DocumentCode
2994955
Title
The system of copper strips surface defects inspection based on intelligent fusion
Author
Zhang, Xuewu ; Liang, Ruiyu ; Ding, Yanqiong ; Chen, Jiasheng ; Duan, Dunqin ; Zong, Guohua
Author_Institution
Comput. & Inf. Eng. Coll., Hohai Univ., Changzhou
fYear
2008
fDate
1-3 Sept. 2008
Firstpage
476
Lastpage
480
Abstract
Directing towards the characteristics and importance of copper strips surface inspection, this paper proposes a copper strips surface inspection system based on artificial intelligence from the standpoint of artificial intelligence. It uses computer vision to capture defects images, uses Hu invariant moments as the eigenvectors and uses BP neural network based on genetic algorithm combined with expert system to train and learn the samples. The trained weights are used to diagnose as the knowledge base and a copper surface defects inspection system based on intelligent fusion is constructed . The experimental results proved that intelligent fusion model can compliment all kinds of intelligent models and has a better performance than single model on copper strips surface inspection.
Keywords
artificial intelligence; automatic optical inspection; backpropagation; computer vision; copper; eigenvalues and eigenfunctions; expert systems; genetic algorithms; metallurgy; neural nets; sensor fusion; BP neural network; Hu invariant moments; artificial intelligence; computer vision; copper strips surface defects inspection; copper strips surface inspection system; copper surface defects inspection system; eigenvectors; expert system; genetic algorithm; intelligent fusion; knowledge base; Artificial intelligence; Artificial neural networks; Computer vision; Copper; Expert systems; Genetic algorithms; Inspection; Intelligent networks; Neural networks; Strips; Copper strips surface defect; Expert system; Intelligent fusion; Neural network;
fLanguage
English
Publisher
ieee
Conference_Titel
Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on
Conference_Location
Qingdao
Print_ISBN
978-1-4244-2502-0
Electronic_ISBN
978-1-4244-2503-7
Type
conf
DOI
10.1109/ICAL.2008.4636198
Filename
4636198
Link To Document