Journal of Automation and Control
ISSN (Print): 2372-3033 ISSN (Online): 2372-3041 Website: http://www.sciepub.com/journal/automation Editor-in-chief: Santosh Nanda
Open Access
Journal Browser
Go
Journal of Automation and Control. 2015, 3(3), 96-100
DOI: 10.12691/automation-3-3-11
Open AccessArticle

Diagnostics of Product Defects by Clustering and Machine Learning Classification Algorithm

Kamil Židek1, and Vladislav Maxim2

1Faculty of Manufacturing Technologies with a seat in Presov, Presov, Slovak Republic

2Institute of Automation, Robotics and Mechatronics, FME, Technical University of Kosice, Slovak Republic

Pub. Date: December 15, 2015

Cite this paper:
Kamil Židek and Vladislav Maxim. Diagnostics of Product Defects by Clustering and Machine Learning Classification Algorithm. Journal of Automation and Control. 2015; 3(3):96-100. doi: 10.12691/automation-3-3-11

Abstract

The article deals with usability of clustering and machine learning classification algorithm for search systematic surface errors. The main idea is to propose a methodology for the automated identification, diagnostics and localization of systematic errors in mass production. The introduced methodology consists of three levels: image processing for error parameterization, clustering for creating of errors classes (teach data) and prediction of new samples by machine learning algorithm. We conducted experiments with density based clustering algorithm DBSCAN. For classification we use multilayer perceptron MLP/ANN.

Keywords:
inspection clustering machine learning image processing

Creative CommonsThis work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Figures

Figure of 10

References:

[1]  E. R. Davies, Computer & Machine Vision, Theory Algorithms Practicalities, Elsevier, p. 934.
 
[2]  S. Har-Peled, B. Sadri, How fast is the k-means method?, Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms, pages, Philadelphia, PA, USA, 877–885, (2005).
 
[3]  D. Arthur, S. Vassilvitskii,K-means++: the advantages of careful seeding, Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, (2007).
 
[4]  W. H. E. Day, H. Edelsbrunner, Efficient algorithms for agglomerative hierarchical clustering methods, Journal of Classification, 1,7-24, (1984).
 
[5]  M. Muja, D. G. Lowe, Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration, in International Conference on Computer Vision Theory and Applications, VISAPP'09, (2009).
 
[6]  M. Ester, H.-P. Kriegel, J. Sander, X. Xu E. Simoudis, J. Han, U. Fayyad, A density-based algorithm for discovering clusters in large spatial databases with noise, Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, vol. 1AAAI Press (1996), pp. 226-231.
 
[7]  C. C. Chang, C.-J. Lin., LIBSVM, a library for support vector machines, ACM Transactions on Intelligent Systems and Technology, 2:27: 1-27:27, (2011).
 
[8]  O. Kadri, L. H. Mouss, M. D. Mouss, Fault diagnosis of rotary kiln using SVM and binary ACO, The Journal of Mechanical Science and Technology, vol. 26, no. 2, pp.601-608, (2012).
 
[9]  K. Fukunaga, Introduction to Statistical Pattern Recognition., New York: Academic Press, (1990).
 
[10]  R.K. Agrawal, R. Bala, Incremental Bayesian classification for multivariate normal distribution data, Volume 29, Issue 13, pp.1873-1876, (2008).
 
[11]  D. Coomans, D.L. Massart, Alternative k-nearest neighbour rules in supervised pattern recognition, k-Nearest neighbour classification by using alternative voting rules, , AnalyticaChimica, Acta 136, pp. 15-27, (1982).
 
[12]  B. Yao, F. Li,P. Kumar, K-Nearest Neighbor Queries and KNN-Joins in Large Relational Databases (Almost) for Free, Data Engineering (ICDE), 2010 IEEE 26th International Conference, pp. 4-15, (2010).
 
[13]  L. Breiman, A. Cutler, Random Forests, available at: <www.stat.berkeley.edu/~breiman/RandomForests/cc_graphics.htm>.
 
[14]  Bo-Suk Yang, Random forests classifier for machine fault diagnosis, The Journal of Mechanical Science and Technology, vol. 22, no. 9, pp.1716-1725, (2008).
 
[15]  J. Friedman, Greedy Function Aproximation, A Gradient Boosting Machine, Feb. 24, 1999, available at: <docs.salford-systems.com/GreedyFuncApproxSS.pdf>.
 
[16]  Y. LeCun, L. Bottou, G.B. Orr and K.R. Muller, Efficient backprop, in Neural Networks, Tricks of the Trade, Springer Lecture Notes in Computer Sciences 1524, pp.5-50.
 
[17]  K. Židek, E, Rigasová, Diagnostics of Products by Vision System, Applied Mechanics and Materials, Trans Tech Publications, Switzerland, , Vol. 308, 33-38, (2013).