A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks

Le Pei; Liyi Li; Jiaxi Liu; Zhenxing Cheng; Qingbo Guo; Hongchen Liu

doi:10.1109/IECON48115.2021.9589761

A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks

Le Pei
, Liyi Li
, Jiaxi Liu
, Zhenxing Cheng
, Qingbo Guo
, Hongchen Liu

School of Electrical Engineering and Automation

Harbin Institute of Technology
Harbin University of Science and Technology

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

3 Scopus citations

Abstract

Due to the skin effect, parameters of motor windings change over frequency. In order to solve the problem in traditional Kalman-filter based deadzone compensator that the performance is sensitive to parameter mismatch, a novel deadzone compensation scheme with high robustness is proposed. Firstly, a deadzone compensation scheme based on Kalman filter technology is presented, and motor parameter variation over frequency changes is studied. Secondly, the impact of motor parameter mismatch is analyzed, and the verification of the performance deterioration is done via computer simulation. Thirdly, an Adaline neural-network(NN) based robustness enhancement algorithm is proposed to analyze the current error components. The performance deterioration is compensated by using the analyzed results of the robustness enhancement algorithm. Finally, the robustness against parameter sensitivity of the proposed method under various parameter mismatch conditions is fully studied and verified.

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
DOIs	https://doi.org/10.1109/IECON48115.2021.9589761
State	Published - 13 Oct 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	IECON Proceedings (Industrial Electronics Conference)
Volume	2021-October

Conference

Conference	47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021
Country/Territory	Canada
City	Toronto
Period	13/10/21 → 16/10/21

Keywords

Adaline neural networks
Kalman filter
deadzone compensation
parameter mismatch
skin effect

Access to Document

10.1109/IECON48115.2021.9589761

Cite this

Pei, L., Li, L., Liu, J., Cheng, Z., Guo, Q., & Liu, H. (2021). A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks. In IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society (IECON Proceedings (Industrial Electronics Conference); Vol. 2021-October). IEEE Computer Society. https://doi.org/10.1109/IECON48115.2021.9589761

@inproceedings{bc5d29cda5514f09963116512e7e3d0b,

title = "A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks",

abstract = "Due to the skin effect, parameters of motor windings change over frequency. In order to solve the problem in traditional Kalman-filter based deadzone compensator that the performance is sensitive to parameter mismatch, a novel deadzone compensation scheme with high robustness is proposed. Firstly, a deadzone compensation scheme based on Kalman filter technology is presented, and motor parameter variation over frequency changes is studied. Secondly, the impact of motor parameter mismatch is analyzed, and the verification of the performance deterioration is done via computer simulation. Thirdly, an Adaline neural-network(NN) based robustness enhancement algorithm is proposed to analyze the current error components. The performance deterioration is compensated by using the analyzed results of the robustness enhancement algorithm. Finally, the robustness against parameter sensitivity of the proposed method under various parameter mismatch conditions is fully studied and verified.",

keywords = "Adaline neural networks, Kalman filter, deadzone compensation, parameter mismatch, skin effect",

author = "Le Pei and Liyi Li and Jiaxi Liu and Zhenxing Cheng and Qingbo Guo and Hongchen Liu",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021 ; Conference date: 13-10-2021 Through 16-10-2021",

year = "2021",

month = oct,

day = "13",

doi = "10.1109/IECON48115.2021.9589761",

language = "英语",

series = "IECON Proceedings (Industrial Electronics Conference)",

publisher = "IEEE Computer Society",

booktitle = "IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society",

address = "美国",

}

Pei, L, Li, L , Liu, J, Cheng, Z, Guo, Q & Liu, H 2021, A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks. in IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society. IECON Proceedings (Industrial Electronics Conference), vol. 2021-October, IEEE Computer Society, 47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021, Toronto, Canada, 13/10/21. https://doi.org/10.1109/IECON48115.2021.9589761

A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks. / Pei, Le; Li, Liyi ; Liu, Jiaxi et al.
IECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society. IEEE Computer Society, 2021. (IECON Proceedings (Industrial Electronics Conference); Vol. 2021-October).

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

TY - GEN

T1 - A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks

AU - Pei, Le

AU - Li, Liyi

AU - Liu, Jiaxi

AU - Cheng, Zhenxing

AU - Guo, Qingbo

AU - Liu, Hongchen

PY - 2021/10/13

Y1 - 2021/10/13

N2 - Due to the skin effect, parameters of motor windings change over frequency. In order to solve the problem in traditional Kalman-filter based deadzone compensator that the performance is sensitive to parameter mismatch, a novel deadzone compensation scheme with high robustness is proposed. Firstly, a deadzone compensation scheme based on Kalman filter technology is presented, and motor parameter variation over frequency changes is studied. Secondly, the impact of motor parameter mismatch is analyzed, and the verification of the performance deterioration is done via computer simulation. Thirdly, an Adaline neural-network(NN) based robustness enhancement algorithm is proposed to analyze the current error components. The performance deterioration is compensated by using the analyzed results of the robustness enhancement algorithm. Finally, the robustness against parameter sensitivity of the proposed method under various parameter mismatch conditions is fully studied and verified.

AB - Due to the skin effect, parameters of motor windings change over frequency. In order to solve the problem in traditional Kalman-filter based deadzone compensator that the performance is sensitive to parameter mismatch, a novel deadzone compensation scheme with high robustness is proposed. Firstly, a deadzone compensation scheme based on Kalman filter technology is presented, and motor parameter variation over frequency changes is studied. Secondly, the impact of motor parameter mismatch is analyzed, and the verification of the performance deterioration is done via computer simulation. Thirdly, an Adaline neural-network(NN) based robustness enhancement algorithm is proposed to analyze the current error components. The performance deterioration is compensated by using the analyzed results of the robustness enhancement algorithm. Finally, the robustness against parameter sensitivity of the proposed method under various parameter mismatch conditions is fully studied and verified.

KW - Adaline neural networks

KW - Kalman filter

KW - deadzone compensation

KW - parameter mismatch

KW - skin effect

UR - https://www.scopus.com/pages/publications/85119494516

U2 - 10.1109/IECON48115.2021.9589761

DO - 10.1109/IECON48115.2021.9589761

M3 - 会议稿件

AN - SCOPUS:85119494516

T3 - IECON Proceedings (Industrial Electronics Conference)

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 -

A Robust Deadzone Compensation Method against Parameter Variations based on Kalman Filter and Neural Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this