Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk

Muhammad Imam Sudrajat; Muhammad Ammar Wibisono; Hermes José Loschi; Niek Moonen; Frank Leferink

doi:10.1109/EMCSI39492.2022.9889401

Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk

Muhammad Imam Sudrajat
, Muhammad Ammar Wibisono
, Hermes José Loschi
, Niek Moonen
, Frank Leferink

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

307 Downloads (Pure)

Abstract

Estimating crosstalk appropriately is very important in the process of mitigating electromagnetic interference. This study evaluates a black-box modeling technique named nonlinear autoregressive with exogenous inputs (NARX) on crosstalk modeling application, especially crosstalk due to random pulse width modulation. The model is developed using the input and output data from the measurement as regressor inputs. For validation, the mean squared error of this model is calculated by comparing the model output with the real measurement output. For evaluation, the model performance also was compared to a Spice-based SACAMOS model. Although less flexible than the Spice model, NARX model can represent the signal on the victim cable well with a small mean squared error value.

Original language	English
Title of host publication	2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI)
Place of Publication	Spokane, USA
Publisher	IEEE
Pages	210-215
Number of pages	6
ISBN (Electronic)	978-1-6654-0929-2, 978-1-6654-0928-5
ISBN (Print)	978-1-6654-0930-8
DOIs	https://doi.org/10.1109/EMCSI39492.2022.9889401
Publication status	Published - 26 Sept 2022
Event	IEEE International Symposium On Electromagnetic Compatibility, Signal & Power Integrity, EMCSI 2022 - Spokane , United States Duration: 1 Aug 2022 → 5 Aug 2022

Conference

Conference	IEEE International Symposium On Electromagnetic Compatibility, Signal & Power Integrity, EMCSI 2022
Abbreviated title	EMCSI 2022
Country/Territory	United States
City	Spokane
Period	1/08/22 → 5/08/22

Access to Document

10.1109/EMCSI39492.2022.9889401

Pure_Evaluation of Nonlinear ARX systemAccepted author version, 829 KB

Cite this

@inproceedings{0c0f18816f62441cb6125915da715218,

title = "Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk",

abstract = "Estimating crosstalk appropriately is very important in the process of mitigating electromagnetic interference. This study evaluates a black-box modeling technique named nonlinear autoregressive with exogenous inputs (NARX) on crosstalk modeling application, especially crosstalk due to random pulse width modulation. The model is developed using the input and output data from the measurement as regressor inputs. For validation, the mean squared error of this model is calculated by comparing the model output with the real measurement output. For evaluation, the model performance also was compared to a Spice-based SACAMOS model. Although less flexible than the Spice model, NARX model can represent the signal on the victim cable well with a small mean squared error value.",

author = "Sudrajat, \{Muhammad Imam\} and Wibisono, \{Muhammad Ammar\} and Loschi, \{Hermes Jos{\'e}\} and Niek Moonen and Frank Leferink",

note = "Funding Information: This project has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation program under the Marie Sk{\l}odowska-Curie grant agreement No 812391. Funding Information: This project has received funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 812391 Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE International Symposium On Electromagnetic Compatibility, Signal \& Power Integrity, EMCSI 2022, EMCSI 2022 ; Conference date: 01-08-2022 Through 05-08-2022",

year = "2022",

month = sep,

day = "26",

doi = "10.1109/EMCSI39492.2022.9889401",

language = "English",

isbn = "978-1-6654-0930-8",

pages = "210--215",

booktitle = "2022 IEEE International Symposium on Electromagnetic Compatibility \& Signal/Power Integrity (EMCSI)",

publisher = "IEEE",

address = "United States",

}

Sudrajat, MI, Wibisono, MA, Loschi, HJ, Moonen, N & Leferink, F 2022, Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk. in 2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI). IEEE, Spokane, USA, pp. 210-215, IEEE International Symposium On Electromagnetic Compatibility, Signal & Power Integrity, EMCSI 2022, Spokane , Washington, United States, 1/08/22. https://doi.org/10.1109/EMCSI39492.2022.9889401

Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk. / Sudrajat, Muhammad Imam; Wibisono, Muhammad Ammar; Loschi, Hermes José et al.
2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI). Spokane, USA: IEEE, 2022. p. 210-215.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk

AU - Sudrajat, Muhammad Imam

AU - Wibisono, Muhammad Ammar

AU - Loschi, Hermes José

AU - Moonen, Niek

AU - Leferink, Frank

N1 - Funding Information: This project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No 812391. Funding Information: This project has received funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 812391 Publisher Copyright: © 2022 IEEE.

PY - 2022/9/26

Y1 - 2022/9/26

N2 - Estimating crosstalk appropriately is very important in the process of mitigating electromagnetic interference. This study evaluates a black-box modeling technique named nonlinear autoregressive with exogenous inputs (NARX) on crosstalk modeling application, especially crosstalk due to random pulse width modulation. The model is developed using the input and output data from the measurement as regressor inputs. For validation, the mean squared error of this model is calculated by comparing the model output with the real measurement output. For evaluation, the model performance also was compared to a Spice-based SACAMOS model. Although less flexible than the Spice model, NARX model can represent the signal on the victim cable well with a small mean squared error value.

AB - Estimating crosstalk appropriately is very important in the process of mitigating electromagnetic interference. This study evaluates a black-box modeling technique named nonlinear autoregressive with exogenous inputs (NARX) on crosstalk modeling application, especially crosstalk due to random pulse width modulation. The model is developed using the input and output data from the measurement as regressor inputs. For validation, the mean squared error of this model is calculated by comparing the model output with the real measurement output. For evaluation, the model performance also was compared to a Spice-based SACAMOS model. Although less flexible than the Spice model, NARX model can represent the signal on the victim cable well with a small mean squared error value.

U2 - 10.1109/EMCSI39492.2022.9889401

DO - 10.1109/EMCSI39492.2022.9889401

M3 - Conference contribution

SN - 978-1-6654-0930-8

SP - 210

EP - 215

BT - 2022 IEEE International Symposium on Electromagnetic Compatibility & Signal/Power Integrity (EMCSI)

PB - IEEE

CY - Spokane, USA

T2 - IEEE International Symposium On Electromagnetic Compatibility, Signal & Power Integrity, EMCSI 2022

Y2 - 1 August 2022 through 5 August 2022

ER -

Evaluation of Nonlinear ARX System Identification Technique on Modeling Crosstalk

Abstract

Conference

Access to Document

Fingerprint

Cite this