Machine learning-based shape error estimation in micromilling by using motor current

Kenta Mizuhara; Daisuke Nakamichi; Wataru Yanagihara; Yasuhiro Kakinuma

Machine learning-based shape error estimation in micromilling by using motor current

Kenta Mizuhara, Daisuke Nakamichi, Wataru Yanagihara, Yasuhiro Kakinuma

Department of System Design Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

The requirement for Mass production of Microlens array (MLA) mold is increasing. MLA molds are manufactured by 5-axis ultra-precision machining center using an ultra-small diameter end mill. Since visual examination is not good at judging quality of product while machining, the development of effective process monitoring technology is required. The ultra-precision machining center used in this study employs a linear motor and has low sliding resistance while machining. Therefore, machining information is directly reflected in servo information. Focusing on this point, we developed a machine learning-based shape error estimation model using servomotor current alone and discussed its usefulness.

Original language	English
Pages	594-596
Number of pages	3
Publication status	Published - 2021
Event	10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021 - Virtual, Online Duration: 2021 Nov 14 → 2021 Nov 18

Conference

Conference	10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021
City	Virtual, Online
Period	21/11/14 → 21/11/18

Keywords

Machine learning
Micro lens array
Sensorless
Servo motor current
Shape error estimation

ASJC Scopus subject areas

Artificial Intelligence
Industrial and Manufacturing Engineering
Electronic, Optical and Magnetic Materials

Cite this

Machine learning-based shape error estimation in micromilling by using motor current. / Mizuhara, Kenta; Nakamichi, Daisuke; Yanagihara, Wataru; Kakinuma, Yasuhiro.

2021. 594-596 Paper presented at 10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021, Virtual, Online.

Research output: Contribution to conference › Paper › peer-review

@conference{4c811288be5e4c2f84c85c1a8ab43a6d,

title = "Machine learning-based shape error estimation in micromilling by using motor current",

abstract = "The requirement for Mass production of Microlens array (MLA) mold is increasing. MLA molds are manufactured by 5-axis ultra-precision machining center using an ultra-small diameter end mill. Since visual examination is not good at judging quality of product while machining, the development of effective process monitoring technology is required. The ultra-precision machining center used in this study employs a linear motor and has low sliding resistance while machining. Therefore, machining information is directly reflected in servo information. Focusing on this point, we developed a machine learning-based shape error estimation model using servomotor current alone and discussed its usefulness.",

keywords = "Machine learning, Micro lens array, Sensorless, Servo motor current, Shape error estimation",

author = "Kenta Mizuhara and Daisuke Nakamichi and Wataru Yanagihara and Yasuhiro Kakinuma",

note = "Funding Information: This work was supported by Strategic Core Technology Advancement Program (Supporting Industry Program), in Ministry of Economy, Trade, and Industry. Publisher Copyright: {\textcopyright} 2021 The Japan Society of Mechanical Engineers.; 10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021 ; Conference date: 14-11-2021 Through 18-11-2021",

year = "2021",

language = "English",

pages = "594--596",

}

TY - CONF

T1 - Machine learning-based shape error estimation in micromilling by using motor current

AU - Mizuhara, Kenta

AU - Nakamichi, Daisuke

AU - Yanagihara, Wataru

AU - Kakinuma, Yasuhiro

N1 - Funding Information: This work was supported by Strategic Core Technology Advancement Program (Supporting Industry Program), in Ministry of Economy, Trade, and Industry. Publisher Copyright: © 2021 The Japan Society of Mechanical Engineers.

PY - 2021

Y1 - 2021

N2 - The requirement for Mass production of Microlens array (MLA) mold is increasing. MLA molds are manufactured by 5-axis ultra-precision machining center using an ultra-small diameter end mill. Since visual examination is not good at judging quality of product while machining, the development of effective process monitoring technology is required. The ultra-precision machining center used in this study employs a linear motor and has low sliding resistance while machining. Therefore, machining information is directly reflected in servo information. Focusing on this point, we developed a machine learning-based shape error estimation model using servomotor current alone and discussed its usefulness.

AB - The requirement for Mass production of Microlens array (MLA) mold is increasing. MLA molds are manufactured by 5-axis ultra-precision machining center using an ultra-small diameter end mill. Since visual examination is not good at judging quality of product while machining, the development of effective process monitoring technology is required. The ultra-precision machining center used in this study employs a linear motor and has low sliding resistance while machining. Therefore, machining information is directly reflected in servo information. Focusing on this point, we developed a machine learning-based shape error estimation model using servomotor current alone and discussed its usefulness.

KW - Machine learning

KW - Micro lens array

KW - Sensorless

KW - Servo motor current

KW - Shape error estimation

UR - http://www.scopus.com/inward/record.url?scp=85124807061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85124807061&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85124807061

SP - 594

EP - 596

T2 - 10th International Conference on Leading Edge Manufacturing Technologies in 21st Century, LEM 2021

Y2 - 14 November 2021 through 18 November 2021

ER -

Machine learning-based shape error estimation in micromilling by using motor current

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this