Use of neural networks for dynamic modelling and predictive control of power plant systems

• Autorzy: Lazar C. , Carari S. , Vrabie D. , Ivana D.
• Języki publikacji: EN

Abstrakty

EN

Boiler drum is a critical power plant component having nonlinearities and a non-minimum phase response but, despite this fact, control structures with PID controllers are usually used in industrial applications. In the last decades, important efforts have been made to improve the closed loop performance of the drum level controller by using on-line self-tuning approaches. In this paper, such a method of on-line adaptation is presented based on a neuro-predictive technique of the authors of [4], [5]. In order to implement the neuro-predictive procedure a neural model was developed for drum level process. By means of simulation, a comparison between the obtained drum level controller's operation and that of a classic controller of the type PI under similar conditions is carried out.

Słowa kluczowe

EN

neural networks; dynamic modelling; predictive control; PID controllers; neurocontrollers; closed loop systems; level control

PL

sieci neuronowe

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Systems Science
• Rocznik: 2005
• Tom: Vol. 31, no 1
• Strony: 37--44
• Opis fizyczny: Bibliogr. 9 poz., rys., wykr.

Twórcy

autor

Lazar C.

• "Gh. Asachi" Technical University of lasi, Department of Automatic Control Blvd. D. Mangeron 53A, 700050 lasi, Romania

autor

Carari S.

• "Gh. Asachi" Technical University of lasi, Department of Automatic Control Blvd. D. Mangeron 53A, 700050 lasi, Romania

autor

Vrabie D.

• "Gh. Asachi" Technical University of lasi, Department of Automatic Control Blvd. D. Mangeron 53A, 700050 lasi, Romania

autor

Ivana D.

• Power Plant Ltd. Ias, Chisinaului 25, 700182 Ias, Romania

Bibliografia

• [1] Astróm K. J., Bell R., Drum-boiler dynamics. Automática, Vol. 36, 2000, 363-378.
• [2] Chen S., Billings S. A., Grant P. M., Nonlinear system identification using neural networks. Int. J. Control, Vol. 49, No. 3, 1990, 1013-1032.
• [3] Farthing D. C., Boiler drum level measurement and control, Seminar on Improving Boiler Room Efficiencies, Tech Paper #909, 2001.
• [4] Lazar C., Vrabie D., Carari S., Ivana D., A neuro-predictive approach for tuning industrial controllers, WSEAS Transactions on Systems, Vol. 3, No. 2, 2004, 730-735.
• [5] Lazar C., Carari S., Vrabie D., Kloetzer M., Neuro-predictive control based self-tuning of PID controllers, Proc. of 12lh European Symposium on Artificial Neural Networks ESANN'04, Bruges, 2004, 391-396.
• [6] Liu G. P., Kadirkamanathan V., Billings S.A., Predictive control for nonlinear systems using neural networks. Int. J. Control, Vol. 71, 1998, 1119-1132.
• [7] Parlos A. G., Chong K. T., Atiya A. F., Application of the recurrent multilayer perceptron in modeling complex process dynamics, IEEE Transaction on Neural Networks, Vol. 5, 1994, 255-266.
• [8] Parlos A. G., Parthasarathy S., Atiya A. F., Neuro-predictive process control using on-line controller adaptation, IEEE Transactions on Control Systems Technology, Vol. 9, No. 5, 2001, 741-751.
• [9] Steingress F. M., Frost H. J., High pressure steam boilers, 2nd ed., American Technical Publisher, 2000.