Title :
Feature Selection for Troubleshooting in Complex Assembly Lines
Author :
Pfingsten, Tobias ; Herrmann, Daniel J L ; Schnitzler, Thomas ; Feustel, Andreas ; Schölkopf, Bernhard
Author_Institution :
Max Planck Inst. for Biol. Cybern., Tubingen
fDate :
7/1/2007 12:00:00 AM
Abstract :
The final properties of sophisticated products can be affected by many unapparent dependencies within the manufacturing process, and the products´ integrity can often only be checked in a final measurement. Troubleshooting can therefore be very tedious if not impossible in large assembly lines. In this paper, we show that feature selection is an efficient tool for serial-grouped lines to reveal causes for irregularities in product attributes.
Keywords :
assembling; failure analysis; fault diagnosis; manufacturing processes; manufacturing systems; quality management; complex assembly line troubleshooting; feature selection; manufacturing process; product integrity; serial-grouped lines; Assembly; Cybernetics; Fault detection; History; Inspection; Manufacturing processes; Production; Pulp manufacturing; Support vector machines; Testing; Feature selection; production chain; support vector machine (SVM);
Journal_Title :
Automation Science and Engineering, IEEE Transactions on
DOI :
10.1109/TASE.2006.888054
