Postprocessing of Near-Field Measurement Based on Neural Networks

This paper presents postprocessing based on neural network (NN) models to reconstruct the magnetic near-field profile with an improved spatial resolution for one or different frequencies. The models aim at decreasing the time required to perform near-field electromagnetic compatibility (EMC) measurements. The multilayer perceptron (MLP) NNs are used to determine the magnetic near field radiated by passive devices and power electronics components. An optimization method, called the split-sample method, is implemented to determine the structures of the NN. The results obtained with the proposed method are compared with the measurement results. A graphic interface (GUI) is created to simplify the utilization of the developed NN models.

[1]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[2]  Caron Green,et al.  Non-destructive evaluation using neural networks , 1995 .

[3]  Masato Enokizono,et al.  Neural network models of eddy current multi-frequency system for nondestructive testing , 2000 .

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  B. Mazari,et al.  Applications of the Near-Field Techniques in EMC Investigations , 2007, IEEE Transactions on Electromagnetic Compatibility.

[6]  M. Ribo,et al.  A genetic algorithm based method for source identification and far-field radiated emissions prediction from near-field measurements for PCB characterization , 2001 .

[7]  J. Schoukens,et al.  The interpolated fast Fourier transform: a comparative study , 1991 .

[8]  B. Mazari,et al.  Overview of emission and susceptibility investigation and modeling with near-field measurements , 2008 .

[9]  Lionel Pichon,et al.  Characterization of radiated emissions from power electronic devices : synthesis of an equivalent model from near-field measurement , 2007 .

[10]  Moncef Kadi,et al.  Characterization of electromagnetic fields close to microwave devices using electric dipole probes , 2008 .

[11]  R. R. Goulette.  The Measurement Of Radiated Emissions From Integrated Circuits , 1992, International Symposium on Electromagnetic Compatibility.

[12]  F. Lafon,et al.  Prediction of the field radiated at one meter from PCB's and microprocessors from near EM field cartography , 2003, 2003 IEEE International Symposium on Electromagnetic Compatibility, 2003. EMC '03..

[13]  S. Bendhia,et al.  Characterisation of electromagnetic susceptibility of integrated circuits using near-field scan , 2007 .

[14]  Stavros M. Panas,et al.  Impedance inversion in eddy current testing of layered planar structures via neural networks , 1997 .

[15]  D. Baudry,et al.  Near-field techniques for detecting EMI sources , 2004, 2004 International Symposium on Electromagnetic Compatibility (IEEE Cat. No.04CH37559).

[16]  S. Criel,et al.  Near-field scanner for the accurate characterization of electromagnetic fields in the close vicinity of electronic devices and systems , 1996, Quality Measurement: The Indispensable Bridge between Theory and Reality (No Measurements? No Science! Joint Conference - 1996: IEEE Instrumentation and Measurement Technology Conference and IMEKO Tec.

[17]  B. Mazari,et al.  Modeling Magnetic Radiations of Electronic Circuits Using Near-Field Scanning Method , 2007, IEEE Transactions on Electromagnetic Compatibility.