Dipole Positioning Recognition Using Neural Networks

Abstract:

A ships position could be detected by its magnetic signature. A crucial issue, regarding this approach for naval vessel monitoring, is the difficulty in defining the appropriate number of magnetic sensors needed and their respective configuration, in order to predict accurately the position of the magnetic mass through the measured magnetic field intensities on a specific boundary. In the present paper, this problem is dealt downscaled at tracing the exact position and orientation of a single dipole. In particular, Neural Networks, properly calibrated, are implemented as a method for the detection of the position and the orientation of a dipole through the measured magnetic field inducted. The results indicate that measurements of two magnetic field sensors at the boundary could provide sufficient information about the dipoles position, with a certainty of 99%.

• Periodical: Key Engineering Materials (Volume 605)
• Pages: 673-676
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.605.673
• Online since: April 2014
• Authors: Katerina Skouta
• Keywords: Finite Element Analysis (FEA), Magnetic Field, Magnetometry, Neural Network (NN), Ship Detection

References

[1] DS Vlachos, DK Fragoulis, JN Avaritsiotis An adaptive neural network topology for degradation compensation of thin film tin oxide gas sensors, Sensors and Actuators B: Chemical, 45, 3, p.223–228, (1997)

DOI: 10.1016/s0925-4005(97)00309-2

[2] CA Papadopoulos, DS Vlachos, Effect of surface catalysts on the long-term performance of reactively sputtered tin and indium oxide gas sensors, Sensors and Actuators B: Chemical 42, 2, p.95–101, (1997)

DOI: 10.1016/s0925-4005(97)00190-1

[3] I. Giouroudi, A. Ktena and E. Hristoforou, Microstructural characterization of cylindrical Fe1-xNix thin films, J. Opt. Adv. Mat., 6, pp.45-50, (2004)

[4] E. Hristoforou, "Magnetostrictive Delay Lines: Engineering Theory and Sensing Applications", Meas. Sci. & Technol., 14, p. R15-R47, (2003)

DOI: 10.1088/0957-0233/14/2/201

[5] E. Hristoforou, Magnetic Effects in Physical Sensor Design, J. Opt. Adv. Mat., 4, pp.245-260, (2002)

[6] E. Hristoforou and D. Niarchos, Mechanical Sensors Based on Re-Entrant Flux Reversal, IEEE Trans. Mag., 28, pp.2190-2192, (1992)

DOI: 10.1109/20.179439

[7] C. Petridis, I Petrou, PD Dimitropoulos, E Hristoforou, Determining appropriate magnetic core properties for a new type of flux-gate like sensor, Sensor Letters, 5, pp.98-101, (2007)

DOI: 10.1166/sl.2007.072

[8] I. Petrou, P. Skafidas, E. Hristoforou, Electronic toll and road traffic monitoring system using 3-D field AMR sensors, Sensor Letters, 11, pp.91-95, (2013)

DOI: 10.1166/sl.2013.2787

[9] E. Hristoforou, New monolithic three dimensional field sensors with high sensitivity, J. Opt. Adv. Mat., 8, pp.1691-1697, (2006)

[10] C. Petridis, A. Ktena, E. Laskaris, PD Dimitropoulos, E Hristoforou, Ni-Fe thin film coated Cu wires for field sensing applications, Sensor Letters, 5, pp.93-97, (2007)

DOI: 10.1166/sl.2007.071

[11] C. Petridis, P. D. Dimitropoulos, E. Hristoforou, New Magnetic Field Sensor Based on Combined Flux-Gate/Hall-Effect Arrangement, IEEE Sensors Journal, 9, pp.128-134, (2009)

DOI: 10.1109/jsen.2008.2011083

[12] E. Hristoforou, H. Hauser and PD Dimitropoulos, On a New Principle of Smart Multi-Sensor Based on Magnetic Effects, IEEE Sensors, 6, pp.372-379, (2006)

DOI: 10.1109/jsen.2005.859781

[13] Holmes, J. J., Reduction of a ship's magnetic field signatures Synthesis Lectures on Computational Electromagnetics, 3(1), pages 68, (2008)

[14] Information on http://www.emcos.com/Naval-EMC-Simulations

[15] E. Hristoforou, New Position Sensor Based on the Magnetostrictive Delay Line Principle, Sensor Letters, 7, pp.303-309, (2009)

DOI: 10.1166/sl.2009.1071

[16] Petrou, J., Skafidas, P., & Hristoforou, E. (2013). Electronic toll and road traffic monitoring system using 3-D field AMR sensors, Sensor Letters, 11(1), p.91 – 95

DOI: 10.1166/sl.2013.2787

[17] Haykin, S. Neural networks: A Comprehensive Foundation, 2nd ed, Prentice-Hall, 1999.

[18] Messai, N., Thomas, P., Lefebvre, D., & Moudni, A. E. Neural networks for local monitoring of traffic magnetic sensors. Control Engineering Practice, 2005, 13(1), pp.67-80.

DOI: 10.1016/j.conengprac.2004.02.005

[19] Fateh, B., Modeling, simulation and optimization of a microcoil for MRI. Computational Engineering, University of Rostock, Germany, (2006)

[20] Demuth, H. Neural network toolbox for use with MATLAB R2013a: User's guide, MathWorks, (2013)