Premium
P‐20: A Predictor Method Based on Neural Network for CRT Cut‐off Potential Control
Author(s) -
Mo C. N.,
Luo M. S. David,
Yeh C. H.,
Wang T. C.
Publication year - 2001
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1889/1.1831937
Subject(s) - artificial neural network , voltage , range (aeronautics) , control theory (sociology) , computer science , stability (learning theory) , control (management) , quality assurance , genetic algorithm , artificial intelligence , engineering , machine learning , electrical engineering , operations management , aerospace engineering , external quality assessment
A predictor system based on neural network to control the cut‐off potential voltage within a stable range in CRT manufacturing was proposed. The neural networks and the genetic algorithms are presented for minimize the error value between the predicted and the desired by regulating the affect parameters. Utilizing this forecast system, the mechanical factors could be adjusted in advance and the cut‐off potential voltage would have a suitable control. This method is applied on the quality assurance department to demonstrate the stability of the cut‐off potential voltage and the CRT mass production performance.