Flekso Baskı Sisteminde Farklı Tramlama Yöntemlerine Göre Tram Yoğunluğunun Yapay Sinir Ağı Yöntemi ile Tahmini
Tram türü, flekso baskı sisteminde baskı kalitesini etkileyen en önemli faktördür. Makine operatörü tarafından baskı işlemi sırasında yapılan işlemlerin (yoğunluk ölçümü, mürekkep ayarları, vb.) amacı, ilk baskıdan son baskıya kadar aynı kaliteyi sağlamaktır. Bu çalışmada, aynı polimer yapısına sahip (DFR) 175 Lpi tram sıklığında, 10 farklı tramlama yapısından elde edilen tram yoğunluğu değerleri Yapay Sinir Ağları Yöntemi (ANN) kullanılarak tahmin edilmiştir. Deneysel çalışmalar sonucunda hesaplamalar için gerekli olan değerler; tram noktalarının densitometrik ölçümlerinden elde edilmiştir. Tram yoğunluğu değerleri için YSA ile oluşturulan modelden elde edilen verilerin korelasyon katsayısı %98,902 olarak bulunmuştur ve bu değer bilimsel değerlerle uyumlu bulunmuştur. Çıkan sonuçlara göre, YSA modelinde flekso baskı sisteminde kullanılan farklı tramlama yöntemlerinin baskı sonucuna etkisi önceden tahmin edilebilir.
Estimation Of Screen Density According To Different Screening Methods With Artificial Neural Network Method In Flexo Printing System
Choice of dot shape is the most important factors that affect the printing quality in the flexographic printing system. The aim of the operations performed by the machine operator during the printing process (densitometric measurements, ink settings, etc.) is to achieve the same quality from the first printing to last printing. This study attempts to estimate screen density values obtained from the same polymer structure (DFR), 175 Lpi screening and 10 different screen structures using the Artificial Neural Networks method (ANN). Data necessary for calculations were obtained from real values as a result of experimental studies. The correlation coefficient of the data obtained from the model created with ANN for screen density values was found to be 98,902% and this value was found to be consistent with scientific values. According to the results, the neural network model used in flexographic printing systems of different screening methods predictable effect on the printing result.
___
- Kurt, M.B., “Determination of The Under Press
Substances and The Pressing Surface Height of The Plate
Used in Flexo Printing System”, PhD Thesis, Istanbul,
TURKEY, (2012).
- Crouch, J.P., “Flexography Primer”, Graphic Arts
Technical Foundation Press,Pittsburgh, PA, (1998).
- Sonmez S., “Development of Printability of Bio-
Composite Materials Using Luffa cylindrica Fiber”,
BioREsources 12(1): 760 –773, (2017).
- Laurent GL., “Prediction of the substrate printing in
flexography by using a new established Printing
Coefficient”, PhD thesis, Royal Institute of Technology,
Stockholm, Sweden, (2002).
- http://esraprint.ir/wp-
content/uploads/2016/06/expert_guide_screening_tech.p
df, (2016).
- http://www.dupont.com/content/dam/assets/products-
and-services/printing-package-
printing/PG/assets/NA/PDS-NA0031-EN-Cyrel-DFR-
Data-Sheet-i.pdf, (2016).
- Olsson R., Yang L., Stam, J., and Magnus L., “Effects on
ink setting in flexographic printing: coating polarity and
dot gain” ,Nordic Pulp & Paper Research Journal,
21(5): 569–574, (2006).
- Ural, E., "The Applied Observation Of The Relationship
Between Printing Pressure And The Amount Of Ink
Printed And Solid Tone Density In Offset Printing On
Coated And Uncoated Papers” İstanbul Ticaret
Üniversitesi Fen Bilimleri Dergisi, 9(17): 61–71, (2010)
- Youssef K.T., “The Impact of FM-AM Hybrid Screening
and Am Screening on Flexographic Printing Quality”,
International Design Journal, 5(4): 1471–1476, (2015).
- TAPPI T402, “Standard conditioning and testing
atmospheres for paper, board, pulp handsheets, and
related products”, TAPPI Press, Atlanta, GA, USA,
(2013).
- Farhana K., and Aishwarya P., “Artificial Neural
Network: Framework for Fault Tolerance and Future.”,
International Conference on Electrical, Electronics,
and Optimization Techniques (ICEEOT), 648– 651,
(2016).
- Ghaedi M., Ansari A., Assefi Nejad P., Ghaedi A., Vafaei
A., and Habibi M.H., “Artificial neural network and Bees
Algorithm for removal of Eosin B using Cobalt Oxide
Nanoparticle-activated carbon: Isotherm and Kinetics
study”, Environ. Prog. Sustainable Energy, 34: 155–
168, (2015).
- Ham F.M., and Kostanic I., “Principles of
Neurocomputing for Science and Engineering“,
McGraw-Hill Higher Education, (2001).
- Ozel Y. , Guney I., and Arca E. “Neural Network Solution
to the Cogeneration System by Using Coal”, 12th
WSEAS International Conference on CIRCUITS,
Heraklion, Greece, 279–283, (2008).
- Lenzi G.G., Evangelista R.F., Duarte E.R., Colpini
L.M.S., Fornari A.C., Menechini Neto R., and Jorge
L.M.M. & Santos O.A.A., “Photocatalytic degradation of
textile reactive dye using artificial neural network
modeling approach”, Desalination and Water
Treatment, 57: 14132–14144, (2016).
- Bates I., Zjakic I., and Budimir I., “Assessment of the
print quality parameters’ impact on the high-quality
flexographic print visual experience”, The Imaging
Science Journal, 63(2): 103–110,(2015).
- Cengiz C., and Kose E., “Modelling of color perception
of different eye colors using artificial neural networks”,
Neural Computing and Applications, 23(7): 2323–2332,
(2013).