Published April 5, 2026 | Version v1
Journal article Open

Artificial Intelligence and Machine Learning Applications in the Textile Industry: A Review

Authors/Creators

  • 1. Textile Technology and Management, Technology Consultant, NC State University, Raleigh, NC

Description

The textile industry is undergoing a transformation driven by Artificial Intelligence (AI) and Machine Learning (ML),
progressing toward the "Fashion 4.0" paradigm. In this review, a systematic evaluation is carried out for AI and ML
applications across the textile lifecycle, fiber classification, yarn production, fabric formation, dyeing, printing, quality
control, supply chain management, and sustainability. Drawing on peer-reviewed studies published between 2015 and
2026, the review reports experimental performance benchmarks, such as convolutional neural networks (CNNs) achieving
over 99% accuracy in fabric defect detection. Furthermore, ML-based dyeing optimization reduces water consumption and
chemical usage. LSTM and Transformer-based models improve demand forecasting accuracy relative to statistical
baselines. Persistent challenges include data scarcity, model interpretability, and integration with legacy systems. The
review also identifies future research directions, including federated learning, digital twins, and foundation models.
Overall, these findings indicate that AI and ML technologies can substantially enhance production efficiency, product
quality, and environmental sustainability in the textile industry.

Files

Artificial Intelligence and Machine Learning Applications in the Textile.pdf

Files (309.8 kB)

Additional details

References

  • Spherical Insights. (2025). Global textile and apparel market: Forecast analysis report. https://www.sphericalinsights.com
  • Statista. (2023). Global apparel market revenue 2015–2026. Statista Research Department.
  • Giri, C., & Chen, Y. (2022). Deep learning for demand forecasting in the fashion and apparel retail industry. Forecasting, 4(2), 565–581. https://doi.org/10.3390/forecast4020031
  • Awasthi, K., Padwekar, K., Shamim, K., & Misra, S. C. (2025). Sustainable synergy: Transforming the textile sector by leveraging Industry 5.0 enablers. Sustainable Development, 1–21. https://doi.org/10.1002/sd.70336
  • Tu, Y. F., Kwan, M. Y., & Yick, K. L. (2024). Asystematic review of AI-driven prediction of fabric properties and handfeel. Materials, 17(20), 5009. https://doi.org/10.3390/ma17205009
  • Majumdar, A., & Majumdar, P. K. (2004). Predicting the breaking elongation of ring spun cotton yarns using mathematical, statistical and artificial neural network models. Textile Research Journal, 74(7), 652–655
  • de Carvalho, P. T., Lopes, J. D., & Raimundo, R. J. (2025). Innovation impact in the textile industry: From the Toyota Production System to artificial intelligence. Sustainability, 17(3), 1170. https://doi.org/10.3390/su17031170
  • Xu, S., Cheng, S., Jin, S., Hu, X., Wu, W., & Xiang, Z. (2025). Industrial fabric defect-generative adversarial network (IFD-GAN): High-fidelity fabric cross-scale defect samples synthesis method for enhancing automated recognition performance. Engineering Applications of Artificial Intelligence, 161(Part C), 112296. https://doi.org/10.1016/j.engappai.2025.112296
  • Toufique Ahmed, A. S. M. J. (2025). Structuring a textile knitting dataset for machine learning and data mining applications. Data in Brief, 61, 111873. https://doi.org/10.1016/j.dib.2025.111873