Industry 4.0
Vol. 9 (2024), Issue 3, pg(s) 86-89

TECHNOLOGICAL BASIS OF “INDUSTRY 4.0”

Simulation experiment for the follow-up controller of the MIMO system

  • 1 AGH University of Krakow, Poland

Abstract

Controlling Multi-Input Multi-Output (MIMO) systems, such as portal conveyors, poses significant challenges due to their inherent complexity and variability. Traditional control methods often fall short in handling the dynamic and nonlinear nature of these systems. This paper presents a novel reinforcement learning (RL) approach, leveraging the twin-delayed deep deterministic policy gradient (TD3) algorithm, to develop a follow-up controller that is robust to changes in system parameters. Our simulation experiments demonstrate the effectiveness of this method.

Keywords

References

  1. Derigent, William, Olivier Cardin, and Damien Trentesaux. "Industry 4.0: contributions of holonic manufacturing control architectures and future challenges." Journal of Intelligent Manufacturing 32.7 (2021): 1797-1818.
  2. Fulton, Nathan, and André Platzer. "Verifiably safe off-model reinforcement learning." International Conference on Tools and Algorithms for the Construction and Analysis of Systems. Cham: Springer International Publishing, 2019.
  3. Bałazy, Patryk, Paweł Gut, and Paweł Knap. "Positioning algorithm for AGV autonomous driving platform based on artificial neural networks." Robotic Systems and Applications 1.2 (2021): 41-45.
  4. Zhu, Meixin, Xuesong Wang, and Yinhai Wang. "Human-like autonomous car-following model with deep RL." Transportation research part C: emerging technologies 97 (2018): 348-368.
  5. Darwish, Ahmed, Momen Khalil, and Karim Badawi. "Optimising public bus transit networks using deep RL." 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2020.
  6. Lalik, K., Kozek, M., Dominik, I., Łukasiewicz, P. (2020). Adaptive MRAC Controller in the Effector Trajectory Generator for Industry 4.0 Machines. In: Bartoszewicz, A., Kabziński, J., Kacprzyk, J. (eds) Advanced, Contemporary Control. Advances in Intelligent Systems and Computing, vol 1196. Springer, Cham.
  7. Lalik, K.; Kozek, M.; Dominik, I. Autonomous Machine Learning Algorithm for Stress Monitoring in Concrete Using Elastoacoustical Effect. Materials 2021, 14, 4116. https://doi.org/10.3390/ma14154116
  8. Zhang, Zidong, Dongxia Zhang, and Robert C. Qiu. "Deep RL for power system applications: An overview." CSEE Journal of Power and Energy Systems 6.1 (2019): 213-225.

Article full text

Download PDF