The buffered optimization methods for online transfer function identification employed on DEAP actuator

• Autorzy: Bernat Jakub , Kołota Jakub

Identyfikatory

DOI

10.24425/acs.2023.146960

• Języki publikacji: EN

Abstrakty

EN

Identification plays an important role in relation to control objects and processes as it enables the control system to be properly tuned. The identification methods described in this paper use the Stochastic Gradient Descent algorithms, which have so far been successfully presented in machine learning. The article presents the results of the Adam and AMSGrad algorithms for online estimation of the Dielectric Electroactive Polymer actuator (DEAP) parameters. This work also aims to validate the learning by batch methodology, which allows to obtain faster convergence and more reliable parameter estimation. This approach is innovative in the field of identification of control systems. The research was supplemented with the analysis of the variable amplitude of the input signal. The dynamics of the DEAP parameter convergence depending on the normalization process was presented. Our research has shown how to effectively identify parameters with the use of innovative optimization methods. The results presented graphically confirm that this approach can be successfully applied in the field of control systems.

Słowa kluczowe

EN

Stochastic Gradient Descent; ADAM; AMSGrad; DEAP; system identification

• Wydawca: Polish Academy of Sciences, Committee of Automatic Control and Robotics
• Czasopismo: Archives of Control Sciences
• Rocznik: 2023
• Tom: Vol. 33, No. 3
• Strony: 565--587
• Opis fizyczny: Bibliogr. 30 poz., fot., rys., tab., wzory

Twórcy

autor

Bernat Jakub

• Institute of Automatic Control and Robotics, Poznan University of Technology, Poznań, Poland

• https://orcid.org/0000-0001-8890-7157

autor

Kołota Jakub

• Institute of Automatic Control and Robotics, Poznan University of Technology, Poznań, Poland

• https://orcid.org/0000-0002-2177-1555

Bibliografia

• [1] M. Andrychowicz, F. Wolski, A. Ray, J. Schneider, R. Fong, P. Welinder, B. McGrew, J. Tobin, P. Abbeel and W. Zaremba: Hindsight experience replay. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan and R. Garnett (eds.), Advances in Neural Information Processing Systems, 30 Curran Associates, Inc., 2017.
• [2] Y. Bar-Cohen: Electroactive Polymer (EAP) Actuators as Artificial Muscles: Reality, Potential, and Challenges. SPIE PRESS, Bellingham, Washington USA, 2nd. edition, 2004.
• [3] R. Baumgartner, A. Kogler, J.M. Stadlbauer, Ch.Ch. Foo, R. Kaltseis, M. Baumgartner, G. Mao, Ch. Keplinger, S.J.A. Koh, N. Arnold, Z. Suo, M. Kaltenbrunner and S. Bauer: A lesson from plants: High-speed soft robotic actuators. Advanced Science, 7(5), (2020). DOI: 10.1002/advs.201903391.
• [4] J. Bernat, J. Kołota and S. Rosset: Identification of a nonlinear dielectric elastomer actuator based on the harmonic balance method. IEEE/ASME Transactions on Mechatronics, 26(5), (2021). DOI: 10.1109/TMECH.2020.3044492.
• [5] J. Bernat and J. Kołota: A PI controller with a robust adaptive law for a dielectric electroactive polymer actuator. Electronics, 10(11), (2021). DOI: 10.3390/electronics10111326.
• [6] J. Bernat and J. Kołota: DEAP actuator composed of a soft pneumatic spring bias with pressure signal sensing. Energies, 14(4), (2021). DOI: 10.3390/en14041189.
• [7] F. Carpi, I. Anderson, S. Bauer, G. Frediani, G. Gallone, M. Gei, C. Graaf, C. Jean-Mistral, W. Kaal, G. Kofod, M. Kollosche, R. Kornbluh, B. Lassen, M. Matysek, S. Michel, S. Nowak, B. O’Brien, Q. Pei, R. Pelrine, B. Rechenbach, S. Rosset and H. Shea: Standards for dielectric elastomer transducers. Smart Materials and Structures, 24(10), (2015). DOI: 10.1088/0964-1726/24/10/105025.
• [8] T. Dozat: Incorporating Nesterov momentum into Adam. International Conference on Learning Representations, San Juan, Puerto Rico (2016). https://api.semanticscholar.org/CorpusID:70293087.
• [9] J.C. Duchi, E. Hazan and Y. Singer: Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(61), (2011). https://jmlr.org/papers/volume12/duchi11a/duchi11a.pdf.
• [10] P. Ioannou: Robust Adaptive Control. Dover Publications, Inc., New York, 2003.
• [11] K.J. Kim and S. Tadokoro: Electroactive Polymers for Robotic Applications: Artificial Muscles and Sensors. Springer, London, 2007.
• [12] D.P. Kingma and J. Ba: Adam: A method for stochastic optimization. Computing Research Repository (CoRR), abs/1412.6980, (2015). DOI: 10.48550/arXiv.1412.6980.
• [13] D.P. Kingma and J. Ba: Adam: A method for stochastic optimization. International Conference on Learning Representations, San Diego, CA, USA (2015).
• [14] J. Kołota: The FEM model of the pump made of dielectric electroactive polymer membrane. Applied Sciences, 10(7), (2020). DOI: 10.3390/app10072283.
• [15] T.P. Lillicrap, J.J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver and D. Wierstra: Continuous control with deep reinforcement learning. Computing Research Repository (CoRR), abs/1509.02971, (2015). DOI: 10.48550/arXiv.1509.02971.
• [16] T.P. Lillicrap, J.J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra: Continuous control with deep reinforcement learning. (2016).
• [17] G. Liu and J. Wang: Dendrite net: A white-box module for classification, regression, and system identification. IEEE Transactions on Cybernetics, 52(1), (2022), 13774-13787. DOI: 10.1109/TCYB.2021.3124328.
• [18] H.B. McMahan and M. Streeter: Adaptive bound optimization for on-line convex optimization. Proceedings of the 23rd Annual Conference On Learning Theory, Haifa, Israel, (2010), 244-256.
• [19] V. Mnih, K. Kavukcuoglu, D. Silver, A.A. Rusu, J. Veness, M.G. Bellemare, A. Graves, M. Riedmiller, A.K. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie, A. Sadik, I. Antonoglou, H. King, D. Kumaran, D. Wierstra, S. Legg, and D. Hassabis: Human-level control through deep reinforcement learning. Nature, 518(7540), (2015), 529-533. DOI: 10.1038/nature14236.
• [20] S.J. Reddi, S. Kale and S. Kumar: On the convergence of Adam and beyond. International Conference on Learning Representations, Vancouver, Canada, (2018).
• [21] S.J. Reddi, S. Kale and S. Kumar: On the convergence of Adam and beyond. arXiv, (2019).
• [22] G. Rizzello, D. Naso, A. York and S. Seelecke: Modeling, identification, and control of a dielectric electro-active polymer positioning system. IEEE Transactions on Control Systems Technology, 23(2), (2015), 632-643. DOI: 10.1109/TCST.2014.2338356.
• [23] S. Rosset, O.A. Araromi, S. Schlatter and H.R. Shea: Fabrication process of silicone-based dielectric elastomer actuators. Journal of Visualized Experiments, 108 (2016), 1-13. DOI: 10.3791/53423.
• [24] T. Söderström and P. Stoica: System Identification. Prentice-Hall, Inc., USA, 1988.
• [25] R.S. Sutton and A.G. Barto: Reinforcement Learning: An Introduction. MIT Press, Cambridge, Massachusetts, London England, 2018.
• [26] T. Tieleman and G. Hinton: RMSprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2), (2012), 26-31.
• [27] J-W. Yeh and S-F. Su: Efficient approach for RLS type learning in TSK neural fuzzy systems. IEEE Transactions on Cybernetics, 47(9), (2017), 2343-2352. DOI: 10.1109/TCYB.2016.2638861.
• [28] M.D. Zeiler: ADADELTA: An adaptive learning rate method. Computing Research Repository (CoRR), abs/1212.5701, (2012). DOI: 10.48550/arXiv.1212.5701.
• [29] G. Zhang, X. Chen and T. Chen: Digital redesign via the generalised bilinear transformation. International Journal of Control, 82(4), (2009), 741-754. DOI: 10.1080/00207170802247728.
• [30] S. Zhang and R.S. Sutton: A deeper look at experience replay. arXiv: 1712.01275, (2018). DOI: 10.48550/arXiv.1712.01275.