Application of Artificial Neural Networks with Fast Fourier Transform for Waveform Analysis and Classification
Main Article Content
Abstract
This research presents electrical signal waveforms analysis and classification by applying the principle and theory of supervised artificial neural network. The input data for training and testing the network were processed by using Fast Fourier Transform. There are three input variables and one output for the network. From the experiment to determine the number of nodes in the hidden layer in order to obtain the optimal Mean Square Errors (MSE) for analyzing signals, the back propagation learning, training function, TrainLM and learning function along with LearnGDM were used. The experimental result found that the best network consisted of the optimal number of nodes at 3-40-1, input nodes, hidden nodes and the output node respectively. The transfer functions for hidden layer and output layer were logsig and purelin function respectively. The optimal MSE of training process was 1.45E-08. The MSE of the test was 1.54E-08, which provides the highest percentage of Efficiency Index (EI) in the testing process. The noise levels were added to the input data for testing the effectiveness of the proposed method. The satisfactory noise levels were not more than 5% of the input data. From the test, it showed that the proposed artificial neural network can be used in signal pattern recognition as a means of signal fault analysis and classification.
Article Details
The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.
References
[2] N. Pecharanin, M. Sone, and H. Mitsui, “An application of neural network for harmonic detection in active filter,” in Proceedings Neural Networks, IEEE World Congress on Computational Intelligence, vol. 6, no. 684, pp. 3756, 1994.
[3] K. Kittisak and J. Somchat, “The use of power quality to forecast reliability in the pea’s distribution system using artificial neural networks,” Journal of King Mongkut’s University of Technology North Bangkok, vol. 20, no. 1, pp. 4, January–April 2010.
[4] I. Porramate and J. Somchat, “Application of artificial neural network in optimal power flow,” Journal of King Mongkut’s University of Technology North Bangkok, vol. 18, no. 2, pp. 10, May–August 2008.
[5] K. Apichit, C. Jirasak and Y. Surapan, “Real time ecg compression/decompression system with multirate digital signal processing,” Thesis of King Mongkut’s University of Technology North Bangkok (Medical Instrumentation), pp. 6–7, 2006.
[6] J. Arrillaga, B. C. Smith, N. R. Watson, and A. R. Wood, Power System Harmonic Analysis. John Wiley & Sons, 1997, pp. 7–31.
[7] T. Dech and M. Phayung, “Ensemble data classification based on decision tree, artificial neuron network and support vector machine optimized by genetic algorithm,” Journal of King Mongkut’s University of Technology North Bangkok, vol. 21, no. 2, pp. 4, May–August 2011.
[8] H. C. Lin, “Intelligent neural network based dynamic power system harmonic analysis,” in Proceedings Power System Technology, PowerCon, vol. 1, no. 21–24, pp. 244–248, Nov. 2004.
[9] R. Rojas, Neural Network: A Systematic Introduction. Berlin: Springer-Verlag Berlin Heidelberg., 1996.
[10] S. Narimol and J. Somchat, “Short-term load forecast using artificial neural networks,” Journal of King Mongkut’s University of Technology North Bangkok, vol. 16, no. 2, pp. 2, April–June 2006.
[11] T. Chanwit and T. Sirivit, “Fault detection and protection of induction motor using artificial neural network,” King Mongkut's University of Technology North Bangkok, vol. 23, no. 1, pp. 4, January–April 2013.
[12] K. Adisorn, L. Panida, and N. Ariya, “An artificial neural network with technical indicators for stock investment: application to the stock exchange of thailand,” Information Technology Journal, vol. 11, no. 1, January–June 2015.
[13] H. Demuth and M. Beale, Neural Network Design, March 2001.
[14] T. Supakrit and J. Somchat, “Electric field estimation of high voltage transmission line using artificial neural networks,” King Mongkut’s University of Technology North Bangkok, vol. 20, no. 3, September–December 2010.
[15] K. Chanchai, T. Chanwit, S. Suriyotai, and T. Sirivit, “Fault detection and protection of Three-phase transformer using artificial neural network,” King Mongkut’s University of Technology North Bangkok, vol. 23, no. 1, pp. 7, January–April 2013.
[16] M. H. Beale, M. T. Hagan, and H. B. Demuth, Neural Network Toolbox, User’s Guide, The Mathworks, January 1998.