Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


toledo1280698960.pdf (9.44 MB)

ETD Abstract Container

Abstract Header

Artificial Neural Network-Based Approaches for Modeling the Radiated Emissions from Printed Circuit Board Structures and Shields

Kvale, David Thomas
http://rave.ohiolink.edu/etdc/view?acc_num=toledo1280698960

Abstract Details

2010, Master of Science, University of Toledo, Electrical Engineering.
This thesis introduces a new modeling approach for efficient and accurate Electromagnetic Interference/Compatibility (EMI/EMC) analysis of electronic systems. Printed Circuit Boards’ (PCB) radiated emissions were investigated by varying the number of apertures on a shield, changing the locations of partially shielded PCB traces, changing the locations of PCB interconnects, and moving EMI sources within a shielding enclosure. The issue with EMC modeling is that given the complexity of solving Maxwell’s equations for a given PCB configuration, the best course for many engineers is to broadly follow design guidelines that are only true for a specific geometry for a specific solution frequency instead of solving Maxwell’s equations for a given problem. There are cases where the complexity of the PCB design and integrated circuits (IC) is so extensive, that it is impractical to have an exact solution of Maxwell’s equations (i.e., modeling a functioning populated server motherboard within a cavity). Typically, EMC revisions are made to PCB designs if the Device Under Test (DUT) does not pass regulation certification, which can be very costly and time consuming. This is one of many reasons why PCB designs are infrequently changed, or if they are changed, only small variations are made. In this thesis, it will be shown that Artificial Neural Networks (ANN) are capable of providing accurate, fast, and computationally light estimates for radiated emissions. One case study employs this computational tool to find an optimized location on a PCB for a trace interconnect. The significance of utilizing ANNs for optimization is that ANNs provide a fast and accurate tool for design as well as for estimating radiated emissions. However, given that ANNs are highly variable, many approaches to ANN creation are examined and evaluated for specific EMC examples. Since ANN models do not require detailed geometrical configurations of the PCB and cable structures under consideration, computational overhead requirements are significantly reduced as compared to electromagnetic and circuit tools. The robustness, efficiency, accuracy, and versatility of ANN models, as demonstrated in this thesis, are particularly useful in the electronics industry since most manufacturers prefer reusing circuits and PCB layouts in new products with minor modifications to the existing time-tested designs.
Vijay Devabhaktuni, Dr. (Committee Chair)
Daniel Georgiev, Dr. (Committee Member)
Roger King, Dr. (Committee Member)
111 p.
Electrical Engineering; Electromagnetism
Artifical Neural Networks; Radiated Emissions; Shielding Enclosures

Recommended Citations

Citations

  • Kvale, D. T. (2010). Artificial Neural Network-Based Approaches for Modeling the Radiated Emissions from Printed Circuit Board Structures and Shields [Master's thesis, University of Toledo]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1280698960

    APA Style (7th edition)

  • Kvale, David. Artificial Neural Network-Based Approaches for Modeling the Radiated Emissions from Printed Circuit Board Structures and Shields. 2010. University of Toledo, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=toledo1280698960.

    MLA Style (8th edition)

  • Kvale, David. "Artificial Neural Network-Based Approaches for Modeling the Radiated Emissions from Printed Circuit Board Structures and Shields." Master's thesis, University of Toledo, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1280698960

    Chicago Manual of Style (17th edition)

toledo1280698960
7,059
© 2010, all rights reserved.
This open access ETD is published by University of Toledo and OhioLINK.