Abstract

In this paper, Neural network algorithm is introduced to study the singular system of a linear electrical circuit for time invariant and time varying cases. The discrete solutions obtained using neural network are compared with Runge-Kutta(RK) method and exact solutions of the electrical circuit problem and are found to be very accurate. Error graphs for inductor currents and capacitor voltages are presented in a graphical form to show the efficiency of neural network algorithm. This neural network algorithm can be easily implemented in a digital computer for any singular system of electrical circuits.

References

• R .K. Alexander and J.J. Coyle, “Runge-Kutta Methods for Differential-Algebric Systems,” SIAM J. of Numerical Analysis, vol. 27, no. 3, 1990, pp. 736-752.
• S.I.Amari “Mathematical Foundations of neurocomputing" Proc. IEEE, Vol. 78, pp. 1443-1463, Sep. 1990.
• J. A. Anderson and E. Rosenfeld, Eds., Neurocomputing: Foundations of Research.Cambridge, MA: MIT Press, 1988.
• G.K.Boray and M.D.Srinath, ”Conjugate Gradient Techniques for Adaptive Filtering," IEEE Trans. Circuits Syst.-I, Vol. 39, pp. 1-10, Jan. 1992.
• S.L.Campbell, Singular Systems of Differential Equations, Pitman, Marshfield, MA, 1980.
• S.L.Campbell, Singular Systems of Differential Equations II, Pitman, Marshfield, MA, 1982.
• L.O. Chua and P.M. Lin, Computer-Aided Analysis of Electronic Circuits, Prentice-Hall, New Jersey, USA, 1975.
• L.O.Chua, C. A. Desoer and E. S. Kuh, Linear and Nonlinear Circuits. McGraw-Hill, 1987.
• L.Dai, Singular Control Systems, Lecture Notes in Control and Information Sciences, Springer Verlag, NewYork, 1989.
• D.J. Evans, “A New 4th Order Runge-Kutta Method for Initial Value Problems with Error Control,” Int.lJ. Computer Mathematics, vol. 139, 1991, pp. 217-227.
• D.J. Evans and A.R. Yaakub, “A New Fifth Order Weighted Runge-Kutta Formula,” Int.J.Computer Mathematics, vol. 59, 1996, pp. 227-243.
• D.J.Evans and A.R.Yaakub, “Weighted Fifth Order Runge-Kutta Formulas for Second Order Differential Equations,” Int. J.Computer Mathematics, vol. 70, 1998, pp. 233-239.
• P. Friedel and D.Zwierski, Introduction to Neural networks. (Introduction aux Reseaux de Neurones.) LEP Technical Report C 91 503, December 1991.
• D.Hammerstrom, “Neural networks at work," IEEE Spectrum, pp. 26-32, June 1993.
• R. Hecht-Nielsen, “Nearest matched filter classification of spatio- temporal patterns ", Applied Optics, Vol. 26, pp. 1892-1899, May 1987.
• D. R. Hush and B. G. Horne, “Progress in Supervised Neural Networks," IEEE Sign.Proc. Mag., pp. 8-39, Jan.1993.
• J. S. R. Jang, “Self-Learning Fuzzy Controllers Based on Temporal Back Propagation," IEEE Trans. Neural Networks, Vol. 3, pp. 714-723, Sep. 1992.
• D.R.Kincaid and E.W.Cheney, Numerical Analysis: Mathematics of Scientific Computing. Books/Cole Publishing Company, 1991.
• I.E. Lagaris, A. Likas, D.I.Fotiadis, Artificial neural networks for solving ordinary and partial differential equations, IEEE Trans.Neural Networks 9(1998) 987–1000.
• J.D. Lambert, Numerical Methods for Ordinary Differential Systems. The Initial Value Problem, John Wiley & Sons, Chichester, UK, 1991.
• F.L. Lewis, A Survey of linear singular systems, Circ. Syst. Signal Process. 5 (1986) 3–36.
• R.P. Lippmann, “An Introduction to Computing with neural Nets," IEEE ASSP Mag., pp. 4-22, Apr. 1987
• C. A. Mead, Analog VLSI and Neural Systems. Reading, MA: Addison-Wesley, 1989.
• P. B. L. Meijer, “Fast and Smooth Highly Nonlinear Table Models for Device Modeling," IEEE Trans. Circuits Syst., Vol. 37, pp. 335-346, Mar. 1990.
• K.Murugesan, D.Paul Dhayabaran, and D.J. Evans, “Analysis of Different Second Order Systems via Runge- Kutta Method,” Int. J.Computer Mathematics, vol. 70, 1999, pp. 477- 493.
• K.Murugesan, D.Paul Dhayabaran, and D.J. Evans,“Analysis of Different Second Order Multivariable Linear System Using Single Term Walsh Series Technique and Runge-Kutta Method,” Int. J. of Computer Mathematics, vol. 72, 1999, pp. 367-374.
• K. Murugesan, D. Paul Dhayabaran, and D.J. Evans, “Analysis of Non-Linear Singular System from Fluid Dynamics Using Extended Runge-Kutta Methods,” Int. Journal.Computer Mathematics, vol. 76, 2000, pp. 239- 266.
• K. Murugesan, D.Paul Dhayabaran, E.C. Henry Amirtharaj, and D.J. Evans, “A Comparison of Extended Runge-Kutta Formulae Based on Variety of Means to Solve System of IVPs,” International .Journal of Computer Mathematics, vol. 78, 2001, pp. 225-252.
• K. Murugesan, D. Paul Dhayabaran, E.C. Henry Amirtharaj and D.J. Evans, “A Fourth Order Embedded Runge-Kutta RKACeM(4,4) Method Based on Arithmetic and Centrodial Means with Error Control,” Int. J. Computer Mathematics, vol. 79, no. 2, 2002, pp. 247- 269.
• K. S. Narendra, K. Parthasarathy, “Gradient Methods for the Optimization of Dynamical Systems Containing Neural Networks," IEEE Trans. Neural Networks, Vol. 2, pp. 252- 262, Mar. 1991. 170 BIBLIOGRAPHY
• D.E . Rumelhart and J.L. McClelland, Eds.,Parallel Distributed Processing, Explorations in the Microstructure of Cognition. Vols. 1 and 2. Cambridge, MA: MIT Press, 1986.
• F. M. A. Salam, Y. Wang and M.-R. Choi, “On the analysis of Dynamic Feedback Neural Nets," IEEE Trans. Circuits Syst., Vol. 38, pp. 196-201, Feb. 1991.
• Senjyu, T., Sakihara, H., Tamaki, Y., and Uezato, K. 2000.“Next Day Peak Load Forecasting using Neural Network with Adaptive Learning Algorithm Based on Similarity”. Electric Machines and Power Systems. 28(7):613- 624.
• P. De Wilde, Neural Network Models, second ed., Springer Verlag, London, 1997.