A synthesis approach of fast robust MPC with RBF-ARX model to nonlinear system with uncertain steady status information

Tian, Xiaoying; Peng, Hui; Feng, Zhou; Peng, Xiaoyan

doi:10.1007/s10489-019-01555-9

Cited by 6 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RBF-ARX model is a typical one in such framework which is based on SD-ARX model and sets the coefficients of model dependent on the output of a RBF network (H. Peng, et al, 2004). The successful applications of this model on a continuously stirred tank reactor system (Zhou, Peng, Zeng, & Tian, 2019), a quad-rotor (Wu, Peng, Chen, & Peng, 2014), an inverted pendulum (Tian, Peng, Zhou, & Peng, 2021), a magnetic levitation (maglev) systems (Qin, Peng, Ruan, Wu, & Gao, 2014) and a tobacco drying system (Zhou, et al, 2018) have proved its superiority in modelling and efficiency in model-based controlling. Hence, combining a state-of-art deep neural network with such SD-ARX model is promising in nonlinear system's modeling to be provided as the basis of controlling.…”

Section: Introductionmentioning

confidence: 99%

T-ARX Model for Nonlinear Discrete System Prediction Based on A Hybrid Modelling Method

Peng

Liu

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

A suited model is meaningful for controlling a plant. A nonlinear model composed of deep neural network impedes the application of the mature controlling methods because of its complex formation, though it may predict precisely. To model a nonlinear and dynamic system with local-linearity and global-nonlinearity, a hybrid model named T-ARX (Transformer Auto-Regression model with eXogenous variables) with good long-term prediction accuracy is proposed in this paper. The T-ARX model is one kind of SD-ARX (State Dependent ARX) model with the coefficients of regression inputs estimated by a deep Transformer network, so that the nonlinear dynamics of plant could be captured. Meanwhile, the model takes state and action sampled from a period of time as its inputs and possesses the pseudo linear structure. When its coefficients are fixed at the sample time, it can be reformed as a discrete state-space model which is quite meaningful for controller design. Because the mask is applied to the input sequence, the model can be trained through parallel schemes, thus the short-term and long-term prediction ability can be trained. To demonstrate the feasibility of the proposed model in both fast-responding and slow-responding system, four experiments were conducted on a quad-rotor helicopter, a maglev ball system, a simulated inverted pendulum, and the Box-Jenkins gas furnace data, respectively. The results demonstrate the superiority of the proposed model over RBF-ARX model and some others in one-step-ahead prediction and multi-step-ahead prediction and show the feasibility of this model.

show abstract