It is often difficult for a single classifier to achieve perfect classification during process monitoring. Sensor fusion enables the final decision to be improved, but uses voting methods, which usually do not perform well when there is a tie vote. In this paper, classifier fusion with class-weighted voting is investigated to further enhance the performance of monitoring systems. The overall performances of individual classifiers are used as the weighting factors to classifier fusion based on majority voting. When applied to tool wear monitoring of the coroning process, the classifier that was based on overall performance weighting improved the classification rate to 95.6% and the one based on state performance weighting showed 98.5% classification, compared to 87.7% for classifier fusion with unity weighting. A classifier fusion further increased performance from 98.5% to 99.7% by applying a penalty vote on the weighting factor.
Skip Nav Destination
ASME 2012 International Manufacturing Science and Engineering Conference collocated with the 40th North American Manufacturing Research Conference and in participation with the International Conference on Tribology Materials and Processing
June 4–8, 2012
Notre Dame, Indiana, USA
Conference Sponsors:
- Manufacturing Engineering Division
ISBN:
978-0-7918-5499-0
PROCEEDINGS PAPER
Classifier Fusion for Acoustic Emission Based Tool Wear Monitoring Available to Purchase
Tae Hyung Kim,
Tae Hyung Kim
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Elijah Kannatey-Asibu, Jr.
Elijah Kannatey-Asibu, Jr.
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Juil Yum
University of Michigan, Ann Arbor, MI
Tae Hyung Kim
University of Michigan, Ann Arbor, MI
Elijah Kannatey-Asibu, Jr.
University of Michigan, Ann Arbor, MI
Paper No:
MSEC2012-7380, pp. 805-812; 8 pages
Published Online:
July 19, 2013
Citation
Yum, J, Kim, TH, & Kannatey-Asibu, E, Jr. "Classifier Fusion for Acoustic Emission Based Tool Wear Monitoring." Proceedings of the ASME 2012 International Manufacturing Science and Engineering Conference collocated with the 40th North American Manufacturing Research Conference and in participation with the International Conference on Tribology Materials and Processing. ASME 2012 International Manufacturing Science and Engineering Conference. Notre Dame, Indiana, USA. June 4–8, 2012. pp. 805-812. ASME. https://doi.org/10.1115/MSEC2012-7380
Download citation file:
15
Views
Related Proceedings Papers
Related Articles
Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring
J. Eng. Ind (August,1990)
Automated Sensor Selection and Fusion for Monitoring and Diagnostics of Plunge Grinding
J. Manuf. Sci. Eng (June,2008)
A Customized Neural Network for Sensor Fusion in On-Line Monitoring of Cutting Tool Wear
J. Eng. Ind (May,1995)
Related Chapters
Process Monitoring Using Online Sensor Signals
Ultrasonic Welding of Lithium-Ion Batteries
Experimental Research on Fiber Grating Sensor Acoustic Emission Detection of Rock Material Specimen Failure
Geological Engineering: Proceedings of the 1 st International Conference (ICGE 2007)
Accumulated Step Deviation Method for Automatic Fuzzy Set Generation
Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17