Stable adaptive control with recurrent neural networks for square MIMO non-linear systems

Zerkaoui, Salem; Druaux, Fabrice; Leclercq, Edouard; Lefebvre, Dimitri

doi:10.1016/j.engappai.2008.12.005

Cited by 34 publications

(30 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Mean square error (MSE) is defined as performance of the net. A backpropagation (BP) algorithm is designed to reduce error between the actual output and the desired output of the network in a gradient descent manner [13]. The hidden layer is responsible for internal representation of data and the information transformation between input and output layers.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

Heidari

Homaei

2013

Advances in Artificial Neural Systems

View full text Add to dashboard Cite

This paper presents a neural scheme for controlling an actuator of pneumatic control valve system. Bondgraph method has been used to model the actuator of control valve, in order to compare the response characteristics of valve. The proposed controller is such that the system is always operating in a closed loop, which should lead to better performance characteristics. For comparison, minimum-and full-order observer controllers are also utilized to control the actuator of pneumatic control valve. Simulation results give superior performance of the proposed neural control scheme.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Recurrent networks have the advantage of being able to model dynamic systems accurately and in a compact form [13]. A recurrent network can be represented in a general diagrammatic form as illustrated in Figure 3(a).…”

Section: Proposed Neural Controllermentioning

confidence: 99%

Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

Heidari

Homaei

2013

Advances in Artificial Neural Systems

View full text Add to dashboard Cite

show abstract

“…T k k k M ω ω = E Then, substituting G (34) into (42), and according to (13) and (43), we can obtain:…”

Section: Robust Stability Of the Closed-loop System Based On Fading Wncnmentioning

confidence: 99%

“…However, many industrial processes inherently have strong multivariable and nonlinear dynamical behaviors. These increasingly complex nonlinear industrial processes can no longer be approximated satisfactorily by linear models and easily obtain desirable system performances using conventional linear control techniques [11][12][13]. Therefore, intelligent control approaches are good candidates to model complex nonlinear plants and design advanced controllers, such as neural network (NN) control [14,15] and fuzzy control [16].…”

Section: Introductionmentioning

confidence: 99%

Distributed robust control for nonlinear systems using wireless neural control

Ren

2015

Int. J. Control Autom. Syst.

View full text Add to dashboard Cite

This paper is concerned with the synthesis of a class of nonlinear system over the wireless neural control network (WNCN) which refers to a group of neuron nodes interacting with each other by radio connection. The nonlinear system is modeled by a standard neural network model (SNNM) which is the interconnection of a linear dynamic system and bounded static nonlinear operators. The WNCN treats itself as a fully distributed nonlinear dynamic controller. The unreliable wireless communication links within WNCN are modeled by fading channels. By constructing appropriate discretetime Lyapunov function, the global asymptotic stability of the closed-loop system is discussed in particular for the cases with stochastic perturbations induced by packet losses. The connection weights among the neuron nodes that guarantee stability of the system can be obtained by solving a convex optimization problem with some linear matrix inequality (LMI) constraints. A numerical example is given to illustrate the correctness and effectiveness of the theoretical results.

show abstract

“…To overcome this difficulty, neural networks are capable of ap proximating any continuous nonlinear functions and have been applied to nonlinear process emulation [8], [11]. An adaptive instantaneous neural emulator was investigated by [2], [4], [12], [13]. This neural emulation has been applied to chemical reactor for control issues.…”

Section: Introductionmentioning

confidence: 99%

Neural emulation applied to chemical reactors

Atig

Druaux

Lefebvre

et al. 2010

2010 7th International Multi- Conference on Systems, Signals and Devices

Self Cite

View full text Add to dashboard Cite

In this paper, a real time recurrent learning-based emulator is presented for nonlinear plants with unknown dy namics. This emulator is based on fully connected recurrent neural networks. Starting from zero values, updating rate, time parameter and weights of the instantaneous neural emulator adapt themselves in order to estimate the process output. The contribution of this paper is to validate the emulator with experimental data from the batch reactor of National Engineering School of Gabes, Tunisia.

show abstract

Stable adaptive control with recurrent neural networks for square MIMO non-linear systems

Cited by 34 publications

References 20 publications

Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

Distributed robust control for nonlinear systems using wireless neural control

Neural emulation applied to chemical reactors

Contact Info

Product

Resources

About