Abstract
The triple inverted pendulum is a nonlinear, dynamic and unsteady system. The traditional control methods of triple inverted pendulum have problems of limited control accuracy, slow responding. This kind of pendulum system is difficult to control due to the inherent instability, nonlinear behavior and difficultly in establishing a precise mathematical model. In addition, the back-propagation (BP) algorithm has the shortage of easy trapped in local minimum. The triple inverted pendulum control based on GA–PIDNN is proposed. The PID neural network (PIDNN) is a new kind of feedforward multi-layer network. Besides multi-layer forward networks traditional merit, such as approach the ability proceed together the calculation nonlinear transformation, its middle layer has the proportional (P) integral, (I) derivative, (D) dynamic characteristic. Genetic algorithm (GA) has good parallel design structure and characteristics of global optimization. The nonlinear identification model is established, and controller is designed via GA–PIDNN based on the combination of the merits GA and PIDNN in the research of triple inverted pendulum. In simulation, through the comparative study of GA–PIDNN and PIDNN optimized by BP (BP–PIDNN), simulations results show that GA is more accurate and effective.
Similar content being viewed by others
References
Da, W.G., Petko, H.P., Mihail, M.K.: A triple inverted pendulum control system design. In: Advanced Textbooks in Control and Signal Processing, pp. 291–325 (2013)
Pavel, P., Michal, H., Ondrej, T.: Computational analysis of dynamic behaviour of inverted pendulum attached using fibres. Differ. Equ. Dyn. Syst. 21(2), 71–81 (2013)
Chen, Y.F., Huang, A.C.: Adaptive control of rotary inverted pendulum system with time-varying uncertainties. Nonlinear Dyn. 76, 95–102 (2014)
Yang, R., Peng, Y.H., Song, Y.L.: Stability and Hopf bifurcation in an inverted pendulum with delayed feedback control. Nonlinear Dyn. 73, 737–749 (2013)
Zhang, Y.L., Wang, J.Y., Li, H.X.: Stabilization of the quadruple inverted pendulum by variable universe adaptive fuzzy controller based on variable gain H\(_{\infty }\) regulator. J. Syst. Sci. Complex. 25(5), 856–872 (2012)
Zhang, X.L., Tian, L.Y., Zhang, S.Y.: Control of triple inverted pendulum by using fuzzy neural network combined with feedforward based on T-S model. Fuzzy Syst. Math. 25(4), 129–135 (2011)
Huang, X.P., Zhang, Y., Zheng, J.L.: Research of triple inverted pendulum based on neural network of genetic algorithm. In: Advances in Swarm Intelligence Lecture Notes in Computer Science, vol. 7331, pp. 437–443 (2012)
Shu, H.L.: Identify of multivariable nonlinear dynamic systems based on PID neural networks. Comput. Eng. Appl. 12, 47–49 (2006)
Li, A.H., Yin, H.Y., Zhou, W.H.: Study on the Mamdani fuzzy classifier based on the genetic algorithm. J. Yunnan Univ. Natl. (Natural Sciences Edition) 19(3), 228–231 (2010)
Shu, H.L.: On the ability the PID neural networks in nonlinear system identification. Guangdong Autom. Inf. Eng. 4, 1–4 (2001)
Shu, H.L.: PID Neural Network and Control System. National Defense Industry Press, pp. 10–25 (2006)
Shu, H.L., Di, Y.G.: PID neural networks for time-delay systems. Comput. Chem. Eng. 24, 859–862 (2000)
Tseng, H.Y.: A genetic algorithm for assessing flatness in automated manufacturing systems. J. Intell. Manuf. 17, 301–306 (2006)
Zhou, C.J., Xiang, C.J., Chen, H., Fang, H.J.: Genetic algorithm-based dynamic reconfiguration for networked control system. Neural Comput. Appl. 17, 153–160 (2008)
Gao, J.W., Cai, G.Q., Ji, Z.J., Qin, Y., Jia, L.M.: Adaptive neural-fuzzy control of triple inverted pendulum. Control Theory Appl. 27(2), 278–282 (2010)
Yao, L.H., Yin, X.P., Zhang, C.Y.: Fuzzy neural network control of a triple inverted-pendulum based on weighted variables. Control Theory Appl. 27(11), 7–10 (2008)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, XL., Fan, HM., Zang, JY. et al. Nonlinear control of triple inverted pendulum based on GA–PIDNN. Nonlinear Dyn 79, 1185–1194 (2015). https://doi.org/10.1007/s11071-014-1735-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-014-1735-0