Neural Network Based Approach Applied to Review Transient Stability of an Alternator Connected to Infinite Bus
|International Journal of Engineering Trends and Technology (IJETT)||
|© 2016 by IJETT Journal|
|Year of Publication : 2016|
|Authors : Priyaranjan Mandal
|DOI : 10.14445/22315381/IJETT-V38P259|
Priyaranjan Mandal"Neural Network Based Approach Applied to Review Transient Stability of an Alternator Connected to Infinite Bus", International Journal of Engineering Trends and Technology (IJETT), V38(6),320-325 August 2016. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group
This paper approaches to analyse the transient stability of an alternator connected to infinite bus. A three phase fault is considered to happen to the total system. The characteristics behaviour of the alternator relative torque angle is studied in time domain Simulink model, based on MATLAB, of a single machine connected to an infinite bus system is assumed to suffer severe three phase short circuit faults. The transient state behaviour of the rotor relative torque angle shows a sustained oscillations indicating an uncertainty of the system to reach the steady state. The behaviour of the system is improved by providing a damping to the system. Inclusion of negative feedback technique is utilized to provide the damping. The damped system shows an underdamped behaviour in the post fault conditions ensuring a good tendency of the system to reach to steady state quickly. A neural network (NN) is assumed to be configured for prediction of the behaviour of the transient stability of the actual system. The artificial neural network is configured by learning and training of the actual system by the Levenberg-Marquardt method of training (trainlm) to predict the actual system. The NN based system predicts the actual system successfully showing its good strength and reliability.
 M.T Hagan and M. Menhaj, “Training feedforward
networks with the Marquardt algorithm,” IEEE Trans. On
Neural Networks, vol. 5, no.6, pp.989-993, 1994.
 M.T Hagan, H. B. Demuth and M. H. Beale, Neural Network Design PWS Publishing, Boston, 1996  G. P. Liu, Nonlinear identification and Control, Springer- Verlag, London, 2001.
 B. S. Manke, Linear Control Systems, Khanna Publishers, Delhi, 7-Ed., 2004.
 Zhang. Zhiguo, “ Research on damage identification in bridge based on model analysis theory and neural networks [D],?? Wuhan: Wuhan University of Technology, 2005.
 Andel Merabet, Mohand Ouhrouche and Rung-Tien Bui, “Neural Generalized Controller for Induction Motor,” University of Quebec at Chicoutimi , vol.1, no.1, pp. 83- 100, 2006.
 R. A. Jayabarathi and N. B. Debarajan, “ANN based DSPIC controller for reactive compensation,” American Journal of Applied Sciences, pp. 508-515, 2007.
 REN Li-na, RUI Zhi-yuhan, Liu Yan-xin, XU Long-Yun, “Study of identification method anomalous electric load data [J],?? Water Power, vol. 34(2), pp 43-45, 2008.
 G. Madhusudhana Rao and Dr. B. V. Sankar Ram, “A neural network based speed control for dc motor,” Int. Journal of Recent Trends in Engineering, vol.2, no. 6, Nov, 2009.
 Lina. J Rashad “speed control of permanent magnet DC motor using neural network control” Eng. & Tech Journal, vol. 28, no 19, 2010.
 C. Jhon, O. Sallan, Noel R. Estoperz, “An artificial neural network based real time reactive power controller,” proc. of World Congress on engineering and Computer Science 2011, vol. I, WCECS 2011, San Francisco, USA, Oct, 19- 20, 2011.
 A. Mishra, P. Choudhary, “Artificial neural network based controller for speed control of an Induction motor using indirect vector control method,” Int. Jr. of Power Electronics and Drives System, vol-2, no. 4, pp. 402-408, Dec, 2012.
 Priyaranjan Mandal, Binay Biswas, “To identify a torque controller system approximating a neural network based on model reference technique,” Int. Jr. of engineering and Computer Science, Vol-5, no.9, pp 17833-17838, Sep, 2016.
Transient Stability, neural network, relative torque angle, training (trainlm).