Main Article Content
In this paper, neural network is used as the tool to study the factors affecting the air flow resistance and the permeability of electrospun nanofiber nonwovens and analyze the major factors affecting the air flow resistance and the permeability such as concentration, distance, voltage and solution filling speed. First, design a five-level orthogonal table for all factors in accordance with the orthogonal experiment theory, select the corresponding parameter values, use polyvinyl alcohol (PVA) to prepare 50 samples on DXES-01 automatic electrostatic spinning machine, train them with neural network model and obtain the precise fitting function. The optimization function is constructed by the idea of two- objective optimization, and its three relative optimal values are calculated, 8.135611, 8.134624, 8.115814. Compared with the experimental results, the average relative error is 12.89 and 8.34. The experimental results show that the error is also ideal.
Ki Myoung Yuna, Adi Bagus Suryamasa, Ferry Iskandara, Li Baoc, Hitoshi Niinumac, Kikuo Okuyamaa. Morphology optimization of polymer nanofiber for applications in aerosol particle filtration. Separation and Purification Technology. 2010;75:340–345.
Senem Kursun Bahadir, Fatma Kalaoglu, Simona Jevsnik, Selin Hanife Eryuruk, Canan Saricam. Use of artificial neural networks for modelling the drape behaviour of woollen fabrics treated with dry finishing processes. Fibres & Textiles in Eastern Europe. 2015;2(110):90-99.
Haghighat E, Johari MS, Etrati SM, Tehran MA. Study of the hairiness of polyester-viscose blended yarns. Part III - Predicting Yarn Hairiness Using an Artificial Neural Network. Fibres & Textiles in Eastern Europe. 2012;1(90):33-38.
Hadley Brooks, Nick Tucker. Electrospinning predictions using artificial neural networks. Polymer. 2015;58:22-29.
Ya Liu, Xiaoning Jiao, Yi Zhang, Yuanlin Ren. The study on moisture-penetrability of electrospinning fabrics. Industrial Textiles. 2004;169(10):21-26.
Vapink V. The nature of statistical learning theory [M]. New York: Springer Verlag; 1995.
Xuanmin Zhao. Design of Experiment, Science Press; 2009.
Hong Ni, Yonghui Pan. Predictions on the slant flexural properties of fabrics based on BP neural network [J]. Journal of Textile Research. 2009;2:48-51.
Written by Vladimir N. Vapnic, translated by Xuegong Zhang, The Nature of Statistical Learning Theory. 1st Edition; 2000.
Ying Chen, Rudong Chen. Study on the rigidity and flexibility of spunlaced non-woven fabrics. Journal of Tianjin Polytechnic University. 2012;31(1):28-32.
Senem Kursun Bahadir, Fatma Kalaoglu, Simona Jevsnik, Selin Hanife Eryuruk, Canan Saricam. Use of artificial neural networks for modelling the drape behaviour of woolen fabrics treated with dry finishing processes, Fibres & Textiles in Eastern Europe. 2015;2(110):90-99.
Małgorzata Matusiak. Application of artificial neural networks to predict the air permeability of woven fabrics. Fibres & Textiles in Eastern Europe. 2015;1(109): 41-48.
Xuemin Shi, Rudong Chen, Xionghua Wu, Xiaonong Fan, Hao Chang, Xiaobo Li. Study on mathematical model of treating brain infarction with acupuncture of Neiguan point based on BP neural network. Chinese Journal of Engineering Mathematics. 2009;26(Supp): 37-46.
Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins. Digital image processing using MATLAB (Second Edition), Electronic Industry Press; 2013.
Chun’an Liu. Dynamic multiple objectives optimization algorithm and its applications. Science Press; 2011.