This paper describes a knowledge-based system and other classical artificial intelligent techniques developed to identify imperfections or defects in industrial products. The defects we are studying used to appear on the piece external area (like spots, fractures, scratches, dark or white lines). The application of the system has been developed in wall or floor tiles factories and it has been showing itself adequate to its finality, as show its application results. The system works, basically, with codified information from the wall or floor tile faces. The piece of information is accessed by special devices which pick up the image and transform it in an array of numbers and codes. Therefore, the system behavior can be defined by these information pieces. Initially the system detects the existence of imperfections using a first group of computational programs; after that, s second group of programs defines the gravity level of each detected defect (for instance: if it implies to reject the piece). Finally, a third group of programs (the identification system) informs to its users what is the most probable kind of imperfection detected (defect identification). We show here the general ideas of the identification system and the structure and some results, what can be seen as a useful and interesting application of knowledge-based systems to quality control area.
[1]
Dianguo Xu,et al.
A New Method of Defects Identification for Wire Rope Based on Three-Dimensional Magnetic Flux Leakage
,
2006
.
[2]
King-Sun Fu,et al.
Syntactic Pattern Recognition And Applications
,
1968
.
[3]
Jose A. Ventura,et al.
A neural network approach for defect identification and classification on leather fabric
,
2000,
J. Intell. Manuf..
[4]
Michael A. Eierman,et al.
Modeling Tool Impact on Defect Identification in IS Design
,
2006
.
[5]
Stamatios V. Kartalopoulos,et al.
Proceedings of the 12th WSEAS international conference on Systems
,
2008,
ICONS 2008.
[6]
Fumio Kojima,et al.
Identification of crack profiles using genetic programming and fuzzy inference
,
2001
.
[7]
G. Stavroulakis,et al.
Defect identification in 3-D elastostatics using a genetic algorithm
,
2006
.
[8]
Joan S. Weszka,et al.
A survey of threshold selection techniques
,
1978
.