PREDICTION OF YARN QUALITY BY DEEP BELIEF NEURAL NETWORK

R. Sudha Muthusamy PhD, Research Scholar, Department of Computer Science, CMS College of Science & Commerce, Coimbatore, India
Dr. B. Sumathi Associate professor, Department of Computer Science, CMS College of Science & Commerce, Coimbatore, India

Abstract

Many textile industries are utilizing the artificial intelligence techniques to enhance the production quality and product performance on each phases of production unit. In spinning mills, examining the yarn parameters such as unevenness, strength and mass are considered important for yarn quality prediction. In order to improve the performance of yarn quality, an innovative quality yarn prediction using Deep Belief Neural Network (DBNN) approach for yarn images are proposed. Initially pre-processing of the images is carried out using deinterlacing. Deinterlacing is a process which introduces the missing lines of encoded image sequence on spatiotemporal domain. It is employed to recognize and initialize weight to the important features and biases. It used for determination of the quality among the pair of units on heterogeneity information of the yarn. Feature extraction and feature selection is carried out by constructing the feature vector using principal component analysis. DBNN is employed for obtaining the latent and optimal features which represents the Yarn Evenness, Yarn Strength and Yarn Mass Parameters. It is considered as yarn quality determining features. The quality of the yarn is determined with respect to quality index of the features explored in deep learning processes. Experimental results obtained from the proposed model on identifying the quality of the yarn images is outperforming in terms of scalability and efficiency on comparing it against traditional deep learning architecture such as Convolution Neural Network.

Keywords:

:

: : Yarn Quality, Feature Extraction, Deep Learning, Yarn Evenness, Yarn Hairiness, Deep Learning, Deinterlacing

Full Text:

PDF


References


References: 1. Wang, W., Xin, B., Deng, N., Li, J., & Liu, N. (2018). Single vision based identification of yarn hairiness using adaptive threshold and image enhancement method. Measurement, 128, 220–230. 2. Hadavandi, E., Mostafayi, S., & Soltani, P. (2018). A Grey Wolf Optimizer-based neural network coupled with response surface method for modeling the strength of siro-spun yarn in spinning mills. Applied Soft Computing, 72, 1–13. 3. Jing, J., Huang, M., Li, P., & Ning, X. (2017). Automatic measurement of yarn hairiness based on the improved MRMRF segmentation algorithm. The Journal of the Textile Institute, 109(6), 740–749. 4. Hu, Z., Zhao, Q., & Wang, J. (2018). The prediction model of worsted yarn quality based on CNN–GRNN neural network. Neural Computing and Applications 5. Ghanmi, H & Ghith, A & Benameur, Tarek. (2019). Prediction of rotor-spun yarn quality using hybrid artificial neural network-fuzzy expert system model. Indian Journal of Fibre and Textile Research. 44. 31-38. 6. Zeng, Xianhui & Xing, Pengcheng. (2019). Yarn Quality Prediction for Spinning Production Using the Improved Apriori Algorithms: Proceedings of the Artificial Intelligence on Fashion and Textiles (AIFT) Conference 2018, Hong Kong, July 3–6, 2018. 7. Gonçalves, N., Carvalho, V., Belsley, M., Vasconcelos, R. M., Soares, F. O., & Machado, J. (2015). Yarn features extraction using image processing and computer vision – A study with cotton and polyester yarns. Measurement, 68, 1–15. 8. Shanbeh, Mohsen & Johari, Majid & Zarrebini, M & Barburski, Marcin & Komisarczyk, Agnieszka & Urbaniak, Mariusz. (2019). Effect of a weft yarn spinning system on the shear characteristics of plain woven fabrics. Textile Research Journal. 004051751985531. 9. Blachowicz, T., & Ehrmann, A. (2018). Investigating surface properties of fibers and yarns by image processing and statistical analysis techniques. Applications of Computer Vision in Fashion and Textiles, 105–121. 10. Yildirim, Pelin & Birant, Derya & ALPYILDIZ, Tuba. (2017). Discovering the relationships between yarn and fabric properties using association rule mining. TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES. 25. 4788-4804. 11. Haleem, Noman & Gordon, Stuart & Liu, Xin & Hurren, Christopher & Wang, Xungai. (2018). Dynamic analysis of spinning triangle geometry part 1: validation of methodology. The Journal of The Textile Institute. 110. 1-11. 12. Ghanmi, Hanen & Ghith, Adel & Benameur, Tarek. (2016). Open-End Yarn Properties Prediction Using HVI Fibre Properties and Process Parameters. Autex Research Journal. 17. 13. Zhenlong, Hu & Qiang, Zhao & Jun, Wang. (2018). The Prediction Model of Cotton Yarn Intensity Based on the CNN-BP Neural Network. Wireless Personal Communications. 102. 14. Li, Zhongjian & Pan, Ruru & Zhang, Jie & Li, Bianbian & Gao, Weidong & Bao, Wei. (2016). Measuring the unevenness of yarn apparent diameter from yarn sequence images. Measurement Science and Technology. 27. 015404. 15. Wang, Lei & Xu, Bugao & Gao, Weidong. (2016). Multi-perspective measurement of yarn hairiness using mirrored images. Textile Research Journal. 88. 004051751668528. 16. Zhu, Bo & Li, Zhongjian & Cao, Xinwei & Liu, Jianli & Gao, Weidong. (2018). Dynamic Measurement of Foam-Sized Yarn Properties from Yarn Sequence Images. Autex Research Journal. 18.

Refbacks

  • There are currently no refbacks.