Variable structure neural networks for adaptive control of nonlinear systems using the stochastic approximation

Mekki, Hassen; Chtourou, Mohamed; Derbel, Nabil

doi:10.1016/j.simpat.2006.07.001

Cited by 5 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the performance of a fully connected NN may be no better than that of a partly connected one with the same number of hidden nodes [97]. For an application with a large domain of input-output mappings, a variable structure NN can be able to perform the mapping task more efficiently in terms of accuracy and network complexity [98][99][100][101].…”

Section: Dynamic Structure-based Neural Networkmentioning

confidence: 99%

An improved dynamic structure-based neural networks determination approaches to simulation optimization problems

Zheng

Tan

Zhang

et al. 2010

Neural Comput & Applic

View full text Add to dashboard Cite

Simulation optimization studies the problem of optimizing simulation-based objectives. This field has a strong history in engineering but often suffers from several difficulties including being time-consuming and NP-hardness. Simulation optimization is a new and hot topic in the field of system simulation and operational research. This paper presents a hybrid approach that combines Evolutionary Algorithms with neural networks (NNs) for solving simulation optimization problems. In this hybrid approach, we use NNs to replace the known simulation model for evaluating subsequent iterative solutions. Further, we apply the dynamic structure-based neural networks to learn and replace the known simulation model. The determination of dynamic structure-based neural networks is the kernel of this paper. The final experimental results demonstrated that the proposed approach can find optimal or close-to-optimal solutions and is superior to other recent algorithms in simulation optimization.

show abstract

Section: Dynamic Structure-based Neural Networkmentioning

confidence: 99%

An improved dynamic structure-based neural networks determination approaches to simulation optimization problems

Zheng

Tan

Zhang

et al. 2010

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…In using RBF networks, the basis function are placed on regular points of a square mesh, for example, covering a relevant region of space where the state is known to be contained [3,4]. This region therefore is the network approximation region, which is in general known for a given system.…”

Section: Determination Of the Rbfs Location Centermentioning

confidence: 99%

“…The dynamic equation of the one-link rigid robotic manipulator is given by [4] The above dynamical equation can be written as the following state equatioṅ…”

Section: Neural Network Adaptive Controlmentioning

confidence: 99%

“…To test the robustness of the proposed algorithm, some disturbances are applied to the considered system. We consider a variation on the mass of the link as follows Comparing with other works [3,4,6,7], it is so clear that we used a minimal number of neuron while respecting the imposed performances. We can notice too, that the recruitment is made by a single neuron.…”

Section: Neural Network Adaptive Controlmentioning

confidence: 99%

“…Output tracking and stabilization of nonlinear systems has received considerable attention during last decades [4,5,24]. Feedback linearizing method has been widely used in this area.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Variable Structure Neural Networks for Adaptive Robust Control Using Evolutionary Artificial Potential Fields

Mekki¹,

Chtourou²

2013

Journal of Electrical Engineering

Self Cite

View full text Add to dashboard Cite

A novel neural network architecture, is proposed and shown to be useful in approximating the unknown nonlinearities of dynamical systems. In the variable structure neural network, the number of basis functions can be either increased or decreased with time according to specified design strategies so that the network will not overfit or underfit the data set. Based on the Gaussian radial basis function (GRBF) variable neural network, an adaptive state feedback controller is presented. The location of the centers of the GRBFs is analyzed using a new method inspired from evolutionary artificial potential fields method combined with a pruning algorithm. Using this method we can guarantee a minimal number of neuron. It is in noted, that both the recruitment and the pruning is made by a single neuron. Consequently, the recruitment phase does not perturb the network and the pruning does not provoke an oscillation of the output response. The weights of neural network are adapted using a Lyapunov approach. Moreover, the stability of the system can be analyzed and guaranteed by introducing the supervisory controller and modified adaptation law with projection.

show abstract

Internal model control based on self-constructing wavelet neural network

Wang

Zhao

Sun

et al. 2015

The 27th Chinese Control and Decision Conference (2015 CCDC)

View full text Add to dashboard Cite

In this paper, a novel internal model control (IMC) algorithm based on self-constructing wavelet neural network (WNN) is proposed for the nonlinear process. The self-constructing learning algorithm is composed of the structure learning and the parameters learning. In the structure learning phase, the similarity measurement method is adopted to determine whether or not to add a new wavelet base to satisfy the identification requirement. In addition, the impact of wavelet base on the output of the network is used as the basis for deciding whether to cut the wavelet base. The gradient descent method which can adjust the learning rate automatically is applied in the parameters learning. Combining the self-constructing WNN with IMC, the networks used to identify the process model and the controller model can dynamically determine the number of nodes. So, the networks convergence speed could be increased, and the dynamic performance and robustness of the system could be improved. 574 978-1-4799-7016-2/15/$31.00 c 2015 IEEE

show abstract

Variable structure neural networks for adaptive control of nonlinear systems using the stochastic approximation

Cited by 5 publications

References 24 publications

An improved dynamic structure-based neural networks determination approaches to simulation optimization problems

An improved dynamic structure-based neural networks determination approaches to simulation optimization problems

Variable Structure Neural Networks for Adaptive Robust Control Using Evolutionary Artificial Potential Fields

Internal model control based on self-constructing wavelet neural network

Contact Info

Product

Resources

About