Maximising 3D printed supercapacitor capacitance through convolutional neural network guided Bayesian optimisation

Jong Hyun Kim; Jae Hyoung Yun; Seon Il Kim; Won Hyoung Ryu

doi:10.1080/17452759.2022.2150231

Maximising 3D printed supercapacitor capacitance through convolutional neural network guided Bayesian optimisation

Jong Hyun Kim, Jae Hyoung Yun, Seon Il Kim, Won Hyoung Ryu

Department of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

A convolutional neural network (CNN) guided Bayesian optimisation framework is introduced to strategically maximise the surface to volume ratio of 3D printed lattice supercapacitors. We applied Bayesian optimisation on printing parameters to exploit regions where uniform and narrow lines are printed. A line shape classifying CNN model guided the optimiser’s search space to straight-line printed regions, minimising optimisation time and cost. An automatic scoring method allowed each iteration to be conducted within two minutes with accurate and precise measurements. The optimisation process has been demonstrated with graphene oxide (GO) and poly(3,4-ethylenedioxythiophene):polystyrene sulphonate (PEDOT:PSS) inks. The results were compared to the parameters that follow the conventional methodologies of direct ink writing (DIW) 3D printing. For each printed line of GO and PEDOT:PSS inks, irregularities decreased by 61.8% and 18.9% and average widths decreased by 39.0% and 28.6%. PEDOT:PSS lattice supercapacitor printed using optimised result showed a 151.0% increase in specific capacitance.

Original language	English
Article number	e2150231
Journal	Virtual and Physical Prototyping
Volume	18
Issue number	1
DOIs	https://doi.org/10.1080/17452759.2022.2150231
Publication status	Published - 2023

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea Government(MSIT) (No. 2020R1A2C3013158) and the Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE)(No. 20193310100030, Development of high efficient F-class gas turbine hot component by controlling and applying Design for Additive Manufacturing).

Publisher Copyright:
© 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

All Science Journal Classification (ASJC) codes

Signal Processing
Modelling and Simulation
Computer Graphics and Computer-Aided Design
Industrial and Manufacturing Engineering

Access to Document

10.1080/17452759.2022.2150231

Cite this

@article{62655b1cd02e4a708ac304a20b46e48e,

title = "Maximising 3D printed supercapacitor capacitance through convolutional neural network guided Bayesian optimisation",

abstract = "A convolutional neural network (CNN) guided Bayesian optimisation framework is introduced to strategically maximise the surface to volume ratio of 3D printed lattice supercapacitors. We applied Bayesian optimisation on printing parameters to exploit regions where uniform and narrow lines are printed. A line shape classifying CNN model guided the optimiser{\textquoteright}s search space to straight-line printed regions, minimising optimisation time and cost. An automatic scoring method allowed each iteration to be conducted within two minutes with accurate and precise measurements. The optimisation process has been demonstrated with graphene oxide (GO) and poly(3,4-ethylenedioxythiophene):polystyrene sulphonate (PEDOT:PSS) inks. The results were compared to the parameters that follow the conventional methodologies of direct ink writing (DIW) 3D printing. For each printed line of GO and PEDOT:PSS inks, irregularities decreased by 61.8% and 18.9% and average widths decreased by 39.0% and 28.6%. PEDOT:PSS lattice supercapacitor printed using optimised result showed a 151.0% increase in specific capacitance.",

author = "Kim, {Jong Hyun} and Yun, {Jae Hyoung} and Kim, {Seon Il} and Ryu, {Won Hyoung}",

note = "Funding Information: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea Government(MSIT) (No. 2020R1A2C3013158) and the Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE)(No. 20193310100030, Development of high efficient F-class gas turbine hot component by controlling and applying Design for Additive Manufacturing). Publisher Copyright: {\textcopyright} 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.",

year = "2023",

doi = "10.1080/17452759.2022.2150231",

language = "English",

volume = "18",

journal = "Virtual and Physical Prototyping",

issn = "1745-2759",

publisher = "Taylor and Francis Ltd.",

number = "1",

}

TY - JOUR

T1 - Maximising 3D printed supercapacitor capacitance through convolutional neural network guided Bayesian optimisation

AU - Kim, Jong Hyun

AU - Yun, Jae Hyoung

AU - Kim, Seon Il

AU - Ryu, Won Hyoung

N1 - Funding Information: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea Government(MSIT) (No. 2020R1A2C3013158) and the Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE)(No. 20193310100030, Development of high efficient F-class gas turbine hot component by controlling and applying Design for Additive Manufacturing). Publisher Copyright: © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

PY - 2023

Y1 - 2023

N2 - A convolutional neural network (CNN) guided Bayesian optimisation framework is introduced to strategically maximise the surface to volume ratio of 3D printed lattice supercapacitors. We applied Bayesian optimisation on printing parameters to exploit regions where uniform and narrow lines are printed. A line shape classifying CNN model guided the optimiser’s search space to straight-line printed regions, minimising optimisation time and cost. An automatic scoring method allowed each iteration to be conducted within two minutes with accurate and precise measurements. The optimisation process has been demonstrated with graphene oxide (GO) and poly(3,4-ethylenedioxythiophene):polystyrene sulphonate (PEDOT:PSS) inks. The results were compared to the parameters that follow the conventional methodologies of direct ink writing (DIW) 3D printing. For each printed line of GO and PEDOT:PSS inks, irregularities decreased by 61.8% and 18.9% and average widths decreased by 39.0% and 28.6%. PEDOT:PSS lattice supercapacitor printed using optimised result showed a 151.0% increase in specific capacitance.

AB - A convolutional neural network (CNN) guided Bayesian optimisation framework is introduced to strategically maximise the surface to volume ratio of 3D printed lattice supercapacitors. We applied Bayesian optimisation on printing parameters to exploit regions where uniform and narrow lines are printed. A line shape classifying CNN model guided the optimiser’s search space to straight-line printed regions, minimising optimisation time and cost. An automatic scoring method allowed each iteration to be conducted within two minutes with accurate and precise measurements. The optimisation process has been demonstrated with graphene oxide (GO) and poly(3,4-ethylenedioxythiophene):polystyrene sulphonate (PEDOT:PSS) inks. The results were compared to the parameters that follow the conventional methodologies of direct ink writing (DIW) 3D printing. For each printed line of GO and PEDOT:PSS inks, irregularities decreased by 61.8% and 18.9% and average widths decreased by 39.0% and 28.6%. PEDOT:PSS lattice supercapacitor printed using optimised result showed a 151.0% increase in specific capacitance.

UR - http://www.scopus.com/inward/record.url?scp=85143428684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85143428684&partnerID=8YFLogxK

U2 - 10.1080/17452759.2022.2150231

DO - 10.1080/17452759.2022.2150231

M3 - Article

AN - SCOPUS:85143428684

SN - 1745-2759

VL - 18

JO - Virtual and Physical Prototyping

JF - Virtual and Physical Prototyping

IS - 1

M1 - e2150231

ER -

Maximising 3D printed supercapacitor capacitance through convolutional neural network guided Bayesian optimisation

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this