TY - GEN

T1 - Neural Network Modeling of Nonlinear Filters for EMC Simulation in Discrete Time Domain

AU - Roche, Jan Philipp

AU - Friebe, Jens

AU - Niggemann, Oliver

N1 - Funding Information: Jens Friebe would like to acknowledge the funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany´s Excellence Strategy – EXC 2163/1 - Sustainable and Energy Efficient Aviation – Project-ID 390881007 and also by the Ministry of Science and Culture of Lower Saxony and the Volkswagen Foundation. The authors are responsible for the content of this publication

PY - 2021

Y1 - 2021

N2 - Optimization loops are often required for the improvement of function and electromagnetic compatibility (EMC) in a product development process. Such optimization can be realized either by simulations or high effort based measurements. The neural network approach is suitable to overcome typical issues of simulation programs like SPICE such as convergence problems and high computation time. This paper addresses a neural network modeling approach for nonlinear passive filters. Long Short-Term Memory (LSTM) networks are applied to model nonlinear passive filters. One measured and two simulated filter circuits are used as application examples. LSTMs are chosen by literature research as a suitable modeling approach. The neural network and training structure is defined by literature research and systematic experiments. The filter behaviors are basically modeled by the trained neural networks. But further improvements have to be done. It is shown that the corresponding voltage and current time series can be learned and predicted by the LSTM networks in their essential characteristics. These voltage and current time series can generally be used in further applications. A possible speed advantage of LSTM networks is also examined.

AB - Optimization loops are often required for the improvement of function and electromagnetic compatibility (EMC) in a product development process. Such optimization can be realized either by simulations or high effort based measurements. The neural network approach is suitable to overcome typical issues of simulation programs like SPICE such as convergence problems and high computation time. This paper addresses a neural network modeling approach for nonlinear passive filters. Long Short-Term Memory (LSTM) networks are applied to model nonlinear passive filters. One measured and two simulated filter circuits are used as application examples. LSTMs are chosen by literature research as a suitable modeling approach. The neural network and training structure is defined by literature research and systematic experiments. The filter behaviors are basically modeled by the trained neural networks. But further improvements have to be done. It is shown that the corresponding voltage and current time series can be learned and predicted by the LSTM networks in their essential characteristics. These voltage and current time series can generally be used in further applications. A possible speed advantage of LSTM networks is also examined.

KW - emc

KW - lstm

KW - modeling

KW - neural network

KW - nonlinear filter

KW - prediction

KW - python

KW - simulation

KW - spectrum

KW - spice

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85119484295&partnerID=8YFLogxK

U2 - 10.1109/iecon48115.2021.9589226

DO - 10.1109/iecon48115.2021.9589226

M3 - Conference contribution

AN - SCOPUS:85119484295

SN - 978-1-6654-0256-9

T3 - Proceedings of the Annual Conference of the IEEE Industrial Electronics Society

BT - IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society

PB - IEEE Computer Society

T2 - 47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021

Y2 - 13 October 2021 through 16 October 2021

ER -