Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame

Xue Qi; Wei Jia Shi; Bo Zhao; Jiu Bin Tan

doi:10.1109/SPAWDA48812.2019.9019229

Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame

Xue Qi
, Wei Jia Shi^*
, Bo Zhao
, Jiu Bin Tan

^*Corresponding author for this work

School of Instrumentation Science and Engineering

Harbin Institute of Technology

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

Abstract

Piezoceramic actuators have been already applied in precision positioning in terms of simple and compact structure, free from noise, and high theoretical positioning resolution. However, the hysteresis characteristic limits the further improvement of positioning accuracy. Nowadays neural networks (NNs) have revolutionized progress in the identification and global linearization tasks, which makes it potential to employ deep learning in identifying hysteresis model of piezoceramic actuators in the linear frame. This paper aims at achieving the identification of the hysteresis model by means of NNs. Based on the Preisach model, datasets are obtained in Matlab. Identification of nonlinear coordinates is accomplished by the auto-encoder afterwards. As a result, weights of the various network branches are computed. Comparing the hysteresis model displacement output with the NNs reconstruction, it is found that the curves are basically consistent. The experimental results confirm the correctness of this method, which is of great significance for analysis and control of nonlinear systems.

Original language	English
Title of host publication	Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019
Editors	Jinxi Liu, Xue-Qian Fang, Guoquan Nie
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728152530
DOIs	https://doi.org/10.1109/SPAWDA48812.2019.9019229
State	Published - Nov 2019
Event	14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019 - Shijiazhuang, China Duration: 1 Nov 2019 → 4 Nov 2019

Publication series

Name	Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019

Conference

Conference	14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019
Country/Territory	China
City	Shijiazhuang
Period	1/11/19 → 4/11/19

Keywords

Neural networks
Piezoceramic actuators
Precision positioning
Preisach model

Access to Document

10.1109/SPAWDA48812.2019.9019229

Cite this

Qi, X., Shi, W. J., Zhao, B., & Tan, J. B. (2019). Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame. In J. Liu, X.-Q. Fang, & G. Nie (Eds.), Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019 Article 9019229 (Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SPAWDA48812.2019.9019229

Qi, Xue ; Shi, Wei Jia ; Zhao, Bo et al. / Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame. Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019. editor / Jinxi Liu ; Xue-Qian Fang ; Guoquan Nie. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019).

@inproceedings{055e45b580104270be711f98f4651791,

title = "Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame",

abstract = "Piezoceramic actuators have been already applied in precision positioning in terms of simple and compact structure, free from noise, and high theoretical positioning resolution. However, the hysteresis characteristic limits the further improvement of positioning accuracy. Nowadays neural networks (NNs) have revolutionized progress in the identification and global linearization tasks, which makes it potential to employ deep learning in identifying hysteresis model of piezoceramic actuators in the linear frame. This paper aims at achieving the identification of the hysteresis model by means of NNs. Based on the Preisach model, datasets are obtained in Matlab. Identification of nonlinear coordinates is accomplished by the auto-encoder afterwards. As a result, weights of the various network branches are computed. Comparing the hysteresis model displacement output with the NNs reconstruction, it is found that the curves are basically consistent. The experimental results confirm the correctness of this method, which is of great significance for analysis and control of nonlinear systems.",

keywords = "Neural networks, Piezoceramic actuators, Precision positioning, Preisach model",

author = "Xue Qi and Shi, \{Wei Jia\} and Bo Zhao and Tan, \{Jiu Bin\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019 ; Conference date: 01-11-2019 Through 04-11-2019",

year = "2019",

month = nov,

doi = "10.1109/SPAWDA48812.2019.9019229",

language = "英语",

series = "Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Jinxi Liu and Xue-Qian Fang and Guoquan Nie",

booktitle = "Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019",

address = "美国",

}

Qi, X, Shi, WJ , Zhao, B & Tan, JB 2019, Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame. in J Liu, X-Q Fang & G Nie (eds), Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019., 9019229, Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019, Institute of Electrical and Electronics Engineers Inc., 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019, Shijiazhuang, China, 1/11/19. https://doi.org/10.1109/SPAWDA48812.2019.9019229

Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame. / Qi, Xue; Shi, Wei Jia ; Zhao, Bo et al.
Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019. ed. / Jinxi Liu; Xue-Qian Fang; Guoquan Nie. Institute of Electrical and Electronics Engineers Inc., 2019. 9019229 (Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019).

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

TY - GEN

T1 - Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame

AU - Qi, Xue

AU - Shi, Wei Jia

AU - Zhao, Bo

AU - Tan, Jiu Bin

PY - 2019/11

Y1 - 2019/11

N2 - Piezoceramic actuators have been already applied in precision positioning in terms of simple and compact structure, free from noise, and high theoretical positioning resolution. However, the hysteresis characteristic limits the further improvement of positioning accuracy. Nowadays neural networks (NNs) have revolutionized progress in the identification and global linearization tasks, which makes it potential to employ deep learning in identifying hysteresis model of piezoceramic actuators in the linear frame. This paper aims at achieving the identification of the hysteresis model by means of NNs. Based on the Preisach model, datasets are obtained in Matlab. Identification of nonlinear coordinates is accomplished by the auto-encoder afterwards. As a result, weights of the various network branches are computed. Comparing the hysteresis model displacement output with the NNs reconstruction, it is found that the curves are basically consistent. The experimental results confirm the correctness of this method, which is of great significance for analysis and control of nonlinear systems.

AB - Piezoceramic actuators have been already applied in precision positioning in terms of simple and compact structure, free from noise, and high theoretical positioning resolution. However, the hysteresis characteristic limits the further improvement of positioning accuracy. Nowadays neural networks (NNs) have revolutionized progress in the identification and global linearization tasks, which makes it potential to employ deep learning in identifying hysteresis model of piezoceramic actuators in the linear frame. This paper aims at achieving the identification of the hysteresis model by means of NNs. Based on the Preisach model, datasets are obtained in Matlab. Identification of nonlinear coordinates is accomplished by the auto-encoder afterwards. As a result, weights of the various network branches are computed. Comparing the hysteresis model displacement output with the NNs reconstruction, it is found that the curves are basically consistent. The experimental results confirm the correctness of this method, which is of great significance for analysis and control of nonlinear systems.

KW - Neural networks

KW - Piezoceramic actuators

KW - Precision positioning

KW - Preisach model

UR - https://www.scopus.com/pages/publications/85082170119

U2 - 10.1109/SPAWDA48812.2019.9019229

DO - 10.1109/SPAWDA48812.2019.9019229

M3 - 会议稿件

AN - SCOPUS:85082170119

T3 - Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019

BT - Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019

A2 - Liu, Jinxi

A2 - Fang, Xue-Qian

A2 - Nie, Guoquan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019

Y2 - 1 November 2019 through 4 November 2019

ER -

Qi X, Shi WJ , Zhao B, Tan JB. Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame. In Liu J, Fang XQ, Nie G, editors, Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9019229. (Proceedings of the 2019 14th Symposium on Piezoelectricity, Acoustic Waves and Device Applications, SPAWDA 2019). doi: 10.1109/SPAWDA48812.2019.9019229

Deep Learning for Identifying Hysteresis Models of Piezoceramic Actuators in the Linear Frame

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this