PREDICTION OF CIELab VALUES AND COLOR CHANGING OCCURRED AFTER CHEMICAL FINISHING APPLICATIONS BY ARTIFICIAL NEURAL NETWORKS ON DYED FABRICS

Yıl 2009, Cilt: 19 Sayı: 1, 61 - 69, 01.06.2009

Onur Balcı R. Tuğrul Oğulata

Öz

Color is a fact affected from the properties of the raw material to the final finishing processes which are the most important ones. In the study, the effect of the finishing processes to CIELab values, consequently the changing on the color were determined, and then these values were tried to be predicted using artificial neural networks (ANN) on different topology. In this way, the color changing concerning on chemical finishing process can be determined in advance and the necessary precaution can be taken without having trouble by changes on the dyeing recipes and process parameters

Anahtar Kelimeler

Chemical finishing, CIELab, Color, Artificial neural network, Prediction

BOYANMIŞ KUMAŞLARDA KİMYASAL APRE UYGULAMALARI SONUCUNDA OLUŞABİLECEK RENK DEĞİŞİMİNİN VE CIELab DEĞERLERİNİN YAPAY SİNİR AĞLARI KULLANILARAK TAHMİN EDİLMESİ

Öz

Renk, hammaddenin özelliğinden, son apre işlemine kadar, üretimin her aşamasından etkilenen bir olgudur. Özellikle kimyasal apre uygulamaları sonucunda oluşan renk farklılığı önemli sorunlar yaratmaktadır. Çalışmada seçilen altı farklı dokunmuş ve renklendirilmiş kumaşın apre işlemlerinin CIELab değerlerine etkisi, dolayısıyla renklerinde meydana gelen değişimler (ΔL*, Δa*, Δb*, ΔC*, ΔH*, ΔE) belirlenmiş ve daha sonra bu değerler farklı topolojilerde yapay sinir ağları (YSA) kullanılarak tahmin edilmeye çalışmıştır. Yapılan çalışma sonucunda kurulan YSA modellerinin, apre uygulamaları ve diğer üretim proseslerine bağlı olarak, boyanmış kumaşta meydana gelebilecek renk değişimlerinin tahmininde kullanılabileceğini göstermektedir

Anahtar Kelimeler

Kimyasal apre, CIELab, Renk, Yapay sinir ağları, Tahmin

Kaynakça

• 1. Elmas, Ç., 2003, Yapay Sinir Ağları, Seçkin Yayıncılık, İstanbul.
• 2. Rumelhart De, 1986, Learning Internal Representation By Error Propagation. In: Parallel Distributed Processing, Cambridge, Ma: Mıt Press, Vol.1, 318–362.
• 3. Krose, B., Smaget, P., V., D., 1996, An Introduction To Neural Networks, The University of Amsterdam, Amsterdam.
• 4. Duda, R., O., Hart, P., E., Stork, D., G., 2000, Pattern Classification, Wiley-Second Edition.
• 5. Cuff, J.A., Barton, G. J., 1999, Evaluation And Improvement Of Multiple Sequence Methods For Protein Secondary Structure Prediction. Proteins: Structure, Function, And Genetics, 34, 508–519.
• 6. Cheng, K., P., S., Lam, H., L., I., 2003, “Evaluating And Comparing The Physical Properties Of Spliced Yarns By Regression And Neural Network Tecniques”, Textile Research Journal, Yıl:73, No:2, 161-164.
• 7. Kanfeng, W., Kai, L., Xiubao, H., 2004, “Prediction Of Worsted Yarn By Using Neural Network”, Proceedings of the Textile Institute 83rd World Conference, 1362-1367.
• 8. Majumdar, A., Majumdar, P., K., Sarkar, B., 2004, “Prediction Of Single Yarn Tenacity Of Ring And Rotor Spun Yarns From Hvı Results Using Artificial Neural Networks”, Indian Journal of Fibre & Textile Research, Vol 29, 157-162.
• 9. Beltran, R. Wang, L., Wang, X., 2004, “Predicting Worsted Spinning Performance with An Artificial Neural Network Model”, Textile Research Journal, Vol.74, 757-763.
• 10. Majumdar, A., Majumdar, P., K., Sarkar, B., 2005, “Application Of An Adaptive Neuro-Fuzzy System for The Prediction of Cotton Yarn Strength From HVI Fibre Properties”, Journal of Textile Institute, Vol.96, No.1, 55-60.
• 11. Lewandowski, S., Stanczyk, T., 2005, “Identificiation And Classfication Of Spliced Wool Combed Yarn Joints By Artifcial Neural Networks Part I. Developing And Artificial Neural Network Model”, The Fibres&Textiles In Eastern Europe, Vol.13, No.1(49), 39-43.
• 12. Lewandowski, S., Stanczyk, T., 2005, “Identificiation And Classfication Of Spliced Wool Combed Yarn Joints By Artifcial Neural Networks Part II. Interpretation of Identification And Classficiation Results of the Unknoted Spilced Yarns Joints”, The Fibres&Textiles In Eastern Europe, Vol.13, No.2(50), 16-19.
• 13. Ramesh, M., C., Rajamanickam, R., Jayaraman, S., 1995, “Prediction of Yarn Tensile Properties By Using Artificial Neural Networks”, Journal of the Textile Institute, Vol.86, No.3, 459-469.
• 14. Babay, A., Cheikhrouhou, M., Vermeulen, B., 2004, “Selecting The Optimal Neural Network Architecture For Predicting Cotton Yarn Hairness”, The Journal of Textile Institute, Vol. 96, No.3, 185-192.
• 15. Lin, J., J., 2007, “Prediction of Yarn Shrinkage Using Neural Nets”, Textile Research Journal, Vol. 77, No.5, 336-342.
• 16. Fan, K., C., Wang, Y., K., Chang, B., L., Wang, T., P., 1998, “Fabric Classification Based On Recognition Using Neural Network and Dimensionality Reduction”, Textile Research Journal, Yıl:68, No:3, 179-185.
• 17. Shiau, Y., Tsai, S., Lin, C-S., 2000, “Classifiying Web Defects With A Back-Propagation Neural Network By Color Image Processing”, Textile Research Journal, Yıl:70, No:7, 633-640.
• 18. Tilacco A., Borzone, P., Carosio, S., Durante, A., 2002, “Detecting Fabric Defects With A Neural Network Using Two Kinds of Optical Patterns”, “Textile Research Journal”, Yıl:72 No:6, 545-550.
• 19. Chen, P., B., Liang, T., C., Yau, H., F., 1998, “Classifying Textile Faults With A Back-Propagation Neural Network Using Power Spectra”, Textile Research Journal, Yıl:68, No:2, 121-126.
• 20. Ertuğrul, S., Uçar, N., 2000, “Predicting Bursting Strenght of Cotton Plain Knitted Fabrics Using Intelligent Techniques”, Textile Research Journal, Yıl:70, No:10, 845-851.
• 21. Gong, R., H., Chen, Y., 1999, “Predicting The Performance of Fabrics in Garment Manufacturing With Artificial Neural Networks”, Textile Research Journal, Yıl:69, No:7, 477-482.
• 22. Tokarska, M., 2004, “Neural Model of The Permeability Features of Woven Fabrics”, Textile Research Journal, Yıl:74, 1045-1048.
• 23. Bhattacharjee, D., Kothari, V., K., “A Neural Network System For Prediction of Thermal Resistance of Textile Fabrics”, Textile Research Journal, Yıl:77, No.1, 4-12.
• 24. Allan, G., Yang, R., Fotherıngham, A., 2001, “Neural Modelling Of Polipropylene Fibre Processing: Predicting The Structure and Properties And Identifying The Control Parameters For Specified Fibres”, Journal of Materials Science, Yıl:36, 3113-3118.
• 25. Uçar, N., Ertuğrul, S., 2007, “Prediction of Fuzz Fibres on Fabric Surface By Using Neural Network and Regression Analysis”, Fibres and Textiles in Eastern Europe, Vol.15, No.2 (61), 58-61.
• 26. Spehl, J., Wölker, M., Kettler, W., 1994, “Application of the Backpropagation Nets for Color Recipe Prediction as a Nonlinear Approximation Problem”, IEEE, 3336-3341.
• 27. Mizutani, E., Jang, J., R., Nishio, K., 2005, “Coactive Neuro-Fuzzy Modeling for Color Recipe Prediction”, www.ieexplore.ieee.org.
• 28. Senthilkumar, M., Selvakumar, N., 2006, “Achieving Expected Depth of Shade in Reactive Dye Application Using Artificial Neural Network Technique”, Dyes and Pigments, Vol.68, 89-94.
• 29. Westland, S., Lovıne, L., Bıshop, J., M., 2002, “Kubelka-Munk or Neural Networks for Computer Colorant Formulation”, 9th Congress of the International Color Association, Proceedings of SPI, Vol.4421, 745-748.
• 30. Westland, S., 1998, “Artificial Neural Networks and Colour Recipe Prediction”, Proceedings of the International conference and Exhibition, Colour Science.
• 31. Balcı, O., Oğulata, S., N., Şahin, C., “Predicting of CIELab Data and Wash Fastness of Nylon 6,6 Using Artificial Neural Network and Linear Regression Model”, Fiber&Polymers, (In press).
• 32. Duran, K., 2001, Tekstilde Renk Ölçümü ve Reçete Çıkartma, E.Ü.Tekstil Ve Konfeksiyon Araştırma-Uygulama Merkezi Yayını, Yayın No:17, İzmir.