Memory neuron networks for identification and control of dynamical systems

In this paper the synthesis of the predictive controller for control of the nonlinear object is considered. It is supposed that the object model is not known. The method is based on a digital recurrent network (DRN) model of the system to be controlled, which is used for predicting the future behavior of the output variables. The cost function which minimizes the difference between the future object outputs and the desired values of the outputs is formulated. The function ga of the Matlab's Genetic Algorithm Optimization Toolbox is used for obtaining the optimum values of the control signals. Controller synthesis is illustrated for plants often referred to in the literature. Results of simulations show effectiveness of the proposed control system.

show abstract

“…The dynamical system used in the simulation example is given in [21]. It is assumed that structure of the model is known, n u = 1, n y = 2.…”

Section: Examplementioning

confidence: 99%

Neural Network Model Predictive Control of Nonlinear Systems Using Genetic Algorithms

Ranković

Radulović

Grujović

et al. 2014

INT J COMPUT COMMUN

View full text Add to dashboard Cite

show abstract

“…The size of the matrix can be represented by c c , the migration coefficient 3 c should be assigned in advance. After initialization, new individuals on the next generation are created by the following step.…”

Section: Fuzzy Model Strategy Based On Mcpsomentioning

confidence: 99%

“…Since for a dynamic system, the output is a nonlinear function of past output or past input or both, and the exact order of the dynamical systems is often unavailable, the identification and control of this system is much more difficult than that has been done in a static system. Therefore, the soft computing methods such as neural networks [1][2][3], fuzzy neural networks [4][5][6] and fuzzy inference systems [7] have been developed to cope with this problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Construction of Fuzzy Models for Dynamic Systems Using Multi-population Cooperative Particle Swarm Optimizer

Niu

Zhu

2005

Fuzzy Systems and Knowledge Discovery

View full text Add to dashboard Cite

Abstract.A new fuzzy modeling method using Multi-population Cooperative Particle Swarm Optimizer (MCPSO) for identification and control of nonlinear dynamic systems is presented in this paper. In MCPSO, the population consists of one master swarm and several slave swarms. The slave swarms execute Particle Swarm Optimization (PSO) or its variants independently to maintain the diversity of particles, while the particles in the master swarm enhance themselves based on their own knowledge and also the knowledge of the particles in the slave swarms. The MCPSO is used to automatic design of fuzzy identifier and fuzzy controller for nonlinear dynamic systems. The proposed algorithm (MCPSO) is shown to outperform PSO and some other methods in identifying and controlling dynamic systems.

show abstract

“…Artificial neural networks (ANNs) have emerged as a powerful learning technique to perform complex tasks in highly nonlinear dynamic environments [8][9][10][11][12][13][14][15]. Some of the prime advantages of using NN are: their ability to learn based on optimization of an appropriate error function and their excellent performance for approximation of nonlinear functions.…”

Section: Introductionmentioning

confidence: 99%

PMSM Servo Drive for V-Belt Continuously Variable Transmission System Using Hybrid Recurrent Chebyshev NN Control System

Lin¹

2015

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-Because the wheel of V-belt continuously variable transmission (CVT) system driven by permanent magnet synchronous motor (PMSM) has much unknown nonlinear and time-varying characteristics, the better control performance design for the linear control design is a time consuming job. In order to overcome difficulties for design of the linear controllers, a hybrid recurrent Chebyshev neural network (NN) control system is proposed to control for a PMSM servo-driven V-belt CVT system under the occurrence of the lumped nonlinear load disturbances. The hybrid recurrent Chebyshev NN control system consists of an inspector control, a recurrent Chebyshev NN control with adaptive law and a recouped control. Moreover, the online parameters tuning methodology of adaptive law in the recurrent Chebyshev NN can be derived according to the Lyapunov stability theorem and the gradient descent method. Furthermore, the optimal learning rate of the parameters based on discrete-type Lyapunov function is derived to achieve fast convergence. The recurrent Chebyshev NN with fast convergence has the online learning ability to respond to the system's nonlinear and timevarying behaviors. Finally, to show the effectiveness of the proposed control scheme, comparative studies are demonstrated by experimental results.

show abstract

Memory neuron networks for identification and control of dynamical systems

Cited by 311 publications

References 18 publications

Neural Network Model Predictive Control of Nonlinear Systems Using Genetic Algorithms

Neural Network Model Predictive Control of Nonlinear Systems Using Genetic Algorithms

Construction of Fuzzy Models for Dynamic Systems Using Multi-population Cooperative Particle Swarm Optimizer

PMSM Servo Drive for V-Belt Continuously Variable Transmission System Using Hybrid Recurrent Chebyshev NN Control System

Contact Info

Product

Resources

About