The PZMI and Artificel Neural Network to identify the electromagnetic radiation sources

Saidi, Sofiene; Slama, Jaleleddine Ben Hadj

doi:10.1109/melcon.2012.6196461

Cited by 6 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then the scan-window algorithm moves up the window until identifying two dipole parameters: the type (electric or magnetic) and the position (X d , Y d ) [14]. The other parameters (magnetic moment M d and the orientation θ and ϕ) will be identified by the GA.…”

Section: The Improved Electromagnetic Inverse Methodsmentioning

confidence: 99%

“…Firstly, we define a suitable window on which we scan the NF cartography and then we use the scanned cartography to search a local dipole. The study [14] shows that the choice of the scan window depends on the measured cartography size, resolution and height. We suppose that in our scan window, we have only one dipole at maximum.…”

Section: The Scan-window Choicementioning

confidence: 99%

“…Referring to [14], we have selected the optimal size of the scan-window. Consequently, we have chosen the measured cartography equal to 10 × 10 cm at an h = 2 cm height and with a measurement resolution equal to 2 mm ( Figure 5).…”

Section: The Scan-window Choicementioning

confidence: 99%

See 2 more Smart Citations

Improving Convergence Time of the Electromagnetic Inverse Method Based on Genetic Algorithm Using the Pzmi and Neural Network

Saidi¹,

Slama²

2013

PIER B

View full text Add to dashboard Cite

Abstract-In this paper we present a methodology to guarantee the convergence of the electromagnetic inverse method. This method is applied to electromagnetic compatibility (EMC) in order to overcome the difficulties of measuring the radiated electromagnetic field and to reduce the cost of the EMC analysis. It consists in using Genetic Algorithms (GA) to identify a model that will be used to estimate the electric and magnetic field radiated by the device under test. This method is based on the recognition of the equivalent radiation sources using the Near Field (NF) cartography radiated by the device. Our contribution in this field is to improve the ability and the convergence of the electromagnetic inverse method by using the Pseudo Zernike Moment Invariant (PZMI) descriptor and the Artificial Neural Network (ANN). The validation of the proposed method is performed using the NF emitted by known electric and magnetic dipoles. Our results have proved that the proposed method guarantees the convergence of the electromagnetic inverse method and that the convergence speeds up while retaining all the other performances.

show abstract

Section: The Improved Electromagnetic Inverse Methodsmentioning

confidence: 99%

Section: The Scan-window Choicementioning

confidence: 99%

See 1 more Smart Citation

Improving Convergence Time of the Electromagnetic Inverse Method Based on Genetic Algorithm Using the Pzmi and Neural Network

Saidi¹,

Slama²

2013

PIER B

View full text Add to dashboard Cite

show abstract

“…The proposed hybrid process has the advantage to identify rectangular structures. In [3], authors applied the Artificial Network and the Pseudo Zernike Moment Invariant and presented a parametric study to evaluate the influence of the different parameters such as measurement resolution and height. This methodology was improved, in [4], by use of GA in the FD in order to accelerate the convergence of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

A full time domain methodology based on near field time reversal for equivalent source identification

Hedia

Zitouna

Slama

et al. 2018

2018 IEEE International Symposium on Electromagnetic Compatibility and 2018 IEEE Asia-Pacific Symposium on Electromagnetic Comp

View full text Add to dashboard Cite

This paper deals with magnetic source characterization in time domain. The basic idea is to solve the inverse problem using the measured near field radiation cartography. In order to ensure the identification procedure, the Time Reversal (TR) technique is used. This procedure allows both the spatial and temporal focusing determination by forcing waves to virtually converge to their initial source. The originality of the proposed methodology is to present a full time domain study of a magnetic source reconstruction. Indeed, this approach is particularly suitable for structures that emit non-sinusoidal radiations such as power electronic systems. First, the Electromagnetic Time Reversal (EMTR) basis are introduced. Then a simulation case study is discussed. Finally, results from an experiment test are presented to verify the proposed methodology. The measured results are in good agreement with the calculated electromagnetic fields. The experimental validation shows that compared to other identification techniques, especially those developed in the frequency domain, the proposed approach is more efficient and simple.

show abstract

“…For instance, authors in [2][3] have used different powerful numerical techniques in order to recognize the radiating sources existing in a DC-DC converter. A parametric study was also presented in [4] to evaluate the influence of the different configurations parameters such as height measurement and resolution. Nevertheless, the frequency method still not efficient and limited in terms of time and resources especially when applied to the power electronic circuits that manifest important perturbations in a wide frequency band [2].…”

Section: Introductionmentioning

confidence: 99%

Electromagnetic Time Reversal for Radiating Source Identification in Time Domain

Hedia

Zitouna

Slama

et al. 2018

2018 15th International Multi-Conference on Systems, Signals &Amp; Devices (SSD)

View full text Add to dashboard Cite

This paper presents a study on the characterization of electromagnetic near field radiation in the time domain. The proposed methodology affords a radiation model based on the electromagnetic inverse method using analytical expressions of the equivalent dipoles. The identification procedure is conducted by the Time Reversal technique (TR). The advantage of this process is focusing a field in both time and space. The main goal of this paper is to investigate the use of the Electromagnetic Time Reversal (EMTR) method in the time domain. First, the EMTR principle is presented. The characterization of the time domain magnetic field distribution is then developed. The radiating source localization and the excitation signal's shape were successfully defined. In addition, the calculated distribution cartography of the magnetic field is compared to the reconstructed cartography. The obtained results show the effectiveness of the proposed approach.

show abstract

The PZMI and Artificel Neural Network to identify the electromagnetic radiation sources

Cited by 6 publications

References 5 publications

Improving Convergence Time of the Electromagnetic Inverse Method Based on Genetic Algorithm Using the Pzmi and Neural Network

Improving Convergence Time of the Electromagnetic Inverse Method Based on Genetic Algorithm Using the Pzmi and Neural Network

A full time domain methodology based on near field time reversal for equivalent source identification

Electromagnetic Time Reversal for Radiating Source Identification in Time Domain

Contact Info

Product

Resources

About