This paper describes a laboratory application for the forecasting the dielectric properties, using an artificial neural network embedded in a microprocessor. The dielectric permittivity and loss factor of the insulation material were determined as a function of temperature and frequency inputs by an implemented ANN model. For this purpose, a three-layer feed-forward back-propagation ANN model with two inputs and two outputs was created. The Levenberg-Marquardt back-propagation algorithm was selected as a training function, the gradient descent method with momentum weighting and bias learning function as an adaptive learning function, and mean squared normalized error as a performance function. The first layer of the network consists of three neurons, the second layer of six neurons with a tangent sigmoid activation function, and the outputlayer of two outputs with a linear transfer function. The initial values of weights and biases were selected randomly. Input and layer of two outputs with a linear transfer function. The initial values of weights and biases were selected randomly. Input and output data were rescaled to have the minimum possible determination errors. The microprocessor-based method is a low-cost determination system independent of computers and can be used in both laboratory and industrial applications.

Keywords - artificial neural network, dielectric constant, microcontroller

[1] F. Aras, K. Keles, Laboratory experiments for electrical insulation courses using a new high-voltage cell. International Journal of Electrical Engineering Education, 44/1, pp. 85-95, 2007.

[2] Y. Liao, Neural Networks in Hardware: A Survey. http://bit.csc.lsu.edu/~jianhua/shiv2. pdf, Visiting Date: 07.02.2010.

[3] I. Aybay, S. Çetinkaya, U. Halıcı, Classification of Neural Network Hardware. Neural Network World, IDG Co.,Vol 6 No 1, pp. 11-29, 1996.

[4] K. Asanovic, J. Beck, BED. Kingsbury, P. Kohn, N. Morgan, J. Wawrzynek, SPERT: a VLIW/SIMD neuro-microprocessor. Neural Networks, IJCNN., International Joint Conference, Volume: 2, pp. 577-582, 1992.

[5] S. Kumar, K. Forward, M. Palaniswami, A Review of Design Aspects for Neurocomputers. Australian New Zealand Conf. on Intelligent Information Systems, Australia, 1996.

[6] A. Onduk, Control of Power Generators Using ANN. Doctoral Thesis, T.C. Sakarya University, Graduate School of Natural and Applied Sciences, 2002.

[7] C. Bal, The Performance Analysis of Artificial Neural Network for Speed Control of DC Motors. T.C. Fırat University, Graduate School of Natural and Applied Sciences, 2002.

[8] JX. Zhao, HZ. Jın, HW. Han, Dielectric Loss Factor Forecasting Based on Artificial Neural Network. Second International Conference on Information and Computing Science, England, 2009.

[9] M. İnal, F. Aras, Determination of Dielectric Properties of Insulating Materials Using Artificial Neural Networks. Journal Of The Faculty of Engineering and Architecture of Gazi University, Vol. 20, No 4, pp. 455-462, 2005.

[10] M. Adé, R. Lauwereins, J. Peperstraete, A fast simulator for neural networks on DSPs or FPGAs. Neural Networks for Signal Processing [1992] II., roceedings of the 1992 IEEE-SP Workshop, pp. 597-605, 1992.

[11] MASK. Khan, MA. Rahman, Real-Time Implementation of 1PM Motor Protection Using Artificial Neural Network. The 33rd Annual Conference of the IEEE Industrial Electronics Society (IECON), Taiwan, 2007.

[12] FI. Ahmed, AM. Zaki, EA. Ebrahim, Neuro-controller for high performance induction motor drives in robots. Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference, ISBN: 0-7803-7044-9, Volume: 3, pp. 2082-2087, 2001.

[13] M. Mohamadian, EP. Nowicki, A. Chu, F. Ashrafzadeh, JC. Salmon, DSP implementation of an artificial neural network for induction motor control. Electrical and Computer Engineering, 1997. IEEE 1997 Canadian Conference, vol.2, pp.435 - 437, 1997.

[14] I. Turkoglu, Hardware implementation of varicap diode’s ANN model using PIC microcontrollers. Sensors and Actuators A, 138, pp.288–293, 2007.

[15] A. Buldu, H. Korkmaz, A Usb kit for digital I/O applications in a digital electronics lab designed by using PIC16C765 microcontroller. Computer Applications in Engineering Education, 17, pp.131-138, 2009.

[16] MMM. Khairurrijal, A. Suhendi, H. Thaha, M. Budiman, An AT89S52 microcontroller-based single board computer for teaching an instrumentation system course. Computer Applications in Engineering Education, 15, pp.166-173, 2007.

[17] Y. Mohanna, M. Hamad, R. Jabr, A. Alaeddine, O. Bazzi, Teaching microprocessors, microcontrollers, and digital signal processing courses using only one target processor: The new born dsPIC30F from Microchip. Computer Applications in Engineering Education, 15, pp. 185-191, 2007.

[18] CM. Hsu, HM. Chao, Construction μ-controller teaching tool with the integration of hardware and software technology. IEEE International Conference on New Trends in Information and Service Science, Beijing, China, 2009.

[19] CR. Alavala, Fuzzy Logic and Neural Networks : Basic Concepts and Applications. Daryaganj, Delhi, IND: New Age International, ISBN: 8122421822, 2008.

[20] Microchip. PIC18FXX2 Data Sheet. 2002, http://ww1.microchip.com/downloads/en /devicedoc/39564c.pdf, Visiting Date: 07.02.2010.