Optimization of Key Process Parameters for Air-Jet Vortex Spun Yarn

Kexiang Yang

doi:10.62177/jaet.v3i2.1424

Authors

Kexiang Yang Xi’an Polytechnic University

DOI:

https://doi.org/10.62177/jaet.v3i2.1424

Keywords:

Process Parameters, Yarn Formation Process, Air-Jet Vortex Spinning, Quality Control

Abstract

As the latest spinning technology in the world at present, air-jet vortex spinning features a short process and high spinning speed by eliminating the two processes of roving and winding. Nevertheless, many problems related to this technology have not been thoroughly solved. To address the difficulty in identifying the key process parameters during yarn formation in air-jet vortex spinning, the input-output relationship of process parameters in the yarn formation process is first analyzed. Based on the collected production process data, a method for screening and optimizing key process parameters is proposed by integrating recursive feature elimination and deep neural network. A deep neural network (DNN) surrogate model is constructed. On the basis of orthogonal experimental design data (L₂₇(3¹³)), a high-precision nonlinear mapping between process parameters and quality indices is established. Experimental results show that the average relative error between the predicted values and the measured values of the model is below 3.85%. On this basis, the optimal combination of process parameters (A2B1C3D1E3F1G2H3) that takes into account four quality indices is determined.

Downloads

Download data is not yet available.

References

Alam, K., Rahman, M., Li, M., et al. (2025). Development and characterization of air jet vortex yarn with novel fiber blends. SPE Polymers, 6(1).

Ingle, N., & Jasper, W. J. (2025). A review of deep learning within the framework of artificial intelligence for enhanced fiber and yarn quality. Textile Research Journal, 95(7–8), 904–933. DOI: https://doi.org/10.1177/00405175241265510

Doran, E. C., & Sahin, C. (2020). The prediction of quality characteristics of cotton/elastane core yarn using artificial neural networks and support vector machines. Textile Research Journal, 90(13–14), 1558–1580. DOI: https://doi.org/10.1177/0040517519896761

Wang, M., Wang, J., Gao, W., et al. (2023). One-dimensional convolutional neural network with data characterization measurement for cotton yarn quality prediction. Cellulose, 30(6), 4025–4039. DOI: https://doi.org/10.1007/s10570-023-05108-9

Bhargava, D. (n.d.). Revolutionizing textile quality control with AI: A path to zero defects.

Liu, Z. Y., Chen, N. L., & Wang, J. (2023). Yarn quality prediction for small samples based on AdaBoost algorithm. Journal of Donghua University (English Edition), 40(3).

Chattopadhyay, R. (2025). Yarn structure properties relationship. In Developments in yarn spinning technologies (pp. 159–186). Elsevier Science Ltd. DOI: https://doi.org/10.1016/B978-0-443-13887-4.00008-9

Erdumlu, N., Ozipek, B., Oztuna, A. S., et al. (2009). Investigation of vortex spun yarn properties in comparison with conventional ring and open-end rotor spun yarns. Textile Research Journal, 79(7), 585–595. DOI: https://doi.org/10.1177/0040517508093590

Basal, G. (2003). The structure and properties of vortex and compact spun yarns. North Carolina State University.

Ortlek, H. G. (2006). Influence of selected process variables on the mechanical properties of core-spun vortex yarns containing elastane. Fibres and Textiles in Eastern Europe, 14(3), 42.

Alam, K., Rahman, M., Li, M., et al. (2025). Development and characterization of air jet vortex yarn with novel fiber blends. SPE Polymers, 6(1), e10158. DOI: https://doi.org/10.1002/pls2.10158

Pei, Z., Wang, X., Li, Z., et al. (2021). Effect of process and nozzle structural parameters on the wrapping quality of core-spun yarns produced on a modified vortex spinning system. Textile Research Journal, 91(15–16), 1841–1856. DOI: https://doi.org/10.1177/0040517521989094

Shang, S., Yu, Z., Sun, G., et al. (2022). Modeling the airflow field of vortex spinning. Textile Research Journal, 92(9–10), 1466–1483. DOI: https://doi.org/10.1177/00405175211056980

Haifeng, F., Zhang, J., Sun, H., et al. (2024). Structure analysis of double comb about jet spinning machine based on CFD. International Journal of Clothing Science and Technology, 36(4), 582–598. DOI: https://doi.org/10.1108/IJCST-07-2023-0101

Xi, C., Wang, J., Wang, Y., et al. (2024). Effects of structural parameters on air consumption and mechanical energy characteristics of airflow in the vortex spinning nozzle. Textile Research Journal, 94(11–12), 1245–1262. DOI: https://doi.org/10.1177/00405175241230083

Liu, G., & Yu, W. (2008). The BP neural network modeling on worsted spinning with grey superior theory and correlation analysis. In 2008 Fourth International Conference on Natural Computation (Vol. 3, pp. 374–378). IEEE. DOI: https://doi.org/10.1109/ICNC.2008.23

Stephan, et al. (1996). The nature of statistical learning theory by V.N. Vapnik. Technometrics, 38(4), 409. DOI: https://doi.org/10.1080/00401706.1996.10484565

Wang, Y., Song, J., Fan, T., et al. (2022). Study of yarn quality prediction model based on fuzzy comprehensive evaluation. Journal of The Institution of Engineers (India): Series E, 103(2), 305–313. DOI: https://doi.org/10.1007/s40034-022-00238-4

Kuo, C. F. J., Tien, C. P., & Chiu, C. H. (2007). Analytical research on intellectual control of yarning characteristics for cotton collocation and rotor spinning. The International Journal of Advanced Manufacturing Technology, 32(7), 764–773. DOI: https://doi.org/10.1007/s00170-005-0396-z

Majumdar, A. (2010). Modeling of cotton yarn hairiness using adaptive neuro-fuzzy inference system. Indian Journal of Fibre & Textile Research, 35(2), 121.

Ethridge, D., & Zhu, R. (1996). Prediction of rotor spun cotton yarn quality: A comparison of neural network and regression algorithms. In Proceedings of the Beltwide Cotton Conference (Vol. 2, pp. 1314–1317).

Sette, S., Boullart, L., & Van Langenhove, L. (1998). Using genetic algorithms to design a control strategy of an industrial process. Control Engineering Practice, 6(4), 523–527. DOI: https://doi.org/10.1016/S0967-0661(98)00046-X

Amin, A. E. (2013). A novel classification model for cotton yarn quality based on trained neural network using genetic algorithm. Knowledge-Based Systems, 39, 124–132. DOI: https://doi.org/10.1016/j.knosys.2012.10.008

Hu, Z., Zhao, Q., & Wang, J. (2019). The prediction model of cotton yarn quality based on artificial recurrent neural network. In International Conference on Applications and Techniques in Cyber Security and Intelligence (pp. 857–866). Springer International Publishing. DOI: https://doi.org/10.1007/978-3-030-25128-4_105

Liu, Z. Y., Li, X. X., Li, L. Q., et al. (2024). Applicability analyses of machine learning algorithm for yarn quality prediction under small samples conditions. Cotton Textile Technology, 52(634).