MUET logo

Optimizing Twill Fabric Structure’s Tensile Strength: A Multi-Objective Approach with Artificial Neural Networks as Prediction Models

Authors

  • Zulfiqar Ali

    Department of Textile Engineering, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Zubair Khaliq

    Department of Materials, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Ali Afzal

    Department of Textile Engineering, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Muhammad Bilal Qadir

    Department of Textile Engineering, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Fayyaz Ahmad

    Department of Applied Sciences, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Badar Munir Zaidi

    Department of Textile Engineering, National Textile University, Faisalabad 37610, Pakistan
    Author

  • Amir Shahzad

    Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hung Hom, Kowloon 999077, Hong Kong
    Author

  • Ammara Phool

    Department of Applied Sciences, National Textile University, Faisalabad 37610, Pakistan
    Author

DOI:

https://doi.org/10.22581/muet1982.0369

Keywords:

Artificial Neural Networks, Bayesian Regularization, Machine Learning, Tensile Strength, Twill Fabric, Multi-Objective Optimization

Abstract

This study investigates the prediction and multi-objective optimization of tensile strength in woven twill fabrics using artificial neural networks (ANNs). A dataset of 135 fabric samples was developed using yarn tensile strength in the warp and weft directions, ends per inch, and picks per inch as predictors, with fabric tensile strength in the warp and weft directions as responses. Feed-forward ANN models with multiple hidden layers were trained using backpropagation and Bayesian regularization. The optimized models showed strong agreement with laboratory measurements. For warp-direction tensile strength, the correlation coefficients were 0.9998 for training, 0.9991 for testing, and 0.9997 for the complete dataset. For weft-direction tensile strength, the corresponding values were 1.0000, 0.99907, and 0.99994. The maximum and mean absolute errors were 8.4093 and 1.7588, respectively, for the warp direction, and 6.4159 and 0.37005 for the weft direction. The maximum percentage errors were 2.8719% and 4.28048%, respectively. A minimax-based multi-objective optimization identified the optimum manufacturing conditions as warp- and weft-yarn strengths of 495.36, 81 ends/in, and 81.9 picks/in. Experimental validation under these conditions produced tensile strengths of 585 in the warp direction and 660 in the weft direction. The results demonstrate that Bayesian-regularized ANN models can accurately predict twill-fabric tensile strength and provide practical manufacturing parameters for quality improvement and structural optimization.

Downloads

References

[1] G. Riello and T. Roy, How India Clothed the World: The World of South Asian Textiles, 1500-1850 (Volume 4). Brill, 2009.

[2] A. Majumdar, A. Ghosh, S. S. Saha, A. Roy, S. Barman, D. Panigrahi, and A. Biswas, “Empirical modelling of tensile strength of woven fabrics,” Fibers Polym., vol. 9, no. 2, Apr. 2008, doi: 10.1007/s12221-008-0038-9.

[3] H. Gabrijelčič, E. Černoša, and K. Dimitrovski, “Influence of weave and weft characteristics on tensile properties of fabrics,” Fibres and Text. East. Eur., vol. 16, no. 2, 2008.

[4] R. Chattopadhyay, “Design of Apparel Fabrics: Role of fibre, yarn and fabric parameters on its functional attributes,” J. Text. Eng., vol. 54, no. 6, 2008.

[5] M. Realff, M. Boyce, and S. Backer, “A micromechanical model of the tensile behavior of woven fabric,” Text. Res. J., vol. 67, no. 6, 1997.

[6] F. T. Peirce, “5—The geometry of cloth structure,” J. Text. Inst. Trans., vol. 28, no. 3, 1937.

[7] L. Love, “Graphical relationships in cloth geometry for plain, twill, and sateen weaves,” Text. Res. J., vol. 24, no. 12, 1954.

[8] H. Taylor, “9—Tensile and tearing strength of cotton cloths,” J. Text. Inst. Trans., vol. 50, no. 1, 1959.

[9] V. Milasius and V. Reklaitis, “The principles of weave-coding,” J. Text. Inst., vol. 79, no. 4, 1988.

[10] J. Thanikai Vimal, C. Prakash, and A. Jebastin Rajwin, “Effect of weave parameters on the tear strength of woven fabrics,” J. Nat. Fibers, vol. 17, no. 9, 2020.

[11] J. Hamilton, “7—A general system of woven-fabric geometry,” J. Text. Inst. Trans., vol. 55, no. 1, 1964.

[12] A. Newton, “The comparison of woven fabrics by reference to their tightness,” J. Text. Inst., vol. 86, no. 2, 1995.

[13] S. De Jong and R. Postle, “39—An Energy Analysis of Woven-Fabric Mechanics by Means of Optimal-Control Theory Part I: Tensile Properties,” J. Text. Inst., vol. 68, no. 11, 1977.

[14] S. de Jong and R. Postle, “40—An Energy Analysis of Woven-Fabric Mechanics by Means of Optimal-Control Theory Part II: Pure-Bending Properties,” J. Text. Inst., vol. 68, no. 11, 1977.

[15] F. Sun, A. M. Seyam, and B. Gupta, “A generalized model for predicting load-extension properties of woven fabrics,” Text. Res. J., vol. 67, no. 12, 1997.

[16] G. Baser, “A Mechanical Approach to the Determination of the Geometry of a Woven Fabric and to the Analysis of Subsequent Changes in This Geometry Part II: The Development of a Geometry of Plain-woven Fabric in the Loomstate and a Theory of Weaving Contractions,” J. Text. Inst., vol. 80, no. 4, 1989.

[17] G. Baser, “A Mechanical Approach to the Determination of the Geometry of a Woven Fabric and to the Analysis of Subsequent Changes in This Geometry Part I: A Theory for the Crimping of the Weft Yarn during Weaving,” J. Text. Inst., vol. 80, no. 4, 1989.

[18] G. Leaf and R. Anandjiwala, “A generalized model of plain woven fabric,” Text. Res. J., vol. 55, no. 2, 1985.

[19] A. Shahpurwala and P. Schwartz, “Modeling woven fabric tensile strength using statistical bundle theory,” Text. Res. J., vol. 59, no. 1, 1989.

[20] Z. A. Malik, M. H. Malik, T. Hussain, and F. A. Arain, “Development of Models to Predict Tensile Strength of Cotton Woven Fabrics,” J. Eng. Fiber. Fabr., vol. 6, no. 4, Dec. 2011, doi: 10.1177/155892501100600407.

[21] G. Chen and X. Ding, “Breaking progress simulation and strength prediction of woven fabric under uni-axial tensile loading,” Text. Res. J., vol. 76, no. 12, 2006.

[22] H. Rahmanifard and T. Plaksina, “Application of artificial intelligence techniques in the petroleum industry: a review,” Artif. Intell. Rev., vol. 52, no. 4, 2019.

[23] O. I. Abiodun, A. Jantan, A. E. Omolara, K. V Dada, N. A. Mohamed, and H. Arshad, “State-of-the-art in artificial neural network applications: A survey,” Heliyon, vol. 4, no. 11, 2018.

[24] D. Balram, K.-Y. Lian, N. Sebastian, F. S. Al-Mubaddel, and M. T. Noman, “Bi-functional renewable biopolymer wrapped CNFs/Ag doped spinel cobalt oxide as a sensitive platform for highly toxic nitroaromatic compound detection and degradation,” Chemosphere, vol. 291, 2022.

[25] X. Liu, F. Gasco, J. Goodsell, and W. Yu, “Initial failure strength prediction of woven composites using a new yarn failure criterion constructed by deep learning,” Compos. Struct., vol. 230, 2019.

[26] P. U. Kurup and N. K. Dudani, “Neural networks for profiling stress history of clays from PCPT data,” J. Geotech. Geoenvironmental Eng., vol. 128, no. 7, 2002.

[27] G. L. Yoon and B. T. Kim, “Regression analysis of compression index for Kwangyang marine clay,” KSCE J. Civ. Eng., vol. 10, 2006.

[28] N. Amor, M. T. Noman, and M. Petru, “Prediction of functional properties of nano TiO2 coated cotton composites by artificial neural network,” Sci. Rep., vol. 11, no. 1, 2021.

[29] A. L. Runehov, L. Oviedo, and N. P. Azari, Encyclopedia of sciences and religions. Springer Netherlands Dordrecht, 2013.

[30] K. L. Petri, R. E. Billo, and B. Bidanda, “A neural network process model for abrasive flow machining operations,” J. Manuf. Syst., vol. 17, no. 1, 1998.

[31] N. Ingle and W. J. Jasper, “A review of deep learning within the framework of artificial intelligence for enhanced fiber and yarn quality,” Text. Res. J., vol. 95, no. 7–8, Apr. 2025, doi: 10.1177/00405175241265510.

[32] W. Dong, J. Liang, and S. Suh, “Effectiveness of AI Technologies in Reducing Textile Waste in the Fashion Industry,” Text. Res. J., vol. 96, no. 3–4, Feb. 2026, doi: 10.1177/00405175251357582.

[33] R. Messnaoui, M. El Bakkali, M. Elkhaoudi, O. Cherkaoui, and A. Soulhi, “Predicting the tensile strength of a new fabric using artificial intelligence (fuzzy logic),” Data Metadata, vol. 4, Jan. 2025, doi: 10.56294/dm2025666.

[34] I. Malashin, D. Martysyuk, V. Tynchenko, A. Gantimurov, V. Nelyub, A. Borodulin, and A. Galinovsky, “Machine Learning in Polymeric Technical Textiles: A Review,” Polymers (Basel)., vol. 17, no. 9, Apr. 2025, doi: 10.3390/polym17091172.

[35] H. Sharma, G. Arora, M. K. Singh, V. Ayyappan, P. Bhowmik, S. M. Rangappa, and S. Siengchin, “Review of machine learning approaches for predicting mechanical behavior of composite materials,” Discov. Appl. Sci., vol. 7, no. 11, Oct. 2025, doi: 10.1007/s42452-025-07616-8.

[36] L.-J. Kao and C. C. Chiu, “Application of integrated recurrent neural network with multivariate adaptive regression splines on SPC-EPC process,” J. Manuf. Syst., vol. 57, 2020.

[37] J. Wang, Y. Ma, L. Zhang, R. X. Gao, and D. Wu, “Deep learning for smart manufacturing: Methods and applications,” J. Manuf. Syst., vol. 48, 2018.

[38] Y. Zhang, X. Gao, and S. Katayama, “Weld appearance prediction with BP neural network improved by genetic algorithm during disk laser welding,” J. Manuf. Syst., vol. 34, 2015.

[39] D. Lu and W. Yu, “Predicting the tensile strength of single wool fibers using artificial neural network and multiple linear regression models based on acoustic emission,” Text. Res. J., vol. 91, no. 5–6, 2021.

[40] S. A. Malik, A. Farooq, T. Gereke, and C. Cherif, “Prediction of blended yarn evenness and tensile properties by using artificial neural network and multiple linear regression,” Autex Res. J., vol. 16, no. 2, 2016.

[41] F. Liu, W. Ding, Y. Qiao, and L. Wang, “An artificial neural network model on tensile behavior of hybrid steel-PVA fiber reinforced concrete containing fly ash and slag power,” Front. Struct. Civ. Eng., vol. 14, 2020.

[42] A. Hussain, A. H. Sakhaei, and M. Shafiee, “Machine learning-based constitutive modelling for material nonlinearity: A review,” Mech. Adv. Mater. Struct., vol. 33, no. 1, Dec. 2026, doi: 10.1080/15376494.2024.2439557.

[43] A. M. Ghaedi and A. Vafaei, “Applications of artificial neural networks for adsorption removal of dyes from aqueous solution: a review,” Adv. Colloid Interface Sci., vol. 245, 2017.

[44] H. Bilal, R. A. Shah, H. Ahmad, A. Jan, and T. Radwan, “An intelligent framework for modeling nonlinear irreversible biochemical reactions using artificial neural networks,” Sci. Rep., vol. 15, no. 1, Aug. 2025, doi: 10.1038/s41598-025-13146-5.

[45] J. Otoo, S. Nasiru, and I. D. Angbing, “Shifted Hexpo activation function: An improved vanishing gradient mitigation activation function for disease classification,” Mach. Learn. with Appl., vol. 20, Jun. 2025, doi: 10.1016/j.mlwa.2025.100651.

[46] J. Terven, D.-M. Cordova-Esparza, J.-A. Romero-González, A. Ramírez-Pedraza, and E. A. Chávez-Urbiola, “A comprehensive survey of loss functions and metrics in deep learning,” Artif. Intell. Rev., vol. 58, no. 7, Apr. 2025, doi: 10.1007/s10462-025-11198-7.

[47] D. J. C. Mackay, “Bayesian methods for adaptive models,” California Institute of Technology, 1992.

[48] N. Akram, R. A. Butt, and M. A. Qureshi, “Modification of a convolutional neural network for the weave pattern classification,” Mehran Univ. Res. J. Eng. Technol., vol. 43, no. 2, Apr. 2024, doi: 10.22581/muet1982.2998.

[49] N. Amor, M. T. Noman, A. Ismail, M. Petru, and N. Sebastian, “Use of an Artificial Neural Network for Tensile Strength Prediction of Nano Titanium Dioxide Coated Cotton,” Polymers (Basel)., vol. 14, no. 5, Feb. 2022, doi: 10.3390/polym14050937.

[50] E. Sariev and G. Germano, “Bayesian regularized artificial neural networks for the estimation of the probability of default,” Quant. Financ., vol. 20, no. 2, Feb. 2020, doi: 10.1080/14697688.2019.1633014.

[51] F. D. Foresee and M. T. Hagan, “Gauss-Newton approximation to Bayesian learning,” in Proceedings of International Conference on Neural Networks (ICNN’97), IEEE, 1997.

Published

2026-07-01

Issue

Vol. 45 No. 3 (2026): July Issue

Section

Articles

License

Copyright (c) 2026 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

Optimizing Twill Fabric Structure’s Tensile Strength: A Multi-Objective Approach with Artificial Neural Networks as Prediction Models. (2026). Mehran University Research Journal of Engineering and Technology, 45(3), 01-24. https://doi.org/10.22581/muet1982.0369

Similar Articles

91-95 of 95

You may also start an advanced similarity search for this article.