Nonlinear one-step-ahead control using neural networks: Control strategy and stability design

Tan, Yonghong; Cauwenberghe, Achiel Van

doi:10.1016/s0005-1098(96)80006-9

Cited by 51 publications

(25 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure of neural networks may be classified as feedforward and recurrent. Most of the publications in nonlinear system identification use feedforward neural networks (FFNNs) with backpropagation or its other variations for training, for example [4,5].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Al-Seyab

Cao

2008

Journal of Process Control

107

View full text Add to dashboard Cite

In this paper, a continuous time recurrent neural network (CTRNN) is developed to be used in nonlinear model predictive control (NMPC) context. The neural network represented in a general nonlinear statespace form is used to predict the future dynamic behavior of the nonlinear process in real time. An efficient training algorithm for the proposed network is developed using automatic differentiation (AD) techniques. By automatically generating Taylor coefficients, the algorithm not only solves the differentiation equations of the network but also produces the sensitivity for the training problem. The same approach is also used to solve the online optimization problem in the predictive controller. The proposed neural network and the nonlinear predictive controller were tested on an evaporation case study. A good model fitting for the nonlinear plant is obtained using the new method. A comparison with other approaches shows that the new algorithm can considerably reduce network training time and improve solution accuracy. The CTRNN trained is used as an internal model in a predictive controller and results in good performance under different operating conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Al-Seyab

Cao

2008

Journal of Process Control

107

View full text Add to dashboard Cite

show abstract

“…trtr6-c m9t bU'o-ckU don giin, dam bao tfnh 5n dinh cda h~thOng kfn. D~U.ng de?chfnh xac, ta c6 th~xet ham sai so phti'c t'!-Phon -nhir trong [5] (41) Plnrong phap tren cling d~dang ap dung cho cac h~thong c6 tr~.…”

Section: Ket Lu~nmentioning

confidence: 99%

Hệ thống mờ nơron với học cấu trúc trên cơ sở cộng hưởng thích nghi và ứng dụng trong điều khiển “đón đầu trước một bước”

Hy¹

2016

JCC

View full text Add to dashboard Cite

“…We can also obtain the one-step-ahead control from the optimization of the cost function (20) by using the gradient descent optimizing technique [25], i.e.,…”

Section: Remarkmentioning

confidence: 99%

Adaptive Observer Based Data-Driven Control for Nonlinear Discrete-Time Processes

Jiang

Shi

2014

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-In this paper, two adaptive observer-based strategies are proposed for control of nonlinear processes using input/output (I/O) data. In the two strategies, pseudo-partial derivative (PPD) parameter of compact form dynamic linearization and PPD vector of partial form dynamic linearization are all estimated by the adaptive observer, which are used to dynamically linearize a nonlinear system. The two proposed control algorithms are only based on the PPD parameter estimation derived online from the I/O data of the controlled system, and Lyapunov-based stability analysis is used to prove all signals of close-loop control system are bounded. A numerical example, a steam-water heat exchanger example and an experimental test show that the proposed control algorithm has a very reliable tracking ability and a satisfactory robustness to disturbances and process dynamics variations.Note to Practitioners-In actual industrial process, the dynamic behaviors is complex and nonlinear, and their mathematical models are often difficult to obtain. How to design the controller for unknown nonlinear systems using input/output (I/O) data has become one main focus of control researches. Therefore, in this paper, two adaptive observer-based data-driven control algorithms are proposed for a class of unknown nonlinear systems. Finally, the effectiveness of two control strategies are illustrated via simulation study and experimental test.Index Terms-Data-driven control, adaptive observer, pseudopartial derivative, Lyapunov-based stability analysis, nonlinear discrete-time systems.

show abstract

Nonlinear one-step-ahead control using neural networks: Control strategy and stability design

Cited by 51 publications

References 7 publications

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

Hệ thống mờ nơron với học cấu trúc trên cơ sở cộng hưởng thích nghi và ứng dụng trong điều khiển “đón đầu trước một bước”

Adaptive Observer Based Data-Driven Control for Nonlinear Discrete-Time Processes

Contact Info

Product

Resources

About