Abstract
In this work, we use a neural network as a substitute for the traditional analytic functions employed as an inversion set in feedback linearization control algorithms applied to hydraulic actuators. Although very effective and with strong stability guarantees, feedback linearization control depends on parameters that are difficult to determine, requiring large amounts of experimental effort to be identified accurately. On the other hands, neural networks require little effort regarding parameter identification, but pose significant hindrances to the development of solid stability analyses and/or to the processing capabilities of the control hardware. Here, we combine these techniques to control the positioning of a hydraulic actuator, without requiring extensive identification procedures nor losing stability guarantees for the closed-loop system, at reasonable computing demands. The effectiveness of the proposed method is verified both theoretically and by means of experimental results.
Similar content being viewed by others
References
Watton J (2009) Fundamentals of fluid power control. Cambridge University Press, Cambridge
Guo Q, Zhang Y, Celler BG, Su SW (2016) Backstepping control of electro-hydraulic system based on extended-state-observer with plant dynamics largely unknown. IEEE Trans Ind Electron 63:6909–6920. https://doi.org/10.1109/TIE.2016.2585080
Yang X, Zheng X, Chen Y (2018) Position tracking control law for an electro-hydraulic servo system based on backstepping and extended differentiator. IEEE/ASME Trans Mechatronics 23:132–140. https://doi.org/10.1109/TMECH.2017.2746142
Sun C, Fang J, Wei J, Hu BO (2018) Nonlinear Motion Control of a Hydraulic Press Based on an Extended Disturbance Observer. IEEE Access 6:18502–18510. https://doi.org/10.1109/ACCESS.2018.2813317
Yao J, Deng W, Jiao Z (2017) RISE-based adaptive control of hydraulic systems with asymptotic tracking. IEEE Trans Autom Sci Eng 14:1524–1531. https://doi.org/10.1109/TASE.2015.2434393
Yao J, Deng W (2017) Active disturbance rejection adaptive control of hydraulic servo systems. IEEE Trans Ind Electron 64:8023–8032. https://doi.org/10.1109/TIE.2017.2694382
Angue Mintsa H, Venugopal R, Kenné JP, Belleau C (2012) Feedback linearization-based position control of an electrohydraulic servo system with supply pressure uncertainty. IEEE Trans Control Syst Technol 20:1092–1099. https://doi.org/10.1109/TCST.2011.2158101
Fales R, Kelkar A (2009) Robust control design for a wheel loader using H∞ and feedback linearization based methods. ISA Trans 48:312–320. https://doi.org/10.1016/j.isatra.2009.01.007
Seoa J, Venugopal R, Kennéa JP (2007) Feedback linearization based control of a rotational hydraulic drive. IFAC Proc 7:940–945. https://doi.org/10.1016/j.conengprac.2007.02.009
Xinliang L, Wang X (2013) Adaptive sliding mode position control of electro-hydraulic servo system with single-rod actuators. IEEE Int Symp Robot Sensors Environ 2013:220–225. https://doi.org/10.1109/ROSE.2013.6698446
Ghazali R, Ngadengon R, Sam YM et al (2011) Chaotic trajectory tracking of an electro-hydraulic actuator system using discrete sliding mode control. IEEE Int Conf Control Syst Comput Eng 2011:500–506. https://doi.org/10.1109/ICCSCE.2011.6190577
Zhu L, Wang Z, Liu Y, Song W (2016) Sliding-mode dynamic surface control for MDF continuous hot pressing hydraulic system. Chin Control Decis Conf 2016:2509–2514. https://doi.org/10.1109/CCDC.2016.7531407
Coelho LDS, Cunha MAB (2011) Adaptive cascade control of a hydraulic actuator with an adaptive dead-zone compensation and optimization based on evolutionary algorithms. Expert Syst Appl 38:12262–12269. https://doi.org/10.1016/j.eswa.2011.04.004
Ji Y, Huang GH, Sun W (2015) Risk assessment of hydropower stations through an integrated fuzzy entropy-weight multiple criteria decision making method: a case study of the Xiangxi River. Expert Syst Appl 42:5380–5389. https://doi.org/10.1016/j.eswa.2014.12.026
Na J, Li Y, Huang Y et al (2020) Output feedback control of uncertain hydraulic servo systems. IEEE Trans Ind Electron 67:490–500. https://doi.org/10.1109/TIE.2019.2897545
Borges FAP, Perondi EA, Cunha MAB, Sobczyk MR (2016) A hybrid feedback linearization + neural network control algorithm applied to a hydraulic actuator. In: 9th FPNI Ph.D. Symposium on Fluid Power, FPNI 2016. ASME, Florianópolis, SC, Brazil, p V001T01A037
Pedro J, Ekoru J (2013) NARMA-L2 control of a nonlinear half-car servo-hydraulic vehicle suspension system. Acta Polytech Hungarica 10:5–26
Borges FAP (2017) Controle em cascata de um atuador hidráulico utilizando redes neurais. Universidade Federal do Rio Grande do Sul
Yao Z, Yao J, Yao F et al (2020) Model reference adaptive tracking control for hydraulic servo systems with nonlinear neural-networks. ISA Trans 100:396–404. https://doi.org/10.1016/j.isatra.2019.11.027
Yang Y, Balakrishnan SN, Tang L, Landers RG (2013) Electro-hydraulic piston control using neural MRAC based on a modified state observer. IEEE/ASME Trans Mechatron 18:867–877. https://doi.org/10.1109/TMECH.2012.2193592
Zhu L, Wang Z, Zhou Y (2018) Adaptive neural network saturated control for MDF continuous hot pressing hydraulic system with uncertainties. IEEE Access 6:2266–2273. https://doi.org/10.1109/ACCESS.2017.2782727
Lin YC, Chen D, Chen M et al (2018) A precise BP neural network-based online model predictive control strategy for die forging hydraulic press machine. Neural Comput Appl 29:585–596. https://doi.org/10.1007/s00521-016-2556-5
Yao Z, Yao J, Sun W (2019) Adaptive RISE control of hydraulic systems with multilayer neural-networks. IEEE Trans Ind Electron 66:8638–8647. https://doi.org/10.1109/TIE.2018.2886773
Lewis FL, Yeşildirek A, Liu K (1996) Multilayer neural-net robot controller with guaranteed tracking performance. IEEE Trans Neural Networks 7:388–399. https://doi.org/10.1109/72.485674
Moreno-Valenzuela J, Aguilar-Avelar C (2018) Adaptive neural network control of the Furuta pendulum. Intell Syst Control Autom Sci Eng 88:93–118. https://doi.org/10.1007/978-3-319-58319-8_6
Moreno-Valenzuela J, Montoya-Cháirez J, Santibáñez V (2020) Robust trajectory tracking control of an underactuated control moment gyroscope via neural network–based feedback linearization. Neurocomputing 403:314–324. https://doi.org/10.1016/j.neucom.2020.04.019
Simon Haykin (1999) Neural networks: a comprehensive foundation, 2nd ed. Pearson
Prabel R, Aschemann H (2014) Nonlinear adaptive backstepping control of two coupled hydraulic servo cylinders. In: 2014 American Control Conference. IEEE, pp 1310–1315
Narendra KS, Parthasarathy K (1990) Identification and control of dynamical systems using neural networks. IEEE Trans neural networks 1:4–27. https://doi.org/10.1109/72.80202
Slotine J-JE, Li W (1991) Applied nonlinear control. Prentice Hall, New Jersey
Khalil HK (2014) Nonlinear Systems, 3rd ed. Pearson
Cunha MAB, Guenther R, De Pieri ER, De Negri VJ (2002) Design of cascade controllers for a hydraulic actuator. Int J Fluid Power 3:35–46. https://doi.org/10.1080/14399776.2002.10781136
Slotine JJE, Weiping L (1988) Adaptive manipulator control: a case study. IEEE Trans Automat Contr 33:995–1003. https://doi.org/10.1109/9.14411
Valdiero AC (2005) Control of hydraulic robots with friction compensation. Universidade Federal de Santa Catarina
Wang J, Guofang Gong, Huayong Yang (2008) Control of bulk modulus of oil in hydraulic systems. In: 2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. IEEE, pp 1390–1395
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4:251–257. https://doi.org/10.1016/0893-6080(91)90009-T
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals, Syst 2:303–314. https://doi.org/10.1007/BF02551274
Chi-Chung Cheung, Ng S-C, Lui AK (2012) Improving the Quickprop algorithm. In: The 2012 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–6
Author information
Authors and Affiliations
Corresponding author
Additional information
Technical Editor: Victor Juliano De Negri.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
-
(1)
Normalization Equations.
Input normalization function: Table 9
$$N(x) = \frac{0,9 - 0,1}{{X_{\max } - X_{\min } }}\left( {x - X_{\min } } \right) + 0,1$$(33)Output normalization function:
$$D(y) = \frac{y - 0,1}{{0,9 - 0,1}}\left( {X_{\max } - X_{\min } } \right) + X_{\min }$$(34) -
(2)
Weights for neural network when Tables 10, 11, 12, 13
\(\dot{y}\ge 0.\)
- (3)
Rights and permissions
About this article
Cite this article
Borges, F.A.P., Perondi, E.A., Cunha, M.A.B. et al. A neural network-based inversion method of a feedback linearization controller applied to a hydraulic actuator. J Braz. Soc. Mech. Sci. Eng. 43, 248 (2021). https://doi.org/10.1007/s40430-021-02957-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-021-02957-y