Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits

Dominik Zupan; Nikolaus Czepl; Daniel Kircher

doi:10.1109/SMACD55068.2022.9816240

Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits

Dominik Zupan^*, Nikolaus Czepl, Daniel Kircher

^*Korrespondierende/r Autor/-in für diese Arbeit

Institut für Elektronik (4390)

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

In this paper we present a framework to develop regression models that predict the behaviour of integrated circuits (ICs) when exposed to electromagnetic interference (EMI). To do so, we use techniques that are commonly used in artificial intelligence (AI) applications. We show, how to create data sets from simulation, how to split these into training and test data, and how to pre-process these. Further on, we explain which AI models are suited best for predicting changes due to EMI. We also elaborate the structure and complexity of these models with regard to the model’s capability to fit the training and test data. We implement this framework using the Tensorflow library in Python and explain its application on an example predicting the EMI induced offset voltage. Therefore, we provide the data sets as well as the source code of the framework.

Originalsprache	englisch
Titel	2022 International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2022)
Seitenumfang	4
ISBN (elektronisch)	978-1-6654-6703-2
DOIs	https://doi.org/10.1109/SMACD55068.2022.9816240
Publikationsstatus	Veröffentlicht - Juli 2022
Veranstaltung	18th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design: SMACD 2022 - Villasimius, Italien Dauer: 12 Juni 2022 → 15 Juni 2022

Konferenz

Konferenz	18th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design
Kurztitel	SMACD 2022
Land/Gebiet	Italien
Ort	Villasimius
Zeitraum	12/06/22 → 15/06/22

Zugriff auf Dokument

10.1109/SMACD55068.2022.9816240

Dieses zitieren

Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits. / Zupan, Dominik ; Czepl, Nikolaus ; Kircher, Daniel.
2022 International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2022). 2022.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Zupan, D , Czepl, N & Kircher, D 2022, Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits. in 2022 International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2022). 18th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design, Villasimius, Italien, 12/06/22. https://doi.org/10.1109/SMACD55068.2022.9816240

@inproceedings{6f65b94dc925428598502c3611036a29,

title = "Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits",

abstract = "In this paper we present a framework to develop regression models that predict the behaviour of integrated circuits (ICs) when exposed to electromagnetic interference (EMI). To do so, we use techniques that are commonly used in artificial intelligence (AI) applications. We show, how to create data sets from simulation, how to split these into training and test data, and how to pre-process these. Further on, we explain which AI models are suited best for predicting changes due to EMI. We also elaborate the structure and complexity of these models with regard to the model{\textquoteright}s capability to fit the training and test data. We implement this framework using the Tensorflow library in Python and explain its application on an example predicting the EMI induced offset voltage. Therefore, we provide the data sets as well as the source code of the framework.",

keywords = "electromagnetic interference, EMI induced offset, prediction, neural network, differential amplifier stage, artificial intelligence",

author = "Dominik Zupan and Nikolaus Czepl and Daniel Kircher",

year = "2022",

month = jul,

doi = "10.1109/SMACD55068.2022.9816240",

language = "English",

booktitle = "2022 International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2022)",

note = "18th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design : SMACD 2022, SMACD 2022 ; Conference date: 12-06-2022 Through 15-06-2022",

}

TY - GEN

T1 - Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits

AU - Zupan, Dominik

AU - Czepl, Nikolaus

AU - Kircher, Daniel

PY - 2022/7

Y1 - 2022/7

N2 - In this paper we present a framework to develop regression models that predict the behaviour of integrated circuits (ICs) when exposed to electromagnetic interference (EMI). To do so, we use techniques that are commonly used in artificial intelligence (AI) applications. We show, how to create data sets from simulation, how to split these into training and test data, and how to pre-process these. Further on, we explain which AI models are suited best for predicting changes due to EMI. We also elaborate the structure and complexity of these models with regard to the model’s capability to fit the training and test data. We implement this framework using the Tensorflow library in Python and explain its application on an example predicting the EMI induced offset voltage. Therefore, we provide the data sets as well as the source code of the framework.

AB - In this paper we present a framework to develop regression models that predict the behaviour of integrated circuits (ICs) when exposed to electromagnetic interference (EMI). To do so, we use techniques that are commonly used in artificial intelligence (AI) applications. We show, how to create data sets from simulation, how to split these into training and test data, and how to pre-process these. Further on, we explain which AI models are suited best for predicting changes due to EMI. We also elaborate the structure and complexity of these models with regard to the model’s capability to fit the training and test data. We implement this framework using the Tensorflow library in Python and explain its application on an example predicting the EMI induced offset voltage. Therefore, we provide the data sets as well as the source code of the framework.

KW - electromagnetic interference

KW - EMI induced offset

KW - prediction

KW - neural network

KW - differential amplifier stage

KW - artificial intelligence

U2 - 10.1109/SMACD55068.2022.9816240

DO - 10.1109/SMACD55068.2022.9816240

M3 - Conference paper

BT - 2022 International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2022)

T2 - 18th International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design

Y2 - 12 June 2022 through 15 June 2022

ER -

Framework for Developing Neural Network Regression Models Predicting the Influence of EMI on Integrated Circuits

Abstract

Konferenz

Zugriff auf Dokument

Fingerprint

Dieses zitieren