Nonlinear system modeling and robust predictive control based on RBF-ARX model

Peng, Hui; Yang, Zi‐Jiang; Gui, Weihua; Wu, Min; Shioya, H.; Nakano, Kazushi

doi:10.1016/j.engappai.2006.05.012

Cited by 40 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The information granule-oriented radial basis function neural network 3.1. General topology of the RBF neural network RBF neural networks (Vong et al, 2006;Zhai and Yu, 2009;Park et al, 2008;Gudur and Dixit, 2008;Matuško et al, 2008;Peng et al, 2007;Barletta et al, 2007;Frias-Martinez et al, 2006;Langoni et al, 2006) have been traditionally associated with a simple architecture of a three-layer neural network, in which an n-dimensional input vector x¼ [x 1 , x 2 , ..., x n ] T is transformed in a nonlinear fashion through the receptive fields (basis functions). Subsequently, the resulting activation levels are transformed in a linear way by a single neuron located at the output layer.…”

Section: Experimental Equipment and Results Of Measurementmentioning

confidence: 99%

“…Because of the attractive simple topological structure and universal approximation abilities (Park and Sandberg 1991), RBF neural networks have been successfully applied to a wide range of engineering applications, see Vong et al (2006), Zhai andYu (2009), Park et al (2008), Gudur and Dixit (2008), Matuško et al (2008), Peng et al (2007), Barletta et al (2007), Frias-Martinez et al (2006), and Langoni et al (2006.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design of information granule-oriented RBF neural networks and its application to power supply for high-field magnet

Park

Chung

et al. 2011

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Section: Experimental Equipment and Results Of Measurementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Design of information granule-oriented RBF neural networks and its application to power supply for high-field magnet

Park

Chung

et al. 2011

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Another control based on ANN applied to induction motor control is presented in [25]. Efforts to make adaptive control to control linear and nonlinear systems are shown in [26,27] or the proposal of [28] using ANN to build a predictive control. As well known, the PID control with fixed gain, after a long time of system operation has the disadvantage of not working properly due to system parameters variations.…”

Section: Introductionmentioning

confidence: 99%

PID Based on a Single Artificial Neural Network Algorithm for Intelligent Sensors

Rivera-Mejia¹,

Léon-Rubio²,

Arzabala-Contreras³

2012

JART

View full text Add to dashboard Cite

Today control is required in any field or application. Nowadays, classic control is the most used, but it is well-known that users need to know the system’s characteristics to reach optimal control. This paper is focused on designing a proportional integral derivative control, based on a single artificial neural network with the aim to improve its performance and its use with minimal control knowledge from the end user. The proposed control was assessed with simulated and practical physical systems of first and second order. In order to increase the confidence of the intelligent sensor control, the evaluation was made using the classical test of control response of a step as input. The proposed control was implemented on an intelligent sensor with a small microcontroller. Also, the performance was compared between the proposed control and a commercial control. Here, an intelligent sensor is presented with control capability for a wide variety of physical systems. The experiments performed demonstrated the capability of the proposed control, which can be easily used and save time at the initial control set up.

show abstract

“…Based on this observation, many LMI-based fuzzy controller designs have been developed to solve output regulation control problems for nonlinear systems [11], [12]. In recently year, several well-developed approaches are proposed to design LMI-based NMPC algorithms for the purpose of regulating the system output at constant values [13], [14]. In this work, we combine coordinate translation, integral control technique, and fuzzy MPC scheme; meanwhile, a piecewise Lyapunov function is defined and utilized to synthesize the controller, to deal with the output regulation problem for nonlinear systems.…”

Section: Introductionmentioning

confidence: 99%

Output regulation using integral fuzzy predictive control with piecewise Lyapunov functions

Liu

Lian

2011

2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)

View full text Add to dashboard Cite

This study proposes an LMI-based integral fuzzy model predictive control (MPC) for output regulation via piecewise Lyapunov function. In order to eliminate the system's bias and guarantee the zero-offset output regulation performance, firstly we take coordinate translation on equilibrium point and introduce an added integral state of output regulation error for the nonlinear plant, and then convert the resulting augmented system into a Takagi-Sugeno fuzzy model. Under the input constraint, an integrator based state feedback control law is computed by solving a convex optimization problem based on the infinite horizon predictive control scheme. Moreover, the proposed control design has following merits: i) reducing the conservatism by using piecewise Lyapunov function; ii) improving the transient performance by adding a decay rate condition; and iii) ensuring asymptotic stability for output regulation in the presence of time varying parameter. Finally, a numerical example is presented to demonstrate the effectiveness of the proposed integral fuzzy predictive controller.

show abstract

Nonlinear system modeling and robust predictive control based on RBF-ARX model

Cited by 40 publications

References 16 publications

Design of information granule-oriented RBF neural networks and its application to power supply for high-field magnet

Design of information granule-oriented RBF neural networks and its application to power supply for high-field magnet

PID Based on a Single Artificial Neural Network Algorithm for Intelligent Sensors

Output regulation using integral fuzzy predictive control with piecewise Lyapunov functions

Contact Info

Product

Resources

About