TY - GEN

T1 - An estimation method of magnetic coupling coefficient between two microstrip lines using machine leaning of near field information

AU - Sato, Yusuke

AU - Muroga, Sho

AU - Kamozawa, Hidefumi

AU - Tanaka, Motoshi

N1 - Publisher Copyright:
© 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - An estimation method of magnetic coupling coefficients between printed-circuit-board-level traces using a near field information was investigated. Parallel two microstrip lines (MSLs) with different distances between the lines were used as a test bench. The current flowing in a signal line and its return current was modeled as a simple one-turn equivalent loop current model. First, a one-dimensional convolutional neural network (CNN) for regression prediction was trained with the theoretical values of the magnetic near-field distribution generated from the loop current model. Next, the simulated magnetic near-field distributions above the parallel two MSLs at 1 GHz were input to the trained CNN to estimate the geometry of the loop current models. The magnetic coupling coefficient between MSLs is estimated through calculating the coupled magnetic flux between the estimated loop current models. The estimated results agreed with the simulation results within 10%, indicating the feasibility of the magnetic field coupling by the proposed method.

AB - An estimation method of magnetic coupling coefficients between printed-circuit-board-level traces using a near field information was investigated. Parallel two microstrip lines (MSLs) with different distances between the lines were used as a test bench. The current flowing in a signal line and its return current was modeled as a simple one-turn equivalent loop current model. First, a one-dimensional convolutional neural network (CNN) for regression prediction was trained with the theoretical values of the magnetic near-field distribution generated from the loop current model. Next, the simulated magnetic near-field distributions above the parallel two MSLs at 1 GHz were input to the trained CNN to estimate the geometry of the loop current models. The magnetic coupling coefficient between MSLs is estimated through calculating the coupled magnetic flux between the estimated loop current models. The estimated results agreed with the simulation results within 10%, indicating the feasibility of the magnetic field coupling by the proposed method.

KW - equivalent electromagnetic field models

KW - inductive coupling coefficient

KW - machine learning

KW - magnetic near-fields scanning

KW - microstrip line

UR - http://www.scopus.com/inward/record.url?scp=85172718994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85172718994&partnerID=8YFLogxK

U2 - 10.1109/INTERMAGShortPapers58606.2023.10228737

DO - 10.1109/INTERMAGShortPapers58606.2023.10228737

M3 - Conference contribution

AN - SCOPUS:85172718994

T3 - 2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023 - Proceedings

BT - 2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

Y2 - 15 May 2023 through 19 May 2023

ER -