TY - GEN
T1 - A vision-based framework for enhanced quality control in a smart manufacturing system
AU - Yang, Zixuan
AU - Teng, Huaiyuan
AU - Goldhawk, Jeremy
AU - Kovalenko, Ilya
AU - Balta, Efe C.
AU - Lopez, Felipe
AU - Tilbury, Dawn
AU - Barton, Kira
N1 - Funding Information:
This work was supported in part by NSF #1544678, an NSF Graduate Fellowship, and a gift from Rockwell Automation. The authors would like to thank Mr. Gibin Joe Zachariah for his work in the configuration of the camera station. In addition, the authors would like to thank Dr. James Moyne for providing feedback and suggesting improvements to the work. Finally, the authors would
Publisher Copyright:
© ASME 2019 14th International Manufacturing Science and Engineering Conference. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Dimensional metrology is an integral part of quality controlin manufacturing systems. Most existing manufacturing systemsutilize contact-based metrology, which is time consuming andnot flexible to design changes. There have been recent applications of computer vision for performing dimensional metrologyin manufacturing systems. Existing computer vision metrologytechniques need repeated calibration of the system and are notutilized with data analysis methods to improve decision making. In this work, we propose a robust non-contact computervision metrology pipeline integrated with Computer Aided Design (CAD) that has the capacity to enable control of smart manufacturing systems. The pipeline uses CAD data to extract nominal dimensions and tolerances. The dimensions are comparedto the measured ones, computed using camera images and computer vision algorithms. A quality check module evaluates if themeasurements are within admissible bounds and informs a central controller. If a part does not meet a tolerance, the centralcontroller changes a program running on a specific machine toensure that parts meet the necessary specifications. Results froman implementation of the proposed pipeline on a manufacturingresearch testbed are given at the end.
AB - Dimensional metrology is an integral part of quality controlin manufacturing systems. Most existing manufacturing systemsutilize contact-based metrology, which is time consuming andnot flexible to design changes. There have been recent applications of computer vision for performing dimensional metrologyin manufacturing systems. Existing computer vision metrologytechniques need repeated calibration of the system and are notutilized with data analysis methods to improve decision making. In this work, we propose a robust non-contact computervision metrology pipeline integrated with Computer Aided Design (CAD) that has the capacity to enable control of smart manufacturing systems. The pipeline uses CAD data to extract nominal dimensions and tolerances. The dimensions are comparedto the measured ones, computed using camera images and computer vision algorithms. A quality check module evaluates if themeasurements are within admissible bounds and informs a central controller. If a part does not meet a tolerance, the centralcontroller changes a program running on a specific machine toensure that parts meet the necessary specifications. Results froman implementation of the proposed pipeline on a manufacturingresearch testbed are given at the end.
UR - http://www.scopus.com/inward/record.url?scp=85076521940&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076521940&partnerID=8YFLogxK
U2 - 10.1115/MSEC2019-2966
DO - 10.1115/MSEC2019-2966
M3 - Conference contribution
AN - SCOPUS:85076521940
T3 - ASME 2019 14th International Manufacturing Science and Engineering Conference, MSEC 2019
BT - Additive Manufacturing; Manufacturing Equipment and Systems; Bio and Sustainable Manufacturing
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2019 14th International Manufacturing Science and Engineering Conference, MSEC 2019
Y2 - 10 June 2019 through 14 June 2019
ER -