Neuro-Fuzzy Model Based Control

Matko, Drago; Kavšek-Biasizzo, Katarina; Kocijan, Juš

doi:10.1142/9789812816528_0007

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last decade, soft computing tools such as neural networks [7][8][9][10], fuzzy systems [11][12][13], genetic algorithms [14] and their hybrids [15][16][17] have been utilized to obtain an accurate model of the plant in the GPC loop. Recently, support vector machines have gained much attention due to their great potential of approximation, and have been used in the GPC scheme [18] for controlling non-linear systems.…”

Section: Introductionmentioning

confidence: 99%

Online trained support vector machines-based generalized predictive control of non-linear systems

İplikçi

2006

Int. J. Adapt. Control Signal Process.

View full text Add to dashboard Cite

In this work, an online support vector machines (SVM) training method (Neural Comput. 2003; 15: 2683-2703, referred to as the accurate online support vector regression (AOSVR) algorithm, is embedded in the previously proposed support vector machines-based generalized predictive control (SVM-Based GPC) architecture (Support vector machines based generalized predictive control, under review), thereby obtaining a powerful scheme for controlling non-linear systems adaptively. Starting with an initially empty SVM model of the unknown plant, the proposed online SVM-based GPC method performs the modelling and control tasks simultaneously. At each iteration, if the SVM model is not accurate enough to represent the plant dynamics at the current operating point, it is updated with the training data formed by persistently exciting random input signal applied to the plant, otherwise, if the model is accepted as accurate, a generalized predictive control signal based on the obtained SVM model is applied to the plant. After a short transient time, the model can satisfactorily reflect the behaviour of the plant in the whole phase space or operation region. The incremental algorithm of AOSVR enables the SVM model to learn the new training data pair, while the decremental algorithm allows the SVM model to forget the oldest training point. Thus, the SVM model can adapt the changes in the plant and also in the operating conditions. The simulation results on non-linear systems have revealed that the proposed method provides an excellent control quality. Furthermore, it maintains its performance when a measurement noise is added to the output of the underlying system.

show abstract

Section: Introductionmentioning

confidence: 99%

Online trained support vector machines-based generalized predictive control of non-linear systems

İplikçi

2006

Int. J. Adapt. Control Signal Process.

View full text Add to dashboard Cite

show abstract

“…Díaz et al (2001a; demonstrated the ability of this type of control system to adapt to changing circumstances. Others who have reported the use of neural network-based control of heat exchangers include AlDuwaish and Karim (1996), who combined a feedforward multilayer neural network and an auto-regressive moving average linear model; Matko et al (1998) who proposed the use of a nonlinear autoregressive method; Riverol and Napolitan (2000) who used it to tune a PID controller; and Quek and Wahab (2000) who addressed the larger issue of integrated process supervision for the real-time control of an industrial heat-exchanger process.…”

mentioning

confidence: 99%

Stabilization of Thermal Neurocontrollers

Dı́az

Sen

Yang

et al. 2004

Applied Artificial Intelligence

View full text Add to dashboard Cite

This work deals with the stabilization of neurocontrollers used in thermal applications. The control system can be reduced to an iterative, nonlinear map in time, and its linearization enables a stability analysis. For simple neural networks with few neurons, the eigenvalues can be analytically calculated in terms of the synaptic weights and biases. However, unless care is taken, usual training methods can drive the network to weights and biases such that the corresponding control system is unstable. A modified backpropagation training method is developed here to simultaneously minimize the target error and increase the dynamic stability of the system. Numerical computations are used to analyze the stability of realistic neural networks and their corresponding control systems. The techniques developed are used on an experimental heat-exchanger facility where the stability results are tested and validated.A complex thermo-hydraulic system can be defined as one which, although containing subsystems whose behavior can be predicted by mathematical models, is itself too complicated for that. These systems are difficult to predict from first principles, using the basic governing equations of mass, momentum, and energy in differential form. Even though the use of computational fluid dynamics is commonplace, currently available hardware and methodologies do not permit solutions in more than in fairly simple geometries and=or for laminar flows. For flows under realistic conditions, such as in a heat exchanger, one can resort to simplifications like one-dimensionality and empirically obtained heat transfer coefficients. The net result is that whatever inaccuracies that are in these assumptions are reflected in the We gratefully acknowledge the support of the late Mr. D. K.

show abstract

Neuro-Fuzzy Model Based Control

Cited by 2 publications

References 0 publications

Online trained support vector machines-based generalized predictive control of non-linear systems

Online trained support vector machines-based generalized predictive control of non-linear systems

Stabilization of Thermal Neurocontrollers

Contact Info

Product

Resources

About