Abstract
In this paper, a random forest regression (RFR) is proposed to reconstruct the statistical characteristics of electric fields in perforated enclosures. The power balance method and a diffusion equation-based model have been applied to the analysis of such problems; however, they are unable to account for the statistical nonisotropy problem. To solve it, RFR is used to predict the variances of six basic electric fields, the real and imaginary parts of the three rectangular electric field components, in perforated enclosures under external excitation. Using the predicted variances, the probability density function to represent each basic electric field can be generated as they are assumed to obey normal distribution with zero mean value. Then the statistical characteristics of other electric fields can be calculated by an analytical method and Monte Carlo method. Using the proposed method relies on RFR, the overall statistical characteristics of electric fields in perforated enclosures with the electric dimensions less than ten times the wavelength can be accurately reconstructed. Using the predicted statistics, the practical electromagnetic compatibility problem, such as global shielding effectiveness of a perforated enclosure, can be evaluated in seconds.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Electromagnetic Compatibility
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
