Data Mining for Burr Detection (in the Drilling Process)

Authors:
Susana Ferreiro;Ramón Arana;Gotzone Aizpurua;Gorka Aramendi;Aitor Arnaiz;Basilio Sierra
Affiliations:
Fundación TEKNIKER, Eibar, Guipúzcoa,;Fundación TEKNIKER, Eibar, Guipúzcoa,;Fundación TEKNIKER, Eibar, Guipúzcoa,;GMTK, San Sebastián, Guipúzcoa,;Fundación TEKNIKER, Eibar, Guipúzcoa,;UPV-EHU, San Sebastián, Guipúzcoa,
Venue:
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living
Year:
2009

Citing 4
Cited 3

Applications of machine learning and rule induction

Communications of the ACM
Machine Learning

Machine Learning
Machine learning and inductive logic programming for multi-agent systems

Mutli-agents systems and applications
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data mining for quality control: Burr detection in the drilling process

Computers and Industrial Engineering
A multiclassifier approach for drill wear prediction

MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
A Bayesian network for burr detection in the drilling process

Journal of Intelligent Manufacturing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Drilling is the most important operation in aeronautic industry carried out previous to riveting. Its main problem lies with the burrs. Nowadays, there is a burr elimination task (manual task) subsequent to drilling and previous to riveting that increases manufacturing cost. It is necessary to develop a monitoring system to detect automatically and on-line when the generated burr is out of aeronautic limits, and then deburring. This system would reduce holes deburring to the holes which really are out of tolerance limits, focusing in trying to avoid false negatives. The article shows an improvement in burr generation prediction, using Data Mining techniques versus current mathematical model. It gives an overview of the process from data preparation and selection to data analysis (with machine learning algorithms) and evaluation of the models.