Authors:
Eija Haapalainen
;
Perttu Laurinen
;
Heli Junno
;
Lauri Tuovinen
and
Juha Röning
Affiliation:
University of Oulu, Finland
Keyword(s):
Feature selection, process identification, k-nearest neighbour classifier, resistance spot welding.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Expert Systems
;
Health Information Systems
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Machine Learning in Control Applications
;
Symbolic Systems
Abstract:
Process identification in the field of resistance spot welding can be used to improve welding quality and to speed up the set-up of a new welding process. Previously, good classification results of welding processes have been obtained using a feature set consisting of 54 features extracted from current and voltage signals recorded during welding. In this study, the usability of the individual features is evaluated and various feature selection methods are tested to find an optimal feature subset to be used in classification. Ways are sought to further improve classification accuracy by discarding features containing less classification-relevant information. The use of a small feature set is profitable in that it facilitates both feature extraction and classification. It is discovered that the classification of welding processes can be performed using a substantially reduced feature set. In addition, careful selection of the features used also improves classification accuracy. In conc
lusion, selection of the feature subset to be used in classification notably improves the performance of the spot welding process identification system.
(More)