Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65518
Volume:
10 |
6 |
Jun 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Applications
Nehru Institute of Information Technology and Management, Coimbatore, Tamil Nadu, India
Department of Computer Applications
Nehru Institute of Information Technology and Management, Coimbatore, Tamil Nadu, India
Yarn quality plays a significant role in determining the strength, durability, and overall performance of textile products. Conventional methods used to evaluate yarn quality mainly depend on laboratory testing and manual inspection, which often require considerable time, effort, and skilled personnel. To address these challenges, YarnInsight was developed as a web-based system for yarn quality prediction and production management. The system uses machine learning techniques to estimate yarn tensile strength and classify yarn into different quality grades based on characteristics such as cellulose content, hemicellulose content, lignin content, moisture content, pH level, fineness, density, porosity, and fiber tenacity. In addition to quality prediction, the application supports batch management, supplier analysis, risk assessment, production monitoring, and report generation. Python, Streamlit, Scikit-learn, Pandas, NumPy, Plotly, and SQLite were used during development. The system provides a user-friendly interface through which users can enter yarn parameters and obtain prediction results instantly. The developed application reduces the dependence on manual quality assessment procedures and supports more consistent decision-making in textile manufacturing environments.
KEYWORDS
This paper described the design and implementation of YarnInsight, a web-based yarn quality prediction and production management system developed for textile manufacturing environments. The application combines machine learning techniques with production management functionalities to support quality assessment and operational monitoring. The system predicts yarn tensile strength and classifies yarn quality grades using multiple yarn characteristics as input parameters. Additional features such as batch management, supplier analytics, risk assessment, and report generation provide comprehensive support for manufacturing activities. The implementation results indicate that the application can assist users in evaluating yarn quality more efficiently while reducing dependence on traditional manual assessment procedures. The developed platform demonstrates the practical use of machine learning in textile quality control and production management.
[1] A. Majumdar, P. Banerjee, and R. Alagirusamy, “Application of Machine Learning Techniques in Textile Manufacturing,” Textile Research Journal, vol. 94, no. 4, pp. 325–340, 2024. [2] S. Hu, Y. Zhang, and X. Li, “Machine Learning-Based Prediction of Yarn Quality Parameters,” IEEE Access, vol. 11, pp. 45672–45684, 2023. [3] J. R. Davis and M. Patel, “Quality Assessment in Textile Manufacturing Using Data Analytics,” Journal of Industrial Engineering, vol. 18, no. 2, pp. 101–114, 2022. [4] Scikit-learn Developers, “Scikit-learn: Machine Learning in Python,” Available: https://scikit-learn.org [5] Plotly Technologies Inc., “Plotly Documentation,” Available: https://plotly.com [6] Streamlit Inc., “Streamlit Documentation,” Available: https://streamlit.io [7] SQLite Consortium, “SQLite Database Engine Documentation,” Available: https://www.sqlite.org [8] W. Smith and R. Johnson, “Textile Production Monitoring and Quality Control Systems,” International Journal of Textile Science, vol. 15, no. 3, pp. 145–158, 2023.
Publication Date
6/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...