人工智能在纺织印染行业中的应用研究进展

doi:10.13475/j.fzxb.20250404402

Abstract

Abstract:

Significance Dyeing and finishing industry, a cornerstone of traditional textile manufacturing, is at a critical juncture. It faces a confluence of modern challenges, including rising consumer demand for personalized products, increasingly stringent environmental regulations, and intense global market competition. The industry's conventional production models, which rely heavily on empirical experience, are proving inadequate, often leading to low efficiency, high consumption of resources, and inconsistent product quality. Artificial Intelligence (AI) has emerged as a key enabling technology to navigate these complexities. By leveraging its powerful capabilities in data processing, pattern recognition, and predictive optimization, AI offers a transformative pathway for the industry to achieve intelligent, green, and highly efficient manufacturing. This review provides a systematic evaluation of recent progress in AI applications across the textile dyeing and finishing landscape, aiming to clarify the current state of AI adoption, identify key challenges, and chart a course for its future trajectory in the industry.

Progress AI is being integrated into every stage of the textile dyeing process, yielding significant advancements. In dye design, AI revolutionizes development by accurately predicting crucial properties (e.g. maximum absorption wavelength(λ_max), solubility) pre-synthesis and facilitating high-throughput virtual screening, dramatically accelerating the discovery of novel dyes. For color management, AI overcomes the limitations of traditional methods. It learns the complex relationship between color attributes and dye recipes from data, solves the "one-to-many" recipe problem, and mitigates metamerism by integrating with hyperspectral imaging. In process optimization, AI introduces a new level of precision. It predicts key dyeing outcomes (e.g., K/S value, exhaustion rates), allowing for the optimization of dyeing conditions to minimize resource consumption and maximize quality. It also solves complex production scheduling problems and enables real-time anomaly monitoring. For quality inspection, AI is driving the shift towards full automation. Unsupervised, reconstruction-based methods have become the dominant solution for defect detection, effectively addressing the challenge of scarce defect samples. A forward-looking application is "dyeing-free" quality prediction, where spectroscopy and ML are used to analyze raw materials to predict their final dyeing uniformity.

Conclusion and Prospect AI technologies are fundamentally reshaping the textile dyeing and finishing industry, demonstrating immense potential to enhance innovation, efficiency, and sustainability. Research has led to clear achievements in accelerating dye discovery, improving color recipe accuracy, optimizing resource utilization, and automating quality control. However, widespread adoption of AI technology faces significant hurdles. These include a critical lack of high-quality, standardized industry data, challenges in ensuring model robustness and generalization from lab environments to real-world production fluctuations, and the high technical and financial costs of integrating AI systems into the existing manufacturing infrastructure. Future research must focus on overcoming these barriers through a more integrated approach. Key priorities should be given to developing inverse design models for dyes that simultaneously optimize multiple objectives (color, fastness, eco-toxicity), creating digital twin systems for holistic process control, and advancing quality systems from "post-process detection" to "in-process prediction" by fusing multi-modal data. Ultimately, the goal is to connect these disparate AI applications into a cohesive, closed-loop intelligent manufacturing system that spans the entire production chain. Achieving this vision will unlock AI's full potential to build a smarter, greener, and more competitive textile industry.

Key words: dyeing and finishing, artificial intelligence, dye design, color matching, process optimization, quality inspection, machine learning, deep learning

CLC Number:

TP18

ZHOU Qingqing, CHANG Shuo, MAO Zhiping, WU Wei. Research progress in applications of artificial intelligence in dyeing and finishing industry[J].Journal of Textile Research, 2025, 46(12): 260-269.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.fzxb.org.cn/EN/10.13475/j.fzxb.20250404402

http://www.fzxb.org.cn/EN/Y2025/V46/I12/260

References 60

[1]	SHAO J N, LIU Y, YAN J Q, et al. Prediction of maximum absorption wavelength using deep neural net-works[J]. Journal of Chemical Information and Modeling, 2022, 62(6): 1368-1375. doi: 10.1021/acs.jcim.1c01449
[2]	XIA Y H, WANG G C, LV Y Z, et al. Prediction of light absorption properties of organic dyes using machine learning technology[J]. Chemical Physics Letters, 2024, 836: 141030. doi: 10.1016/j.cplett.2023.141030
[3]	MAI J Q, LU T, XU P C, et al. Predicting the maximum absorption wavelength of azo dyes using an interpretable machine learning strategy[J]. Dyes and Pigments, 2022, 206: 110647. doi: 10.1016/j.dyepig.2022.110647
[4]	LUKANOV M M, KSENOFONTOV A A. Using graph neural networks to predict positions of the absorption maxima of a number of dyes[J]. Russian Journal of Physical Chemistry A, 2024, 98(14): 3342-3346. doi: 10.1134/S003602442470287X
[5]	GUPTA A, CHAKRABORTY S, GHOSH D, et al. Data-driven modeling of S₀ → S₁ excitation energy in the BODIPY chemical space: high-throughput computation, quantum machine learning, and inverse design[J]. Journal of Chemical Physics, 2021, 155(24): 244102. doi: 10.1063/5.0076787
[6]	HU J H, TAMURA K, YAN J. Solubility measurements of anthraquione disperse dyestuffs in supercritical carbon dioxide and neural network modeling[J]. The Journal of Chemical Thermodynamics, 2024, 188: 107161. doi: 10.1016/j.jct.2023.107161
[7]	YAN J, DU S, HU J H, et al. Solubility prediction of CI Disperse Red 4 and CI Disperse Red 15 in supercritical carbon dioxide based on the back propagation neural network[J]. Coloration Technology, 2024, 140(2): 230-238. doi: 10.1111/cote.v140.2
[8]	GONZÁLEZ-DE-LA-CRUZ S, BONILLA-PETRICIOLET A. A machine learning technique based on group contributions to calculate the solubility of dye molecules in supercritical CO₂[J]. Fluid Phase Equilibria, 2024, 577: 113981. doi: 10.1016/j.fluid.2023.113981
[9]	KSENOFONTOV A A, LUKANOV M M, BOCHAROV P S. Can machine learning methods accurately predict the molar absorption coefficient of different classes of dyes?[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 279: 121442. doi: 10.1016/j.saa.2022.121442
[10]	MAHATO K D, DAS S S G K, AZAD C, et al. Stokes shift prediction of fluorescent organic dyes using machine learning based hybrid cascade models[J]. Dyes and Pigments, 2024, 222: 111918. doi: 10.1016/j.dyepig.2023.111918
[11]	MAHATO K D, KUMAR U. Optimized Machine learning techniques Enable prediction of organic dyes photophysical Properties: absorption Wavelengths, emission wavelengths, and quantum yields[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 308: 123768. doi: 10.1016/j.saa.2023.123768
[12]	JU C W, BAI H Z, LI B, et al. Machine learning enables highly accurate predictions of photophysical properties of organic fluorescent materials: emission wavelengths and quantum yields[J]. Journal of Chemical Information and Modeling, 2021, 61(3): 1053-1065. doi: 10.1021/acs.jcim.0c01203
[13]	LI Y, LUO Y, HE Q. Chemical footprint of textile and apparel products: an assessment of human and ecological toxicities based on USEtox model[J]. The Journal of the Textile Institute, 2020, 111(7): 960-971. doi: 10.1080/00405000.2019.1710907
[14]	HUSSAIN TAHIR M, KADYROV T, MOHAMED MOUSSA I. Data-driven designing of dyes: chemical space generation and dipole moment prediction[J]. Materials Science and Engineering: B, 2025, 311: 117792. doi: 10.1016/j.mseb.2024.117792
[15]	GUAN Y R, TAHIR M H, RIYAD Y M, et al. Generation of chemical library of near-IR dyes for photovoltaics applications[J]. Dyes and Pigments, 2024, 231: 112429. doi: 10.1016/j.dyepig.2024.112429
[16]	AHMAD N, EID G, EL-TOONY M M, et al. Harnessing machine learning for the rational design of high-performance fluorescent dyes[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2025, 334: 125918. doi: 10.1016/j.saa.2025.125918
[17]	LIU S C, CHEN D, ZHANG F X, et al. Machine learning assisted prediction of disperse dye exhaustion on polylactic acid fiber with interpretable model[J]. Dyes and Pigments, 2025, 237: 112693. doi: 10.1016/j.dyepig.2025.112693
[18]	YU C B, CAO W G, LIU Y Q, et al. Evaluation of a novel computer dye recipe prediction method based on the PSO-LSSVM models and single reactive dye data-base[J]. Chemometrics and Intelligent Laboratory Systems, 2021, 218: 104430. doi: 10.1016/j.chemolab.2021.104430
[19]	LI F, CHEN C T, MAO Z P. A novel approach for recipe prediction of fabric dyeing based on feature-weighted support vector regression and particle swarm optimisation[J]. Coloration Technology, 2022, 138(5): 495-508. doi: 10.1111/cote.v138.5
[20]	ZHANG J X, ZHANG X N, WU J K, et al. Dyeing recipe prediction of cotton fabric based on hyperspectral colour measurement and an improved recurrent neural network[J]. Coloration Technology, 2021, 137: 166-180. doi: 10.1111/cote.v137.2
[21]	YU C B, CAO W G, WANG Q X, et al. Prediction of the reactive dye recipe in cotton fabric dyeing using the pad-dry-pad-steam process by particle swarm optimisation-least squares support vector machine with matching database[J]. Coloration Technology, 2022, 138(6): 632-639. doi: 10.1111/cote.v138.6
[22]	SOUISSI M, CHAOUCH S, MOUSSA A, et al. Dyeing of advanced denim fabrics (blend of cotton/bicomponent polyester filaments) using different processes and artificial intelligence method[J]. Scientific Reports, 2024, 14(1): 1952. doi: 10.1038/s41598-024-52189-y pmid: 38263417
[23]	QIN X N, ZHANG X J. An industrial dyeing recipe recommendation system for textile fabrics based on data-mining and modular architecture design[J]. IEEE Access, 2021, 9: 136105-136110. doi: 10.1109/ACCESS.2021.3117261
[24]	XIE Y T, ZHANG H, ZHANG S J, et al. A data-driven approach for predicting industrial dyeing recipes of polyester fabrics[J]. Fibers and Polymers, 2024, 25(8): 2985-2991. doi: 10.1007/s12221-024-00624-2
[25]	ALI SHAH S S, JUNAID A, HUSNAIN G, et al. Multi-colour recipe prediction through invertible neural network and clustering algorithm[J]. Coloration Technology, 2025, 141(4): 505-517. doi: 10.1111/cote.v141.4
[26]	DAS S, WAHI A. Digital image analysis using deep learning convolutional neural networks for color matching of knitted cotton fabric[J]. Journal of Natural Fibers, 2022, 19(17): 15716-15722. doi: 10.1080/15440478.2022.2133052
[27]	HASANLOU E, SHAMS-NATERI A, IZADAN H. Instrumental shade sorting of coloured fabrics using genetic algorithm and particle swarm optimisation[J]. Coloration Technology, 2023, 139(4): 454-463. doi: 10.1111/cote.v139.4
[28]	PENG L H, ZHANG X R, LI J Q, et al. Illumination correction of dyed fabrics method using the kernel extreme learning machine based on the improved Aquila Optimizer[J]. Textile Research Journal, 2025, 95(13/14): 1557-1575. doi: 10.1177/00405175241269180
[29]	ZHOU Z Y, JI H D, YANG X F. Illumination correction of dyed fabric based on extreme learning machine with improved ant lion optimizer[J]. Color Research & Application, 2022, 47(4): 1065-1077. doi: 10.1002/col.v47.4
[30]	黄敏, 郭春丽, 何瑞丽, 等. 用聚类分析的方法分类观察者颜色匹配函数[J]. 光谱学与光谱分析, 2020, 40(2): 454-460.
	HUANG Min, GUO Chunli, HE Ruili, et al. Classification of Color Matching Functions with the Method of Cluster Analysis[J]. Spectroscopy and Spectral Analysis, 2020, 40(2): 454-460.
[31]	LI J, HANSELAER P, SMET K A G. Impact of matching field size on color matching (functions) accuracy[J]. Color Research and Application, 2023, 48(1): 88-102. doi: 10.1002/col.v48.1
[32]	WU F, HSIAO S W, LU P. An AIGC-empowered methodology to product color matching design[J]. Displays, 2024, 81: 102623. doi: 10.1016/j.displa.2023.102623
[33]	PERVEZ M N, YEO W S, LIN L N, et al. Optimization and prediction of the cotton fabric dyeing process using Taguchi design-integrated machine learning approach[J]. Scientific Reports, 2023, 13(1): 12363. doi: 10.1038/s41598-023-39528-1 pmid: 37524835
[35]	ZHANG Z, SUN F Y, LI Q L, et al. Establishment of the predicting models of the dyeing effect in supercritical carbon dioxide based on the generalized regression neural network and back propagation neural net-work[J]. Processes, 2020, 8(12): 1631. doi: 10.3390/pr8121631
[36]	SHAHMORADI GHAHEH F, RAZBIN M, TEHRANI M, et al. Modeling and optimization of dyeing process of polyamide 6 and woolen fabrics with plum-tree leaves using artificial intelligence[J]. Scientific Reports, 2024, 14: 15067. doi: 10.1038/s41598-024-64761-7 pmid: 38956163
[37]	CHEN J, LIN Y Y, LIU Y. Fast prediction of optimal reaction conditions and dyeing effects of natural dyes on silk fabrics by lightweight integrated learning (XG-Boost) models[J]. Coloration Technology, 2025, 141(2): 223-237. doi: 10.1111/cote.v141.2
[38]	ZHANG J X, HUANG X J, ZHENG H Y, et al. Segmented modelling and analysis of disperse dye concentration based on multidimensional spectrum[J]. Coloration Technology, 2024, 140(2): 287-299. doi: 10.1111/cote.v140.2
[39]	ZHOU Y Q, WANG J L, ZHANG P, et al. Research on dyeing workshop scheduling methods for knitted fabric production based on a multi-objective hybrid genetic algorithm[J]. Measurement and Control, 2020, 53(7/8): 1529-1539. doi: 10.1177/0020294020944947
[40]	WANG J, LI D B, TANG H T, et al. A dynamical teaching-learning-based optimization algorithm for fuzzy energy-efficient parallel batch processing machines scheduling in fabric dyeing process[J]. Applied Soft Computing, 2024, 167: 112413. doi: 10.1016/j.asoc.2024.112413
[41]	PARK K T, KANG Y T, YANG S G, et al. Cyber physical energy system for saving energy of the dyeing process with industrial Internet of Things and manufacturing big data[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2020, 7(1): 219-238. doi: 10.1007/s40684-019-00084-7
[42]	HOSSEINI DEHSHIRI S S, FIROOZABADI B. Solar heating as sustainable solution in dyeing industries: a compromise solution approach integrated machine learning[J]. Energy, 2025, 318: 134796. doi: 10.1016/j.energy.2025.134796
[43]	WANG C C, LI Y H. Machine-learning-based system for the detection of entanglement in dyeing and finishing processes[J]. Sustainability, 2022, 14(14): 8575. doi: 10.3390/su14148575
[44]	WANG C C, KUO C H. Detecting dyeing machine entanglement anomalies by using time series image analysis and deep learning techniques for dyeing-finishing process[J]. Advanced Engineering Informatics, 2023, 55: 101852. doi: 10.1016/j.aei.2022.101852
[45]	YU Z Q, XU Y, WANG Y F, et al. Unsupervised fabric defect detection based on multiscale image reconstruction and structural similarity assessment[J]. Coloration Technology, 2024, 140(6): 827-842. doi: 10.1111/cote.v140.6
[46]	WU K, ZHU L, SHI W H, et al. Automated fabric defect detection using multi-scale fusion MemAE[J]. The Visual Computer, 2025, 41(1): 723-737. doi: 10.1007/s00371-024-03358-7
[47]	ZHANG H W, ZHANG W W, WANG Y, et al. Colour-patterned fabric-defect detection using unsupervised and memorial defect-free features[J]. Coloration Technology, 2022, 138(6): 602-620. doi: 10.1111/cote.v138.6
[48]	ZHANG H W, QIAO G H, LIU S T, et al. Attention-based vector quantisation variational autoencoder for colour-patterned fabrics defect detection[J]. Coloration Technology, 2023, 139(3): 223-238. doi: 10.1111/cote.v139.3
[49]	ZHANG H W, LIU S B, LU S, et al. Knowledge distillation for unsupervised defect detection of yarn-dyed fabric using the system DAERD: dual attention embedded reconstruction distillation[J]. Coloration Technology, 2024, 140(1): 125-143. doi: 10.1111/cote.v140.1
[50]	LIU S B, LIU Y K, KAN C-W. Using Bayesian regulated neural network (BRNN) to predict the effect of plasma treatment on the fading effect of cotton fabric[J]. The Journal of the Textile Institute, 2024, 115(8): 1207-1217. doi: 10.1080/00405000.2023.2220218
[51]	FAROOQ A, IRSHAD F, AZEEMI R, et al. Development of shade prediction system to quantify the shade change after crease recovery finish application using artificial neural networks[J]. The Journal of the Textile Institute, 2021, 112(8): 1287-1294. doi: 10.1080/00405000.2020.1812921
[52]	LI J Q, SHI W M, YANG D H. Color difference classification of dyed fabrics via a kernel extreme learning machine based on an improved grasshopper optimization algorithm[J]. Color Research & Application, 2021, 46(2): 388-401. doi: 10.1002/col.v46.2
[53]	CHO H, LEE J E, KIM A R, et al. Predicting dyeing properties and light fastness rating of recycled PET by artificial neural network[J]. Fibers and Polymers, 2024, 25(9): 3493-3502. doi: 10.1007/s12221-024-00672-8
[54]	YU X L, WANG H L. Support vector machine classification model for color fastness to ironing of vat dyes[J]. Textile Research Journal, 2021, 91(15/16): 1889-1899. doi: 10.1177/0040517521992366
[55]	LIU Z, HUANG S L, JIN W, et al. A novel method based on near-infrared imaging spectroscopy and graph-learning to evaluate the dyeing uniformity of polyester yarn[J]. Engineering Applications of Artificial Intelligence, 2024, 131: 107912. doi: 10.1016/j.engappai.2024.107912
[56]	HUANG S L, LIU Z, JIN W, et al. A deep multi-instance neural network for dyeing-free inspection of yarn dyeing uniformity[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106159. doi: 10.1016/j.engappai.2023.106159
[57]	RIBA J R, PUIG R, CANTERO R. Portable instruments based on NIR sensors and multivariate statistical methods for a semiautomatic quality control of textiles[J]. Machines, 2023, 11(5): 564. doi: 10.3390/machines11050564
[58]	MENG S, WANG J G, PAN R R, et al. Recognition of the layout of colored yarns in yarn-dyed fabrics[J]. Textile Research Journal, 2021, 91(1/2): 100-114. doi: 10.1177/0040517520932830
[59]	ZHANG J X, ZHANG K P, WU J K, et al. Color segmentation and extraction of yarn-dyed fabric based on a hyperspectral imaging system[J]. Textile Research Journal, 2021, 91(7/8): 729-742. doi: 10.1177/0040517520957401
[60]	FAN M Z, DENG N, XIN B J, et al. Recognition and analysis of fabric texture by double-sided fusion of transmission and reflection images under compound light source[J]. The Journal of the Textile Institute, 2023, 114(11): 1634-1646. doi: 10.1080/00405000.2022.2145428

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Research progress in applications of artificial intelligence in dyeing and finishing industry

RichHTML

PDF (PC)

Abstract

Cite this article

share this article

References 60

Related Articles 15

Metrics

Comments

Recommended 0

[1]	TUO Wu, LIU Qiongyang, LI Qingxiang, CHEN Qian, FAN Ruige, LI Pei. Automatic size measurement of women's trousers based on machine vision and YOLO11n [J]. Journal of Textile Research, 2025, 46(12): 208-215.
[2]	DENG Yuntao, TAN Yanjun, ZHANG Hongsong, YAN Yu, YU Qiuyu, LIN Fengxi, WANG Yixin, AN Lele. Nival system for fabric pilling grade evaluation [J]. Journal of Textile Research, 2025, 46(11): 102-110.
[3]	YU Zhicai, YU Xiaona, DING Xiaojun, GU Bingfei. Matching of three-dimensional fabric drape models based on PointNet classification modeling [J]. Journal of Textile Research, 2025, 46(11): 111-117.
[4]	ZHU Yaolin, LI Zheng, ZHANG Qiang, CHEN Xin, CHEN Jinni, ZHANG Hongsong. Quantitative detection of wool and cashmere based on near infrared spectroscopy and multi-feature network [J]. Journal of Textile Research, 2025, 46(09): 104-111.
[5]	ZHANG Qingyang, ZHU Shigen, BAI Yunfeng, DONG Weiwei, LUO Yilan. Consistency detection method for precision parts based on machine learning [J]. Journal of Textile Research, 2025, 46(08): 226-235.
[6]	WANG Qing, JIANG Yuefu, ZHAO Tiantian, ZHAO Shihang, LIU Jiayi. Pose estimation and bobbin grasping based on deep learning methods [J]. Journal of Textile Research, 2025, 46(07): 217-226.
[7]	JIANG Shuning, YANG Haiwei, LI Changlong, ZHENG Tianliang, WANG Zongqian. Nanofibrils exfoliated from silk fibroin by deep eutectic solvent and its film-forming properties [J]. Journal of Textile Research, 2025, 46(07): 1-9.
[8]	GU Mengshang, ZHANG Ning, PAN Ruru, GAO Weidong. Object detection of weaving fabric defects using frequency-domain convolution modules [J]. Journal of Textile Research, 2025, 46(05): 159-168.
[9]	MAO Jiayi, SU Miao. 2-D image and 3-D model generation method of Badayun patterns based on artificial intelligence generated content technology [J]. Journal of Textile Research, 2025, 46(04): 129-137.
[10]	BAI Yuwei, XU Jian, ZHU Yaolin, DING Zhanbo, LIU Chenyu. Image detection of cotton nep in carding net based on improved YOLOv8 [J]. Journal of Textile Research, 2025, 46(03): 56-63.
[11]	HUANG Xiaoyuan, HOU Jue, YANG Yang, LIU Zheng. Automatic generation of high-precision garment patterns based on improved deep learning model [J]. Journal of Textile Research, 2025, 46(02): 236-243.
[12]	CAI Liling, WANG Mei, SHAO Yibing, CHEN Wei, CAO Huaqing, JI Xiaofen. Intelligent customization recommendation for traditional Hanfu based on improved stack-generative adversarial network [J]. Journal of Textile Research, 2024, 45(12): 180-188.
[13]	LIU Yanping, GUO Peiyao, WU Ying. Research progress in deep learning technology for fabric defect detection [J]. Journal of Textile Research, 2024, 45(12): 234-242.
[14]	LI Yang, ZHANG Yongchao, PENG Laihu, HU Xudong, YUAN Yanhong. Fabric defect detection based on improved cross-scene Beetle global search algorithm [J]. Journal of Textile Research, 2024, 45(10): 89-94.
[15]	LÜ Zihao, XU Huihui, YUAN Xiaohong, WANG Qingqing, WEI Qufu. Preparation and properties of photodynamic antimicrobial spunlaced cotton made by integrated dyeing and finishing [J]. Journal of Textile Research, 2024, 45(08): 26-34.