Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation

Diluka Patikiri Arachchige; Quan Zhou

doi:10.1109/MARSS58567.2023.10294154

Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation

Diluka Patikiri Arachchige
, Quan Zhou

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

55 Downloads (Pure)

Abstract

Shape morphing of liquid droplets is important for advances in both medical and industrial applications. However current manipulation techniques lack methods to control shapes other than elliptical-shaped droplets. Here we propose using Long Short-Term Memory (LSTM) based model to learn and predict the evolution of the shape of a non-magnetic liquid droplet at an air-ferrofluid interface deformed with programmed sequential actuation of electromagnets. The resulting droplet shapes can be convex or concave. We can also predict the actuation sequences for a given shape sequence with an accuracy of 79.1 %. The proposed method could also be applied to a variety of other liquid droplet shape-morphing systems which utilize arrays of electromagnetic or electric actuators.

Original language	English
Title of host publication	2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)
Editors	Sinan Haliyo, Mokrane Boudaoud, Mohammad A. Qasaimeh, Sergej Fatikow
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	979-8-3503-3039-7
ISBN (Print)	979-8-3503-3040-3
DOIs	https://doi.org/10.1109/MARSS58567.2023.10294154
Publication status	Published - 13 Oct 2023
MoE publication type	A4 Conference publication
Event	International Conference on Manipulation, Automation and Robotics at Small Scales - Abu Dhabi, United Arab Emirates Duration: 9 Oct 2023 → 13 Oct 2023

Conference

Conference	International Conference on Manipulation, Automation and Robotics at Small Scales
Abbreviated title	MARSS
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	09/10/2023 → 13/10/2023

Keywords

Adaptation models
Magnetic flux density
Actuators
Liquids
Shape
Atmospheric modeling
Magnetic liquids

Access to Document

10.1109/MARSS58567.2023.10294154

Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of ActuationAccepted author manuscript, 2.1 MB

Cite this

Patikiri Arachchige, D., & Zhou, Q. (2023). Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation. In S. Haliyo, M. Boudaoud, M. A. Qasaimeh, & S. Fatikow (Eds.), 2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) (pp. 1-6). Article 10294154 IEEE. https://doi.org/10.1109/MARSS58567.2023.10294154

@inproceedings{e92b0c3cde41462ea81e74c851ececbf,

title = "Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation",

abstract = "Shape morphing of liquid droplets is important for advances in both medical and industrial applications. However current manipulation techniques lack methods to control shapes other than elliptical-shaped droplets. Here we propose using Long Short-Term Memory (LSTM) based model to learn and predict the evolution of the shape of a non-magnetic liquid droplet at an air-ferrofluid interface deformed with programmed sequential actuation of electromagnets. The resulting droplet shapes can be convex or concave. We can also predict the actuation sequences for a given shape sequence with an accuracy of 79.1 \%. The proposed method could also be applied to a variety of other liquid droplet shape-morphing systems which utilize arrays of electromagnetic or electric actuators.",

keywords = "Adaptation models, Magnetic flux density, Actuators, Liquids, Shape, Atmospheric modeling, Magnetic liquids",

author = "\{Patikiri Arachchige\}, Diluka and Quan Zhou",

year = "2023",

month = oct,

day = "13",

doi = "10.1109/MARSS58567.2023.10294154",

language = "English",

isbn = "979-8-3503-3040-3",

pages = "1--6",

editor = "Sinan Haliyo and Mokrane Boudaoud and Qasaimeh, \{Mohammad A.\} and Sergej Fatikow",

booktitle = "2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)",

publisher = "IEEE",

address = "United States",

note = "International Conference on Manipulation, Automation and Robotics at Small Scales, MARSS ; Conference date: 09-10-2023 Through 13-10-2023",

}

Patikiri Arachchige, D & Zhou, Q 2023, Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation. in S Haliyo, M Boudaoud, MA Qasaimeh & S Fatikow (eds), 2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)., 10294154, IEEE, pp. 1-6, International Conference on Manipulation, Automation and Robotics at Small Scales, Abu Dhabi, United Arab Emirates, 09/10/2023. https://doi.org/10.1109/MARSS58567.2023.10294154

Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation. / Patikiri Arachchige, Diluka; Zhou, Quan.
2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS). ed. / Sinan Haliyo; Mokrane Boudaoud; Mohammad A. Qasaimeh; Sergej Fatikow. IEEE, 2023. p. 1-6 10294154.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation

AU - Patikiri Arachchige, Diluka

AU - Zhou, Quan

PY - 2023/10/13

Y1 - 2023/10/13

N2 - Shape morphing of liquid droplets is important for advances in both medical and industrial applications. However current manipulation techniques lack methods to control shapes other than elliptical-shaped droplets. Here we propose using Long Short-Term Memory (LSTM) based model to learn and predict the evolution of the shape of a non-magnetic liquid droplet at an air-ferrofluid interface deformed with programmed sequential actuation of electromagnets. The resulting droplet shapes can be convex or concave. We can also predict the actuation sequences for a given shape sequence with an accuracy of 79.1 %. The proposed method could also be applied to a variety of other liquid droplet shape-morphing systems which utilize arrays of electromagnetic or electric actuators.

AB - Shape morphing of liquid droplets is important for advances in both medical and industrial applications. However current manipulation techniques lack methods to control shapes other than elliptical-shaped droplets. Here we propose using Long Short-Term Memory (LSTM) based model to learn and predict the evolution of the shape of a non-magnetic liquid droplet at an air-ferrofluid interface deformed with programmed sequential actuation of electromagnets. The resulting droplet shapes can be convex or concave. We can also predict the actuation sequences for a given shape sequence with an accuracy of 79.1 %. The proposed method could also be applied to a variety of other liquid droplet shape-morphing systems which utilize arrays of electromagnetic or electric actuators.

KW - Adaptation models

KW - Magnetic flux density

KW - Actuators

KW - Liquids

KW - Shape

KW - Atmospheric modeling

KW - Magnetic liquids

UR - https://www.scopus.com/pages/publications/85178148811

U2 - 10.1109/MARSS58567.2023.10294154

DO - 10.1109/MARSS58567.2023.10294154

M3 - Conference article in proceedings

SN - 979-8-3503-3040-3

SP - 1

EP - 6

BT - 2023 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

A2 - Haliyo, Sinan

A2 - Boudaoud, Mokrane

A2 - Qasaimeh, Mohammad A.

A2 - Fatikow, Sergej

PB - IEEE

T2 - International Conference on Manipulation, Automation and Robotics at Small Scales

Y2 - 9 October 2023 through 13 October 2023

ER -

Learning to Shape Liquid Droplets on an Air-Ferrofluid Interface with Sequences of Actuation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this