TY - GEN
T1 - Profile monitoring and fault diagnosis via sensor fusion for ultrasonic welding
AU - Guo, Weihong
AU - Jin, Jionghua
AU - Hu, S. Jack
N1 - Funding Information: This research is supported by the National Science Foundation and General Motors Collaborative Research Lab in Advanced Vehicle Manufacturing at The University of Michigan. Publisher Copyright: Copyright © 2016 by ASME.
PY - 2016
Y1 - 2016
N2 - Sensor signals acquired during the manufacturing process contain rich information that can be used to facilitate effective monitoring of operational quality, early detection of system anomalies, quick diagnosis of fault root causes, and intelligent system design and control. This paper develops a method for effective monitoring and diagnosis of multi-sensor heterogeneous profile data based on multilinear discriminant analysis. The proposed method operates directly on the multistream profiles and then extracts uncorrelated discriminative features through tensor-to-vector projection, and thus preserving the interrelationship of different sensors. The extracted features are then fed into classifiers to detect faulty operations and recognize fault types. The developed method is demonstrated with both simulated and real data from ultrasonic metal welding.
AB - Sensor signals acquired during the manufacturing process contain rich information that can be used to facilitate effective monitoring of operational quality, early detection of system anomalies, quick diagnosis of fault root causes, and intelligent system design and control. This paper develops a method for effective monitoring and diagnosis of multi-sensor heterogeneous profile data based on multilinear discriminant analysis. The proposed method operates directly on the multistream profiles and then extracts uncorrelated discriminative features through tensor-to-vector projection, and thus preserving the interrelationship of different sensors. The extracted features are then fed into classifiers to detect faulty operations and recognize fault types. The developed method is demonstrated with both simulated and real data from ultrasonic metal welding.
KW - Fault diagnosis
KW - Profile monitoring
KW - Sensor fusion
KW - Tensor decomposition
UR - http://www.scopus.com/inward/record.url?scp=84991628089&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84991628089&partnerID=8YFLogxK
U2 - https://doi.org/10.1115/MSEC2016-8750
DO - https://doi.org/10.1115/MSEC2016-8750
M3 - Conference contribution
T3 - ASME 2016 11th International Manufacturing Science and Engineering Conference, MSEC 2016
BT - Materials; Biomanufacturing; Properties, Applications and Systems; Sustainable Manufacturing
PB - American Society of Mechanical Engineers
T2 - ASME 2016 11th International Manufacturing Science and Engineering Conference, MSEC 2016
Y2 - 27 June 2016 through 1 July 2016
ER -