Scientific journal
Scientific Review. Technical science
ISSN 2500-0799
ПИ №ФС77-57440

ALGORITHMIC CLASSIFICATION OF FLOAT GLASS SPOT DEFECTS

Efimov I.V. 1 Petrov D.Y. 1, 2 Ivaschenko V.A. 1, 2 Meshalkin V.P. 3, 4
1 Yuri Gagarin State Technical University of Saratov
2 Institute of Precision Mechanics and Control
3 D.Mendeleyev University of Chemical Technology of Russia
4 Kurnakov Institute of General and Inorganic Chemistry of the Russian Academy of Sciences
The article “Algorithmic classification of float glass spot defects” deals with issues of developing an algorithm for classification of these defects and its application in the program system for analyzing float glass for defects. The authors place primary emphasis upon the implementation of the algorithm for classification of defects which plays a key role in the operation of the system. The article starts with an introduction which provides a general explanation of the operating principle of the programs for identification of float glass spot defects and the algorithm of their classification using an artificial neural network and heuristic rules for identification of the defect type. A flow-chart of the algorithm as well as its detailed description are provided. At the end of the article, the interaction between the proposed program system and the control system of multi-stage float glass manufacturing and software development tools of the program system are described.