1.870 502


Abstract. Neural networks are intelligent calculator tools which have the capability of learning and they are considered as a solution and a novel methodology in solving the unknown phenomena in the fields of science and technology. Neural networks learn the dynamic state behavior of a system using its performance or a phenomenon occurrence. Furthermore, they are able to simulate a system model or a complicated phenomenon with non-linear behavior even by using examples with high desperation and turbulence. Using advanced learning algorithms, neural networks will be converged towards the physic of the phenomenon or the system rapidly and accurately. In this survey, after presenting a concise explanation of biologic neurons, artificial neurons will be studied. Then, the structure and relations ruling the artificial neural networks as well as the learning algorithm will be surveyed. Consequently, the particular implementation of neural network in the problem of estimating the attributes of power network and the neural network success will be evaluated in this article by presenting examples.


Turbulence, Neural networks, Transition lines

Full Text:



Rafiq, M. Y., Bugmann, G., and Easterbrook, D.J. (2001). "Neural network design for engineering applications." Computers & Structures 79(2): 1541-1552.

Beatty J. (2000). “The human brain: essentials of behavioral neuroscience”, California USA Sage Publications, 2 (3): 101–135.

Sadiku, M.N.O.(2004) . Numerical Technique in Electromagnetics. New York: CRC Press

Sanger, M., Terence, D. (1989). "Optimal unsupervised learning in a single-layer linear feedforward neural network." Neural networks 2(6): 459-473.

Papagiannis, G.K., Tsiamitros, D.A., Labridis, D.P., Dokopoulos, P.S. (2005). Direct numerical evaluation of earth path impedances of underground cables, IEE Proc.-Gener. Transm. Distrib., 152(3):321–327.

Papagiannis, G.K., Tsiamitros, D.A., Labridis, D.P., Dokopoulos, P.S., (2005). A systematic approach to the evaluation of the influence of multilayered earth on overhead power transmission lines, IEEE Trans. Power Del., 20(4):2594–2601.

Tsiamitros, D.A., Papagiannis, G.K., Labridis, D.P., Dokopoulos, P.S. (2005). “Earth return path impedance of underground cables for the two layer case”. IEEE Trans. Power Del., 20(3):2174–2181.

Carson, J.R. (1926). “Wave propagation in overhead wires with ground return.” Bell Syst. Tech. J., . 5(3): 539–554.

Xu, X.B., Liu, G., Chow, P. (2002). “A finite-element method solution of the zero-sequence impedance of underground pipe-type cable”.IEEE Trans. Power Del., 17(1):13–17.

Zhang, B., Cui, X., Li, L., He, J. (2005). “Parameter estimation of horizontal multilayer earth by complex image method”. IEEE Trans. Power Del.,20(2):1394–1401.

Uribe, J., Naredo, L., Moreno, P., and Guardado, L. (2004). “Algorithmic evaluation of underground cable earth impedances.” IEEE Trans. Power Del., 19(1): 316–322,

Cirino, André W., et al. (2009). "Cable parameter variation due to skin and proximity effects: determination by means of finite element analysis." Industrial Electronics, 2009. IECON'09. 35th Annual Conference of IEEE. IEEE

Habib, M.D. (2011). “Electromagnetic full wave modal analysis of frequency-dependent underground cables”, Diss. University of Manitoba.

Papagiannis, D. G. Triantafyllidis, and D. P. Labridis, “A one-step Şnite element formulation for the modeling of single and double circuit transmission lines,” IEEE Trans. Power Syst., vol. 15, no. 1, pp. 33–38, Feb. 2000.