Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks

Tuan Luong; Sungwon Seo; Kihyeon Kim; Jeongmin Jeon; Ja Choon Koo; Hyouk Ryeol Choi; Hyungpil Moon

doi:10.1007/978-3-030-91892-7_56

Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks

Tuan Luong, Sungwon Seo, Kihyeon Kim, Jeongmin Jeon, Ja Choon Koo, Hyouk Ryeol Choi, Hyungpil Moon

Department of Mechanical Engineering

Sungkyunkwan University

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

2 Scopus citations

Abstract

Twisted-coiled polymer actuators (TCAs) are a new promising type of artificial muscles that is light-weight, low-cost and provides high stroke. This paper presents a dynamic model based on long short term memory (LSTM) networks to predict the nonlinear behavior of an antagonistic joint driven by the hybrid TCA bundle made from Spandex and nylon fibers. Different from our previous work, the current model considers pre-strains of TCAs as its inputs, therefore, any change in pre-strains of both TCA actuators will not require new data and training. It was verified from the experimental results that when there are pre-strain changes, the present model has better performance in capturing the system’s behavior compared with that of the previous one. The proposed LSTM based model can estimate the joint angle with the mean error of 0.06^∘ compared with that of 1.57^∘ using the previous one within the working range of 30 % of the TCA.

Original language	English
Title of host publication	Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021
Editors	Nguyen Van Khang, Nguyen Quang Hoang, Marco Ceccarelli
Publisher	Springer Science and Business Media B.V.
Pages	590-599
Number of pages	10
ISBN (Print)	9783030918910
DOIs	https://doi.org/10.1007/978-3-030-91892-7_56
State	Published - 2022
Event	6th IFToMM Asian Mechanisms and Machine Science Conference, Asian MMS 2021 - Virtual, Online Duration: 15 Dec 2021 → 18 Dec 2021

Publication series

Name	Mechanisms and Machine Science
Volume	113 MMS
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	6th IFToMM Asian Mechanisms and Machine Science Conference, Asian MMS 2021
City	Virtual, Online
Period	15/12/21 → 18/12/21

Keywords

Antagonistic mechanism
Hysteresis modeling
Long short term memory
Twisted-coiled actuators

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-91892-7_56

Cite this

Luong, T., Seo, S., Kim, K., Jeon, J., Koo, J. C., Choi, H. R., & Moon, H. (2022). Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks. In N. V. Khang, N. Q. Hoang, & M. Ceccarelli (Eds.), Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021 (pp. 590-599). (Mechanisms and Machine Science; Vol. 113 MMS). Springer Science and Business Media B.V.. https://doi.org/10.1007/978-3-030-91892-7_56

Luong, Tuan ; Seo, Sungwon ; Kim, Kihyeon et al. / Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks. Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021. editor / Nguyen Van Khang ; Nguyen Quang Hoang ; Marco Ceccarelli. Springer Science and Business Media B.V., 2022. pp. 590-599 (Mechanisms and Machine Science).

@inproceedings{8f57449e9e554b789c871cfc260f4d7d,

title = "Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks",

abstract = "Twisted-coiled polymer actuators (TCAs) are a new promising type of artificial muscles that is light-weight, low-cost and provides high stroke. This paper presents a dynamic model based on long short term memory (LSTM) networks to predict the nonlinear behavior of an antagonistic joint driven by the hybrid TCA bundle made from Spandex and nylon fibers. Different from our previous work, the current model considers pre-strains of TCAs as its inputs, therefore, any change in pre-strains of both TCA actuators will not require new data and training. It was verified from the experimental results that when there are pre-strain changes, the present model has better performance in capturing the system{\textquoteright}s behavior compared with that of the previous one. The proposed LSTM based model can estimate the joint angle with the mean error of 0.06∘ compared with that of 1.57∘ using the previous one within the working range of 30 \% of the TCA.",

keywords = "Antagonistic mechanism, Hysteresis modeling, Long short term memory, Twisted-coiled actuators",

author = "Tuan Luong and Sungwon Seo and Kihyeon Kim and Jeongmin Jeon and Koo, \{Ja Choon\} and Choi, \{Hyouk Ryeol\} and Hyungpil Moon",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 6th IFToMM Asian Mechanisms and Machine Science Conference, Asian MMS 2021 ; Conference date: 15-12-2021 Through 18-12-2021",

year = "2022",

doi = "10.1007/978-3-030-91892-7\_56",

language = "English",

isbn = "9783030918910",

series = "Mechanisms and Machine Science",

publisher = "Springer Science and Business Media B.V.",

pages = "590--599",

editor = "Khang, \{Nguyen Van\} and Hoang, \{Nguyen Quang\} and Marco Ceccarelli",

booktitle = "Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021",

address = "Netherlands",

}

Luong, T, Seo, S, Kim, K, Jeon, J, Koo, JC , Choi, HR & Moon, H 2022, Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks. in NV Khang, NQ Hoang & M Ceccarelli (eds), Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021. Mechanisms and Machine Science, vol. 113 MMS, Springer Science and Business Media B.V., pp. 590-599, 6th IFToMM Asian Mechanisms and Machine Science Conference, Asian MMS 2021, Virtual, Online, 15/12/21. https://doi.org/10.1007/978-3-030-91892-7_56

Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks. / Luong, Tuan; Seo, Sungwon; Kim, Kihyeon et al.
Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021. ed. / Nguyen Van Khang; Nguyen Quang Hoang; Marco Ceccarelli. Springer Science and Business Media B.V., 2022. p. 590-599 (Mechanisms and Machine Science; Vol. 113 MMS).

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

TY - GEN

T1 - Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks

AU - Luong, Tuan

AU - Seo, Sungwon

AU - Kim, Kihyeon

AU - Jeon, Jeongmin

AU - Koo, Ja Choon

AU - Choi, Hyouk Ryeol

AU - Moon, Hyungpil

PY - 2022

Y1 - 2022

N2 - Twisted-coiled polymer actuators (TCAs) are a new promising type of artificial muscles that is light-weight, low-cost and provides high stroke. This paper presents a dynamic model based on long short term memory (LSTM) networks to predict the nonlinear behavior of an antagonistic joint driven by the hybrid TCA bundle made from Spandex and nylon fibers. Different from our previous work, the current model considers pre-strains of TCAs as its inputs, therefore, any change in pre-strains of both TCA actuators will not require new data and training. It was verified from the experimental results that when there are pre-strain changes, the present model has better performance in capturing the system’s behavior compared with that of the previous one. The proposed LSTM based model can estimate the joint angle with the mean error of 0.06∘ compared with that of 1.57∘ using the previous one within the working range of 30 % of the TCA.

AB - Twisted-coiled polymer actuators (TCAs) are a new promising type of artificial muscles that is light-weight, low-cost and provides high stroke. This paper presents a dynamic model based on long short term memory (LSTM) networks to predict the nonlinear behavior of an antagonistic joint driven by the hybrid TCA bundle made from Spandex and nylon fibers. Different from our previous work, the current model considers pre-strains of TCAs as its inputs, therefore, any change in pre-strains of both TCA actuators will not require new data and training. It was verified from the experimental results that when there are pre-strain changes, the present model has better performance in capturing the system’s behavior compared with that of the previous one. The proposed LSTM based model can estimate the joint angle with the mean error of 0.06∘ compared with that of 1.57∘ using the previous one within the working range of 30 % of the TCA.

KW - Antagonistic mechanism

KW - Hysteresis modeling

KW - Long short term memory

KW - Twisted-coiled actuators

UR - https://www.scopus.com/pages/publications/85122031014

U2 - 10.1007/978-3-030-91892-7_56

DO - 10.1007/978-3-030-91892-7_56

M3 - Conference contribution

AN - SCOPUS:85122031014

SN - 9783030918910

T3 - Mechanisms and Machine Science

SP - 590

EP - 599

BT - Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021

A2 - Khang, Nguyen Van

A2 - Hoang, Nguyen Quang

A2 - Ceccarelli, Marco

PB - Springer Science and Business Media B.V.

T2 - 6th IFToMM Asian Mechanisms and Machine Science Conference, Asian MMS 2021

Y2 - 15 December 2021 through 18 December 2021

ER -

Luong T, Seo S, Kim K, Jeon J, Koo JC , Choi HR et al. Hysteresis Modeling of Twisted-Coiled Polymer Actuators Using Long Short Term Memory Networks. In Khang NV, Hoang NQ, Ceccarelli M, editors, Advances in Asian Mechanism and Machine Science - Proceedings of IFToMM Asian MMS 2021. Springer Science and Business Media B.V. 2022. p. 590-599. (Mechanisms and Machine Science). doi: 10.1007/978-3-030-91892-7_56