Fuzzy Logic and Neural Network-Based Self-Tuning PID for Vacuum Pressure Stabilization
DOI:
https://doi.org/10.30871/jaic.v9i5.10945Keywords:
Adaptive control, Fuzzy logic, Neural Networks, Self-tuning PID,, Vacuum systemAbstract
The conventional PID controller is widely used for vacuum pressure control; however, it has limitations when faced with nonlinear system characteristics and external disturbances, leading to a decline in performance. Several previous studies have proposed the integration of PID with intelligent methods, such as neural networks or fuzzy logic separately. Nevertheless, these singular approaches still encounter limitations in terms of adaptability and robustness. This study aims to develop a self-tuning PID method based on the combination of Neural Networks (NN) and Fuzzy Inference Systems (FIS) to enhance the stability and accuracy of vacuum pressure control. A nonlinear vacuum system plant model is constructed within the Simulink environment to generate a dataset used for training the NN with the Levenberg-Marquardt algorithm. The NN is employed to predict changes in PID parameters adaptively, while the FIS provides fine corrections to strengthen system stability. Simulation results demonstrate that the proposed approach effectively reduces overshoot from 36.47% to 31.51%, decreases steady-state error from 0.069 to 0.052, and lowers the RMSE value from 0.125 to 0.108 compared to conventional PID. Thus, the integration of NN and FIS within the self-tuning mechanism proves to be more effective in addressing nonlinear dynamics and external disturbances, resulting in a more stable and accurate system response.
Downloads
References
[1] N. K. Quang, V. Q. B. Ngo, N. K. Anh, H. Than, T. T. Dong, and N. D. Tho, “Neural Network PID Controller for PMSM Drives,” 2022 7th Int. Sci. Conf. Appl. New Technol. Green Build. ATiGB 2022, no. November, pp. 146–149, 2022, doi: 10.1109/ATiGB56486.2022.9984109.
[2] M. Davanipour, R. Dadkhah Tehrani, and F. Shabani-Nia, “Self-tuning PID control of liquid level system based on Fuzzy Wavelet Neural Network model,” 2016 24th Iran. Conf. Electr. Eng. ICEE 2016, pp. 511–516, 2016, doi: 10.1109/IranianCEE.2016.7585575.
[3] B. Y. Xing, L. Y. Yu, and Z. K. Zhou, “Composite single neural PID controller based on fuzzy self-tuning gain and RBF network identification,” 26th Chinese Control Decis. Conf. CCDC 2014, pp. 606–611, 2014, doi: 10.1109/CCDC.2014.6852238.
[4] M. Ma, “Research on Parameter Self-tuning PID Control Algorithm Based on BP Neural Network,” Proc. 2022 Conf. Russ. Young Res. Electr. Electron. Eng. ElConRus 2022, pp. 1215–1220, 2022, doi: 10.1109/ElConRus54750.2022.9755484.
[5] D. K. Bhutto, J. Ansari, and H. Zameer, “Implementation of AI Based Power Stabilizer Using Fuzzy and Multilayer Perceptron in MatLab,” 2020 3rd Int. Conf. Comput. Math. Eng. Technol. Idea to Innov. Build. Knowl. Econ. iCoMET 2020, 2020, doi: 10.1109/iCoMET48670.2020.9073892.
[6] J. H. Chen et al., “Modeling and temperature control of a water-cooled PEMFC system using intelligent algorithms,” Appl. Energy, vol. 372, no. June, 2024, doi: 10.1016/j.apenergy.2024.123790.
[7] Y. Wang, X. Yang, Z. Sun, and Z. Chen, “A systematic review of system modeling and control strategy of proton exchange membrane fuel cell,” Energy Rev., vol. 3, no. 1, p. 100054, 2024, doi: 10.1016/j.enrev.2023.100054.
[8] I. Khan, A. Zakari, J. Zhang, V. Dagar, and S. Singh, “A study of trilemma energy balance, clean energy transitions, and economic expansion in the midst of environmental sustainability: New insights from three trilemma leadership,” Energy, vol. 248, p. 123619, 2022, doi: 10.1016/j.energy.2022.123619.
[9] Z. Zhong, Z. Luo, W. Huang, and H. Wu, “Optimization of Electrical Equipment for Special Transmission Engineering Based on Fuzzy Neural Network,” Procedia Comput. Sci., vol. 247, no. C, pp. 138–145, 2024, doi: 10.1016/j.procs.2024.10.017.
[10] K. Bouhoune, K. Yazid, M. S. Boucherit, and A. Chériti, “Hybrid control of the three phase induction machine using artificial neural networks and fuzzy logic,” Appl. Soft Comput. J., vol. 55, pp. 289–301, 2017, doi: 10.1016/j.asoc.2017.01.048.
[11] A. A. Prokhorov, Y. V. Mitrishkin, P. S. Korenev, and M. I. Patrov, “The plasma shape control system in the tokamak with the artificial neural network as a plasma equilibrium reconstruction algorithm,” IFAC-PapersOnLine, vol. 53, no. 2, pp. 857–862, 2020, doi: 10.1016/j.ifacol.2020.12.843.
[12] H. Wei, N. Zhu, Z. Sun, S. Tan, and R. Tian, “Research on the intelligent control strategy of pressurizer pressure in PWRs based on a fuzzy neural network PID controller,” Nucl. Eng. Des., vol. 433, no. February, p. 113875, 2025, doi: 10.1016/j.nucengdes.2025.113875.
[13] X. Sun, Z. Chen, Y. Zhou, P. Yu, and H. Sang, “Neural network based self-tuning IPID for wave glider heading tracking control,” Ocean Eng., vol. 307, no. January, p. 118152, 2024, doi: 10.1016/j.oceaneng.2024.118152.
[14] S. M. Alardhi et al., “Artificial neural network and response surface methodology for modeling reverse osmosis process in wastewater treatment,” J. Ind. Eng. Chem., vol. 133, no. January, pp. 599–613, 2024, doi: 10.1016/j.jiec.2024.02.039.
[15] Q. Liu and X. Jiang, “Dynamic multi-objective optimization control for wastewater treatment process based on modal decomposition and hybrid neural network,” J. Water Process Eng., vol. 61, no. December 2023, p. 105274, 2024, doi: 10.1016/j.jwpe.2024.105274.
[16] Q. Liang, C. Fang, X. Ma, Y. Zhang, X. Xue, and L. Yan, “Experimental study and artificial neural network modeling of a pulsating heat pipe PV/T module using a low-efficiency photovoltaic panel,” Energy, vol. 334, no. July, p. 137788, 2025, doi: 10.1016/j.energy.2025.137788.
[17] R. Şener, M. A. Koç, and K. Ermiş, “Hybrid ANFIS-PSO algorithm for estimation of the characteristics of porous vacuum preloaded air bearings and comparison performance of the intelligent algorithm with the ANN,” Eng. Appl. Artif. Intell., vol. 128, no. April 2022, 2024, doi: 10.1016/j.engappai.2023.107460.
[18] R. Sabetahd and O. Jafarzadeh, “Development of an adaptive chaotic fuzzy neural network controller for mitigating seismic response in a structure equipped with an active tuned mass damper,” Expert Syst. Appl., vol. 267, no. December 2024, p. 126048, 2025, doi: 10.1016/j.eswa.2024.126048.
[19] E. Baghelani, M. Teshnehlab, and J. Roshanian, “A novel combination of fuzzy PID and deep neural controller in feedback-error-learning framework,” Chaos, Solitons and Fractals, vol. 194, no. February, p. 116250, 2025, doi: 10.1016/j.chaos.2025.116250.
[20] Ş. Gülcü, “Training of the feed forward artificial neural networks using dragonfly algorithm[Formula presented],” Appl. Soft Comput., vol. 124, p. 109023, 2022, doi: 10.1016/j.asoc.2022.109023.
[21] O. Rodriguez-Abreo, J. Rodriguez-Resendiz, C. Fuentes-Silva, R. Hernandez-Alvarado, and M. D. C. P. T. Falcon, “Self-Tuning Neural Network PID with Dynamic Response Control,” IEEE Access, vol. 9, pp. 65206–65215, 2021, doi: 10.1109/ACCESS.2021.3075452.
[22] M. P. Belov, D. D. Truong, and P. Van Tuan, “Self-Tuning PID Controller Using a Neural Network for Nonlinear Exoskeleton System,” Proc. 2021 2nd Int. Conf. Neural Networks Neurotechnologies, NeuroNT 2021, pp. 6–9, 2021, doi: 10.1109/NeuroNT53022.2021.9472852.
[23] Y. Zhu, L. Wang, J. Li, and J. Yu, “Single Point Suspension Control of Maglev Train Based on BP Neural Network,” Chinese Control Conf. CCC, vol. 2022-July, pp. 5487–5492, 2022, doi: 10.23919/CCC55666.2022.9901574.
[24] L. Chu and Z. Tian, “Time Delay Compensation Strategy of Networked Control System Based on CS-BP and IGPC,” 2022 2nd Int. Conf. Consum. Electron. Comput. Eng. ICCECE 2022, pp. 374–379, 2022, doi: 10.1109/ICCECE54139.2022.9712660.
[25] D. A. Permatasari and D. A. Maharani, “Backpropagation neural network for tuning PID pan-tilt face tracking,” Proc. - 2018 3rd Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng. ICITISEE 2018, pp. 357–361, 2018, doi: 10.1109/ICITISEE.2018.8720968.
[26] D. Karayel, O. Güngör, and E. Šarauskis, “Estimation of Optimum Vacuum Pressure of Air‐Suction Seed‐Metering Device of Precision Seeders Using Artificial Neural Network Models,” Agronomy, vol. 12, no. 7, 2022, doi: 10.3390/agronomy12071600.
[27] I. Sharifi and A. Alasty, “Self-Tuning PID Control via a Hybrid Actor-Critic-Based Neural Structure for Quadcopter Control,” 2023, [Online]. Available: http://arxiv.org/abs/2307.01312
[28] W. Kong et al., “PID control algorithm based on multistrategy enhanced dung beetle optimizer and back propagation neural network for DC motor control,” Sci. Rep., vol. 14, no. 1, pp. 1–26, 2024, doi: 10.1038/s41598-024-79653-z.
[29] J. C. Almachi, R. Vicente, E. Bone, J. Montenegro, E. Cando, and S. Reina, “Implementation of a Neural Network for Adaptive PID Tuning in a High-Temperature Thermal System,” Energies, vol. 18, no. 12, 2025, doi: 10.3390/en18123113.
[30] S. Slama, A. Errachdi, and M. Benrejeb, “Adaptive pid controller based on neural networks for mimo nonlinear systems,” J. Theor. Appl. Inf. Technol., vol. 97, no. 2, pp. 361–371, 2019.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Berza H. Sanjaya, Ardi Pujiyanta Ardi, Riky Dwi Puriyanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
