Abstract
A two-loop cascade control system of a DC drive is considered in this research. The task is to keep transients quality in both speed and armature current loops. It is solved by a usage of P- and PI-controller parameters neural tuner, which operates in real time and does not require a plant model. The tuner is trained online during its functioning in order to follow the plant parameters change, but usage of too high values of a learning rate may result in instability of the control system. So, the upper bound of the learning rate value calculation method is proposed. It is based on Lyapunov’s second method application to estimate the system sustainability. It is applied to implement adaptive control of a mathematical model of a two-high rolling mill. Obtained results show that the proposed method is reliable. The tuner allowed to reduce the plant energy consumption by 1–2% comparing to conventional P-controller.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Astrom, K.J., Wittenmark, B.: Adaptive Control, 2nd edn. Dover, New York (2008)
Leonhard, W.: Control of Electrical Drives. Springer, Berlin (2001)
Son, Y.I., et al.: Robust cascade control of electric motor drives using dual reduced-order PI observer. IEEE Trans. Ind. Electron. 6(62), 3672–3682 (2015)
Rotach, V.Y., Kuzishchin, V.F., Petrov, S.V.: Tuning of industrial controllers from the transient responses of control systems without approximating them by analytical expressions. Therm. Eng. 10(57), 872–879 (2010). doi:10.1134/S0040601510100083
Liu, Y., et al.: Model reference adaptive control-based speed control of brushless DC motors with low-resolution Hall-effect sensors. IEEE Trans. Power Electron. 3(29), 1514–1522 (2014). doi:10.1109/TPEL.2013.2262391
Glushchenko, A.I.: Neural tuner development method to adjust PI-controller parameters on-line. 2017 IEEE Conf. Russ. Young Res. Electr. Electron. Eng. (2017). doi:10.1109/EIConRus.2017.7910689
Eremenko, Y., Glushchenko, A., Petrov, V.: On PI-controller parameters adjustment for rolling mill drive current loop using neural tuner. Procedia Comput Sci 103, 355–362 (2017). doi:10.1016/j.procs.2017.01.121
Tang, J., Deng, C., Huang, G.B.: Extreme learning machine for multilayer perceptron. IEEE Trans. Neural Netw. Learn. Syst. 4(27), 809–821 (2016)
Demuth, H.B., et al.: Neural Network Design. Martin Hagan, USA (2014)
Eremenko, Y.I., Glushchenko, A.I., Fomin, A.V.: On development of method to calculate time delay values of neural network input signals to implement PI-controller parameters neural tuner. International Conference on Industrial Engineering. Applications and Manufacturing (ICIEAM), pp. 1–6. IEEE, Chelyabinsk (2016)
Changa, W.-D., Hwangb, R.-C., Hsieha, J.-G.: A self-tuning PID control for a class of nonlinear systems based on the Lyapunov approach. J. Process Control 12, 233–242 (2002). doi:10.1016/S0959-1524(01)00041-5
Rossomando, F.G., Soria, C.M.: Design and implementation of adaptive neural PID for non linear dynamics in mobile robots. IEEE Lat. Am. Trans. 4, 913–918 (2015)
Acknowledgments
This work was supported by the Russian Foundation for Basic Research. Grant No 15-07-06092.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Glushchenko, A.I. (2018). Method of Calculation of Upper Bound of Learning Rate for Neural Tuner to Control DC Drive. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research. NEUROINFORMATICS 2017. Studies in Computational Intelligence, vol 736. Springer, Cham. https://doi.org/10.1007/978-3-319-66604-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-66604-4_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66603-7
Online ISBN: 978-3-319-66604-4
eBook Packages: EngineeringEngineering (R0)