Abstract
In this paper, a novel general regression neural network-based data-driven model-free nonlinear predictive functional control approach is proposed for a class of unknown single-input/single-output discrete-time nonlinear systems. The historical measurable data are used to construct an explicit model for control design and estimate system time-varying parameters online, making the approach model free. By using basis functions to structuralize system input, online computational load (OCL) of the controller can be reduced dramatically compared with existing model-free predictive control approaches. Moreover, the prediction function is realized by a general regression neural network-based system parameter predictive algorithm, bringing the controller good robustness and strong capability against sudden changes from prescribed references and external circumstances simultaneously. Simulation results show that, by using much less OCL, the proposed approach-based closed-loop systems can achieve even smaller overshoot and shorter response time than the existing model-free predictive control approaches.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Hou, Z.S., Jin, S.T.: Model Free Adaptive Control: Theory and Applications. Tylor Francis Group, Boca Raton (2013)
Hanul, H., Kiho, J., Jae-Gu, K., Sehoon, O.: Iterative feedback tuning of cascade control of two inertia system. IEEE Control Syst. Lett. 5(3), 785–790 (2021)
Chrystian, L.R., Rodrigo, B.G., Jeferson, V.F., Fausto, B.L., Luciola, C.: Virtual reference feedback tuning applied to DC–DC converters. IEEE Trans. Ind. Electron. 68(1), 544–552 (2021)
Wu, X.Z., Wang, X.M., Qin, W., Li, L.W., Sun, Z.X., Shen, M.Q.: Iterative learning control for nonlinear systems with iteration-varying trial lengths using modified reference trajectories. In: Proceedings of 2021 IEEE 10th Data Driven Control and Learning Systems Conference, 2021 (DDCLS 2021). IEEE, pp. 1161–1165 (2021)
Liu, D.R., Xue, S., Zhao, B., Luo, B., Wei, Q.L.: Adaptive dynamic programming for control: a survey and recent advances. IEEE Trans. Syst. Man Cybern. Syst. 51(1), 142–160 (2021)
Chen, J.: Flexible joint manipulator controlling algorithm based on neural network improved PID. In: Proceedings of 2021 13th International Conference on Measuring Technology and Mechatronics Automation, 2021 (ICMTMA 2021). IEEE, pp. 419–422 (2021)
Marc, F.Q.S., Edwin, S., Argel, A.B., Ryan, R.P.V., Alvin, L.C.: A genetic algorithm approach to PID tuning of a quadcopter UAV. In: Proceedings of 2021 IEEE/SICE International Symposium on System Integration, 2021 (SII 2021). IEEE, pp. 675–678 (2021)
Mokhtar, S., Monier, H.: Tuning of PID controller using different optimization algorithms for industrial DC motor. In: Proceedings of 2021 International Conference on Advance Computing and Innovative Technologies in Engineering, 2021. (ICACITE 2021). IEEE, pp. 756–759 (2021)
Abdullah, M., Takeshi, M,: Extremum seeking control of preload-controllable ultrasonic motor. In: Proceedings of 2021 IEEE International Conference and Exhibition on New Actuator Systems and Applications, 2021. IEEE, pp. 42–45 (2021)
Oleg, G., Victoria, E., Yury, I., Jiang, Y.M.: Simultaneous perturbation stochastic approximation-based consensus for tracking under unknown-but-bounded disturbances. IEEE Trans. Autom. Control 66(8), 3710–3717 (2021)
Yavuz, B.K., Yilmaz, A., Baris, G.: Speed control based PID configuration of a DC motor for an unmanned agricultural vehicle. In: Proceedings of 2021 8th International Conference on Electrical and Electronics Engineering, 2021. IEEE, pp. 117–120 (2021)
Hou, Z.S., Liu, S.D., Tian, T.T.: Lazy-learning-based data-driven model-free adaptive predictive control for a class of discrete-time nonlinear systems. IEEE Trans. Neural Netw. Learn. Syst. 28(8), 1–15 (2017)
Zhao, L.G., He, W.L., Lv, F.K.: Model-free adaptive control for parafoil systems based on the iterative feedback tuning method. IEEE Access 9, 35900–35914 (2021)
Xu, J., Lin, N., Chi, R.H.: Improved high-order model free adaptive control. In: Proceedings of 2021 IEEE 10th Data Driven Control and Learning Systems Conference, 2021. (DDCLS 2021), pp. 704–708
Liu, S.D., Hou, Z.S., Zhang, X., Ji, H.H.: Model-free adaptive control method for a class of unknown MIMO systems with measurement noise and application to quadrotor aircraft. IET Control Theory Appl. 14(15), 2084–2096 (2020)
Hou, Z.S., Jin, S.T.: A novel data-driven control approach for a class of discrete-time nonlinear systems. IEEE Trans. Control Syst. Technol. 19(6), 1549–1558 (2011)
Wu. H.Y., Jin, S.T., Yin, C.K., Zheng, J.M., Hou, Z.S.: Model free adaptive predictive tracking control for robot manipulators with uncertain parameters. In: Proceedings of 2021 IEEE 10th Data Driven Control and Learning Systems Conference, 2021 (DDCLS 2021), pp. 1571–1576. IEEE (2021)
Wang, Y.S., Hou, M.D.: Model-free adaptive integral terminal sliding mode predictive control for a class of discrete-time nonlinear systems. ISA Trans. 93(2019), 209–217 (2019)
Hou, Z.S., Lei, T.: Constrained model free adaptive predictive perimeter control and route guidance for multi-region urban traffic systems. IEEE Trans. Intell. Transp. Syst., 1-13 (2021)
Li, Z.X., Jin, S.T., Xu, C.Y., Li, J.: Model-free adaptive predictive control for an urban road traffic network via perimeter control. IEEE Access 7, 172489–172495 (2019)
Lei, T., Hou, Z.S.: Perimeter control for two-region urban traffic system based on model free adaptive predictive control with constraints. IFAC PapersOnLine 52(6), 25–30 (2019)
Li, D., De Schutter, B.: Distributed model-free adaptive predictive control for urban traffic networks. IEEE Trans. Control Syst. Technol., 1-13 (2021)
Tan, H.R., Wang, Y.N., Wu, M., Huang, Z.W., Miao, Z.Q.: Distributed group coordination of multiagent systems in cloud computing systems using a model-free adaptive predictive control strategy. IEEE Trans. Neural Netw. Learn. Syst., 1–13 (2021)
Zhou, P., Zhang, S., Wen, L., Fu, J., Chai, T.Y., Wang, H.: Kalman filter-based data-driven robust model- free adaptive predictive control of a complicated industrial process. IEEE Trans. Autom. Sci. Eng., 1–16 (2021)
Yu, Z., Bai, J.J., Zou, H.B.: Improved disturbed predictive function control with basic function and PID control structure. IEEE Access 8, 18219–18227 (2020)
Xiang, Y., Liu, Z.L., Wang, L.M.: Genetic-algorithm-optimization-based predictive functional control for chemical industry processes against partial actuator faults. IEEE Access 8, 214586–214595 (2020)
Juliani, V., Adytia, D., Adiwijaya: wave height prediction based on wind information by using general regression neural network, study case in Jakarta Bay. In: Proceedings of 2020 8th International Conference on Information and Communication Technology (ICoICT 2020). IEEE, pp. 1–5 (2020)
Mian, H.R., Hu, G.J., Hewage, K., Rodriguez, M.J., Sadiq, R.: Predicting unregulated disinfection by-products in water distribution networks using generalized regression neural networks. Urb. Water J. 15(7), 1–14 (2021)
Alzo’Ubi, A.K., Ibrahim, F.: Predicting the pile static load test using backpropagation neural network and generalized regression neural network—a comparative study. Int. J. Geotech. Eng. 15(7), 810–821 (2021)
Salehi, M., Farhadi, S., Moieni, A., Safaie, N., Hesami, M.: A hybrid model based on general regression neural network and fruit fly optimization algorithm for forecasting and optimizing paclitaxel biosynthesis in Corylus avellana cell culture. Plant Methods 17, 1–13 (2021)
Niu, D.X., Wang, K.K., Wu, J., Sun, L.J., Liang, Y., Xu, X.M., Yang, X.L.: Can china achieve its 2030 carbon emissions commitment? scenario analysis based on an improved general regression neural network. J. Clean. Prod. 243(2020), 1–14 (2020)
Kabir, Md.R., Faysal, T.I., Hossain, Md.S., Shorno, J.N., Siddique, S.: A satellite collision avoidance system based on General Regression Neural Network. In: Proceedings of 2020IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT 2020). IEEE, pp. 154–160 (2020)
Bu, X.H., Wang, Q.F., Hou, Z.S., Qian, W.: Data driven control for a class of nonlinear systems with output saturation. ISA Trans. 81(2018), 1–7 (2018)
Acknowledgements
This study was funded by National Natural Science Foundation of China (Grant Number 52002181).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A: Proof of Theorem 1
From formula (12), it is easy to obtain that:
where \(i=1,2\). Let’s consider the RHPI (14). Considering the necessary condition \(\frac{\partial {J(k)}}{\partial {\varDelta u(k+n_i-1)}}=0\) and formula (13) yields:
Then bringing formula (11) and the internal predictive model (12) into (27) yields:
Then by considering \(i=1,2\), formula (28) can be written by:
Treat \(\varDelta u(k)\) and \(\mu _2\) as variables, then, the incremental control law \(\varDelta u(k)\) can be derived by solving formula (29):
Thus, Theorem 1 is proved.
Appendix B: Proof of Theorem 2
Denote \(\phi _e(k)={\hat{\phi }}(k)-\phi (k)\). Subtracting \(\phi (k)\) from both sides of the first equation of formula (20) yields:
Considering that function \(f(x)=1-\frac{\eta x}{\mu +x}\) is a decreasing function with respect to \(x \ge 0\) and using the conditions \(\mu \ge 0\) and \(\eta \in (0,1]\) yields:
Recall in Remark 1 that \(|\phi (k)| \le {\bar{b}}\). Thus, by using (33), it has:
Recall that \(|w(k)| \le {\bar{W}}\). Thus, one can derive \(|\varDelta w(k)|=|w(k)-w(k-1)| \le |w(k)|+|w(k-1)| \le 2{\bar{W}}\). Hence, one can infer that \(0 \le |\frac{\eta \varDelta u(k-1)}{\mu +|\varDelta u(k-1)|^2}\varDelta w(k)| \le c\), c is a bounded number. Let \(\delta =1-\frac{\eta \varepsilon ^2}{\mu +\varepsilon ^2}\). Taking absolute value of both sides of formula (31) and considering formulas (32)−(34) yield:
Formula (35) means that \(\phi _e(k)\) is bounded. By recalling the boundedness of the PPD \(\phi (k)\), it can be inferred that \({\hat{\phi }}(k)\) is bounded. Then Theorem 2 is proved.
Appendix C: Proof of Theorem 3
Denote:
Then the incremental input \(\varDelta u(k)\) in formula (21) can be re-written into:
On one hand, bringing formula (4) into (36) and considering formulas (21) and (37) yield:
Thus, it has:
On the other hand, it also has:
Then, by recalling assumptions A1 and A2, it can be inferred that:
Notice that \(M_1>0\). Hence, there exists a positive number \(d_2 \in (0,1)\) such that:
It also has:
Thus, it has:
Hence, taking absolute value of both sides of formula (39) yields:
Therefore, by considering formula (44), it has:
Particularly, \(w(k+1)=0 \Rightarrow {\bar{W}}=0 \Rightarrow \lim \limits _{k \rightarrow \infty }|y^*-y_p(k+1)-w(k+1)|=0\).
To prove the UUB, select following Lyapunov function:
Bringing formula (38) into (47) yields:
The rest task of the proof is to show \(\varDelta V(k+1) \le 0\).
In formula (48), denote \(a=[1-\frac{{\phi }(k)}{{\hat{\phi }}(k)}]^2-1\), \(b=2[1-\frac{{\phi }(k)}{{\hat{\phi }}(k)}][\frac{{\phi }(k)}{{\hat{\phi }}(k)}w(k)-\varDelta w(k+1)]\) and \(c=[\frac{{\phi }(k)}{{\hat{\phi }}(k)}w(k)-\varDelta w(k+1)]^2\). It is clear that \(a<0\) and \(0 \le \sqrt{\varDelta }=\sqrt{b^2-4ac}=2|\frac{{\phi }(k)}{{\hat{\phi }}(k)}w(k)-\varDelta w(k+1)| \le 2(d_1+1) {\bar{W}}\). This means that the function \(a \cdot \varepsilon ^2(k)+b \cdot \varepsilon (k)+c=0\) has solutions \(\varepsilon _1\) and \(\varepsilon _2\) (there might be \(\varepsilon _1=\varepsilon _2\)). Let \(\varepsilon _0=max\{ \varepsilon _1, \varepsilon _2 \}\). Thus, there must exist a STP \(k_0\) such that when \(k \ge k_0\), it has \(\varepsilon (k) \ge \varepsilon _0\), making \(\varDelta V(k+1) \le 0\).
Then UUB of the system is proved.
Rights and permissions
About this article
Cite this article
Wang, Y., Li, S. & Zhang, B. General regression neural network-based data-driven model-free predictive functional control for a class of discrete-time nonlinear systems. Nonlinear Dyn 107, 953–966 (2022). https://doi.org/10.1007/s11071-021-06991-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-021-06991-2