Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator

Min Woo Na, Tae Jung Kim, Jae-Bok Song

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This study discusses data-based failure state estimation of the mobile IT parts assembly using a 6 DOF manipulator. A position control-based robotic assembly is fast and simple for automation of production lines. However, when the assembly fails, it is very difficult to find the error that causes the assembly to fail. And the worker should stop and intervene in the assembly process to compensate the error. This is time-consuming and inefficient for the productivity of factory automation. To compensate the error without the aid of worker, this study presents a method for assembly failure state estimation. First, the failure state modeling of the mobile IT parts assembly is proposed. And the supervised learning was used for training whose input is the F/T sensor data and whose output is the failure state of the assembly. Furthermore, it is shown that artificial neural network (ANN) can lead to a higher classification accuracy for estimating the failure state and faster prediction.

Original languageEnglish
Title of host publicationInternational Conference on Control, Automation and Systems
PublisherIEEE Computer Society
Pages1703-1707
Number of pages5
Volume2018-October
ISBN (Electronic)9788993215151
Publication statusPublished - 2018 Dec 10
Event18th International Conference on Control, Automation and Systems, ICCAS 2018 - PyeongChang, Korea, Republic of
Duration: 2018 Oct 172018 Oct 20

Other

Other18th International Conference on Control, Automation and Systems, ICCAS 2018
CountryKorea, Republic of
CityPyeongChang
Period18/10/1718/10/20

Fingerprint

State estimation
Manipulators
Robotic assembly
Factory automation
Supervised learning
Position control
Automation
Productivity
Neural networks
Sensors

Keywords

  • Assembly failure state
  • Fault detection
  • Robotic assembly
  • State estimation
  • Supervised learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Na, M. W., Kim, T. J., & Song, J-B. (2018). Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator. In International Conference on Control, Automation and Systems (Vol. 2018-October, pp. 1703-1707). [8571933] IEEE Computer Society.

Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator. / Na, Min Woo; Kim, Tae Jung; Song, Jae-Bok.

International Conference on Control, Automation and Systems. Vol. 2018-October IEEE Computer Society, 2018. p. 1703-1707 8571933.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Na, MW, Kim, TJ & Song, J-B 2018, Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator. in International Conference on Control, Automation and Systems. vol. 2018-October, 8571933, IEEE Computer Society, pp. 1703-1707, 18th International Conference on Control, Automation and Systems, ICCAS 2018, PyeongChang, Korea, Republic of, 18/10/17.
Na MW, Kim TJ, Song J-B. Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator. In International Conference on Control, Automation and Systems. Vol. 2018-October. IEEE Computer Society. 2018. p. 1703-1707. 8571933
Na, Min Woo ; Kim, Tae Jung ; Song, Jae-Bok. / Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator. International Conference on Control, Automation and Systems. Vol. 2018-October IEEE Computer Society, 2018. pp. 1703-1707
@inproceedings{811f5fcce2e04b7090d98caedd22184a,
title = "Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator",
abstract = "This study discusses data-based failure state estimation of the mobile IT parts assembly using a 6 DOF manipulator. A position control-based robotic assembly is fast and simple for automation of production lines. However, when the assembly fails, it is very difficult to find the error that causes the assembly to fail. And the worker should stop and intervene in the assembly process to compensate the error. This is time-consuming and inefficient for the productivity of factory automation. To compensate the error without the aid of worker, this study presents a method for assembly failure state estimation. First, the failure state modeling of the mobile IT parts assembly is proposed. And the supervised learning was used for training whose input is the F/T sensor data and whose output is the failure state of the assembly. Furthermore, it is shown that artificial neural network (ANN) can lead to a higher classification accuracy for estimating the failure state and faster prediction.",
keywords = "Assembly failure state, Fault detection, Robotic assembly, State estimation, Supervised learning",
author = "Na, {Min Woo} and Kim, {Tae Jung} and Jae-Bok Song",
year = "2018",
month = "12",
day = "10",
language = "English",
volume = "2018-October",
pages = "1703--1707",
booktitle = "International Conference on Control, Automation and Systems",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Data-based assembly failure state estimation of mobile IT parts using a 6 DOF manipulator

AU - Na, Min Woo

AU - Kim, Tae Jung

AU - Song, Jae-Bok

PY - 2018/12/10

Y1 - 2018/12/10

N2 - This study discusses data-based failure state estimation of the mobile IT parts assembly using a 6 DOF manipulator. A position control-based robotic assembly is fast and simple for automation of production lines. However, when the assembly fails, it is very difficult to find the error that causes the assembly to fail. And the worker should stop and intervene in the assembly process to compensate the error. This is time-consuming and inefficient for the productivity of factory automation. To compensate the error without the aid of worker, this study presents a method for assembly failure state estimation. First, the failure state modeling of the mobile IT parts assembly is proposed. And the supervised learning was used for training whose input is the F/T sensor data and whose output is the failure state of the assembly. Furthermore, it is shown that artificial neural network (ANN) can lead to a higher classification accuracy for estimating the failure state and faster prediction.

AB - This study discusses data-based failure state estimation of the mobile IT parts assembly using a 6 DOF manipulator. A position control-based robotic assembly is fast and simple for automation of production lines. However, when the assembly fails, it is very difficult to find the error that causes the assembly to fail. And the worker should stop and intervene in the assembly process to compensate the error. This is time-consuming and inefficient for the productivity of factory automation. To compensate the error without the aid of worker, this study presents a method for assembly failure state estimation. First, the failure state modeling of the mobile IT parts assembly is proposed. And the supervised learning was used for training whose input is the F/T sensor data and whose output is the failure state of the assembly. Furthermore, it is shown that artificial neural network (ANN) can lead to a higher classification accuracy for estimating the failure state and faster prediction.

KW - Assembly failure state

KW - Fault detection

KW - Robotic assembly

KW - State estimation

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85060459206&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060459206&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060459206

VL - 2018-October

SP - 1703

EP - 1707

BT - International Conference on Control, Automation and Systems

PB - IEEE Computer Society

ER -