouver Demirtaş M. A Hybrid Algorithm for Adaptive Neuro-controllers. BSJ Eng. Sci. 2023;6(2):87-9.

                                                24890