The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques

Ping Wun Huang; Kuan Jung Chung

doi:10.1109/IMPACT47228.2019.9024996

The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques

Ping Wun Huang, Kuan Jung Chung

Department of Mechatronic Engineering

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

Abstract

This study presents an Artificial Intelligence (AI) approach for estimating the Cartesian positioning shift of a wafer handling robot arm to prevent the occurrence of unexpected event, drop of wafers. First, a Charge-coupled Device (CCD) based robot arm fault diagnostic system was built to measure the target positions of the robot arm when handling wafers. An ensemble-based machine learning model with time series cross validation technique from a commercial software called Decanter AI (Mobagel Inc.) was applied to predict the quantity of the maximum position shift with respect to X and Y axis for next one minute. The prediction results by the test datasets through 38,417 minutes show that the Root Mean Square Error (RMSE) is 4.351 μm to validate the trained model is appropriate for predicting the positioning shift of the handling robot arm.

Original language	English
Title of host publication	IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding
Publisher	IEEE Computer Society
Pages	58-61
Number of pages	4
ISBN (Electronic)	9781728160702
DOIs	https://doi.org/10.1109/IMPACT47228.2019.9024996
Publication status	Published - 2019 Oct
Event	14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, IMPACT 2019 - Taipei, Taiwan Duration: 2019 Oct 23 → 2019 Oct 25

Publication series

Name	Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT
Volume	2019-October
ISSN (Print)	2150-5934
ISSN (Electronic)	2150-5942

Conference

Conference	14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, IMPACT 2019
Country	Taiwan
City	Taipei
Period	19-10-23 → 19-10-25

Fingerprint

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Control and Systems Engineering
Electrical and Electronic Engineering

Cite this

Huang, P. W., & Chung, K. J. (2019). The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques. In IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding (pp. 58-61). [9024996] (Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/IMPACT47228.2019.9024996

Huang, Ping Wun ; Chung, Kuan Jung. / The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques. IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding. IEEE Computer Society, 2019. pp. 58-61 (Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT).

@inproceedings{cdb7a39f83274e969f55e9d64da89d17,

title = "The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques",

abstract = "This study presents an Artificial Intelligence (AI) approach for estimating the Cartesian positioning shift of a wafer handling robot arm to prevent the occurrence of unexpected event, drop of wafers. First, a Charge-coupled Device (CCD) based robot arm fault diagnostic system was built to measure the target positions of the robot arm when handling wafers. An ensemble-based machine learning model with time series cross validation technique from a commercial software called Decanter AI (Mobagel Inc.) was applied to predict the quantity of the maximum position shift with respect to X and Y axis for next one minute. The prediction results by the test datasets through 38,417 minutes show that the Root Mean Square Error (RMSE) is 4.351 μm to validate the trained model is appropriate for predicting the positioning shift of the handling robot arm.",

author = "Huang, {Ping Wun} and Chung, {Kuan Jung}",

year = "2019",

month = oct

doi = "10.1109/IMPACT47228.2019.9024996",

language = "English",

series = "Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT",

publisher = "IEEE Computer Society",

pages = "58--61",

booktitle = "IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding",

address = "United States",

note = "14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, IMPACT 2019 ; Conference date: 23-10-2019 Through 25-10-2019",

}

Huang, PW & Chung, KJ 2019, The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques. in IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding., 9024996, Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT, vol. 2019-October, IEEE Computer Society, pp. 58-61, 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, IMPACT 2019, Taipei, Taiwan, 19-10-23. https://doi.org/10.1109/IMPACT47228.2019.9024996

The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques. / Huang, Ping Wun; Chung, Kuan Jung.

IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding. IEEE Computer Society, 2019. p. 58-61 9024996 (Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT; Vol. 2019-October).

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

TY - GEN

T1 - The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques

AU - Huang, Ping Wun

AU - Chung, Kuan Jung

PY - 2019/10

Y1 - 2019/10

N2 - This study presents an Artificial Intelligence (AI) approach for estimating the Cartesian positioning shift of a wafer handling robot arm to prevent the occurrence of unexpected event, drop of wafers. First, a Charge-coupled Device (CCD) based robot arm fault diagnostic system was built to measure the target positions of the robot arm when handling wafers. An ensemble-based machine learning model with time series cross validation technique from a commercial software called Decanter AI (Mobagel Inc.) was applied to predict the quantity of the maximum position shift with respect to X and Y axis for next one minute. The prediction results by the test datasets through 38,417 minutes show that the Root Mean Square Error (RMSE) is 4.351 μm to validate the trained model is appropriate for predicting the positioning shift of the handling robot arm.

AB - This study presents an Artificial Intelligence (AI) approach for estimating the Cartesian positioning shift of a wafer handling robot arm to prevent the occurrence of unexpected event, drop of wafers. First, a Charge-coupled Device (CCD) based robot arm fault diagnostic system was built to measure the target positions of the robot arm when handling wafers. An ensemble-based machine learning model with time series cross validation technique from a commercial software called Decanter AI (Mobagel Inc.) was applied to predict the quantity of the maximum position shift with respect to X and Y axis for next one minute. The prediction results by the test datasets through 38,417 minutes show that the Root Mean Square Error (RMSE) is 4.351 μm to validate the trained model is appropriate for predicting the positioning shift of the handling robot arm.

UR - http://www.scopus.com/inward/record.url?scp=85082695988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082695988&partnerID=8YFLogxK

U2 - 10.1109/IMPACT47228.2019.9024996

DO - 10.1109/IMPACT47228.2019.9024996

M3 - Conference contribution

AN - SCOPUS:85082695988

T3 - Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT

SP - 58

EP - 61

BT - IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding

PB - IEEE Computer Society

T2 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, IMPACT 2019

Y2 - 23 October 2019 through 25 October 2019

ER -

Huang PW, Chung KJ. The Prediction of Positioning shift for a Robot Arm Using Machine Learning Techniques. In IMPACT 2019 - 14th International Microsystems, Packaging, Assembly and Circuits Technology Conference, Proceeding. IEEE Computer Society. 2019. p. 58-61. 9024996. (Proceedings of Technical Papers - International Microsystems, Packaging, Assembly, and Circuits Technology Conference, IMPACT). https://doi.org/10.1109/IMPACT47228.2019.9024996

Access to Document

10.1109/IMPACT47228.2019.9024996