Details
| Original language | English |
|---|---|
| Title of host publication | IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society |
| Publisher | IEEE Computer Society |
| ISBN (electronic) | 9781665435543 |
| ISBN (print) | 978-1-6654-0256-9 |
| Publication status | Published - 2021 |
| Event | 47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021 - Toronto, Canada Duration: 13 Oct 2021 → 16 Oct 2021 |
Publication series
| Name | Proceedings of the Annual Conference of the IEEE Industrial Electronics Society |
|---|---|
| ISSN (Print) | 1553-572X |
| ISSN (electronic) | 2577-1647 |
Abstract
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.
Keywords
- emc, lstm, modeling, neural network, nonlinear filter, prediction, python, simulation, spectrum, spice, time series
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society. IEEE Computer Society, 2021. (Proceedings of the Annual Conference of the IEEE Industrial Electronics Society).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
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 -