Regularized Adaptive Weight Noise Injection-Based Evolutionary Training with Generative AI for Industrial Dye Recipe Optimization

Authors

  • Ridha El Hamdi Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
  • Hana Charaabi Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
  • Mohamed Njah Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax, Tunisia | Digital Research Center of Sfax, Technopole of Sfax, Tunisia
  • Mounir Zaag Industrial Textiles Company (SITEX), Ksar Hellal, Tunisia
Volume: 15 | Issue: 5 | Pages: 27165-27171 | October 2025 | https://doi.org/10.48084/etasr.12143

Received: 14 May 2025 | Revised: 1 July 2025 and 11 July 2025 | Accepted: 13 July 2025 | Online: 11 August 2025


Corresponding author: Ridha El Hamdi

Abstract

This study introduces the Regularized Adaptive Weight Noise Injection-Based Evolutionary (RAWE) training approach, enhanced by generative Artificial Intelligence (AI), to optimize the dye recipe formulation in industrial textile manufacturing. RAWE integrates a self-adaptive evolutionary strategy with adaptive weight noise injection, dynamically balancing the exploration and exploitation during model training. A key innovation of RAWE is its use of generative AI to synthesize high-quality, domain-specific data, addressing the challenge of limited historical dyeing records. This synthetic data generation significantly improves the model generalization and robustness, enabling more accurate and reliable predictions in real-world industrial settings. The effectiveness of RAWE is demonstrated through its deployment in a real-world textile dyeing automation system, where it achieves significant improvements in dye recipe optimization. The results show that RAWE reduces the material waste, minimizes the production costs, and enhances the color consistency compared to traditional methods. By combining generative AI with adaptive evolutionary training, RAWE offers a scalable and practical solution for complex industrial processes, aligning with the latest advancements in automated Machine Learning (ML) and AI-driven optimization.

Keywords:

generative AI, generative adversarial networks, variational autoencoders, evolutionary algorithms, weight noise injection, adaptive regularization, industrial dyeing optimization

Downloads

Download data is not yet available.

References

Md. N. Pervez, W. S. Yeo, L. Lin, X. Xiong, V. Naddeo, and Y. Cai, "Optimization and prediction of the cotton fabric dyeing process using Taguchi design-integrated machine learning approach," Scientific Reports, vol. 13, no. 1, July 2023, Art. no. 12363.

M. Njah and R. El Hamdi, "A Constrained Multi-Objective Learning Algorithm for Feed-Forward Neural Network Classifiers," Engineering, Technology & Applied Science Research, vol. 7, no. 3, pp. 1685–1693, June 2017.

R. M. Zur, Y. Jiang, L. L. Pesce, and K. Drukker, "Noise injection for training artificial neural networks: A comparison with weight decay and early stopping," Medical Physics, vol. 36, no. 10, pp. 4810–4818, Oct. 2009.

M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, "Synthetic data augmentation using GAN for improved liver lesion classification," in 2018 IEEE 15th International Symposium on Biomedical Imaging, Washington, DC, Apr. 2018, pp. 289–293.

K. Dorji, S. Jittanon, P. Thanarak, P. Mensin, and C. Termritthikun, "Electricity Load Forecasting using Hybrid Datasets with Linear Interpolation and Synthetic Data," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 17931–17938, Dec. 2024.

N. Tarafder, "Applications of Machine Learning in Textile Industry," Journal of IoT and Machine Learning, vol. 1, no. 2, pp. 24–27, Aug. 2024.

N. Ingle and W. J. Jasper, "A review of deep learning and artificial intelligence in dyeing, printing and finishing," Textile Research Journal, vol. 95, no. 5–6, pp. 625–657, Mar. 2025.

M. An, S. Wang, L. Zheng, and X. Liu, "Fabric defect detection using deep learning: An Improved Faster R-approach," in 2020 International Conference on Computer Vision, Image and Deep Learning, Chongqing, China, July 2020, pp. 319–324.

X. Xiong et al., "A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classifications," in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, Republic of, Apr. 2024, pp. 7310–7314.

L. Schaerf, A. Alfarano, and E. Postma, "ColorwAI: Generative Colorways of Textiles Through GAN and Diffusion Disentanglement," in Computer Vision – ECCV 2024 Workshops, vol. 15628, A. Del Bue, C. Canton, J. Pont-Tuset, and T. Tommasi, Eds. Cham: Springer Nature Switzerland, 2025, pp. 137–160.

A. Imtiaz, N. Pathirana, S. Saheel, K. Karunanayaka, and C. Trenado, "A Review on the Influence of Deep Learning and Generative AI in the Fashion Industry," Journal of Future Artificial Intelligence and Technologies, vol. 1, no. 3, pp. 201–216, Oct. 2024.

X. Wang, L. Kong, and L. Wang, “Estimation of Error Variance in Regularized Regression Models via Adaptive Lasso,” Mathematics, vol. 10, no. 11, June 2022, Art. no. 1937.

P. Züge, C. Klos, and R.-M. Memmesheimer, "Weight versus Node Perturbation Learning in Temporally Extended Tasks: Weight Perturbation Often Performs Similarly or Better," Physical Review X, vol. 13, no. 2, Apr. 2023, Art. no. 021006.

A. Orvieto, A. Raj, H. Kersting, and F. Bach, "Explicit Regularization in Overparametrized Models via Noise Injection." arXiv, 2022.

B. Wang, Y. Sun, B. Xue, and M. Zhang, "Evolving deep neural networks by multi-objective particle swarm optimization for image classification," in Proceedings of the Genetic and Evolutionary Computation Conference, Prague Czech Republic, July 2019, pp. 490–498.

E. Duran, C. Ozturk, and M. A. Ornek, "Combinatorial optimization methods for yarn dyeing planning," Flexible Services and Manufacturing Journal, vol. 37, no. 1, pp. 282–319, Mar. 2025.

Downloads

How to Cite

[1]
R. El Hamdi, H. Charaabi, M. Njah, and M. Zaag, “Regularized Adaptive Weight Noise Injection-Based Evolutionary Training with Generative AI for Industrial Dye Recipe Optimization”, Eng. Technol. Appl. Sci. Res., vol. 15, no. 5, pp. 27165–27171, Oct. 2025.

Metrics

Abstract Views: 68
PDF Downloads: 33

Metrics Information

License

Copyright (c) 2025 Ridha El Hamdi, Hana Charaabi, Mohamed Njah, Mounir Zaag

Creative Commons License

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

Authors who publish with this journal agree to the following terms:

- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.