Performance-Based Classification of Industrial Flocculent Cellulose Fibers Using Multi-Index Testing, Principal Component Analysis, and K-Means Clustering

DOI

10.2991/978-94-6463-902-5_53How to use a DOI?

Keywords

Road engineering; Flocculent cellulose fibers; Key performance; Analysis and evaluation; PCA; K-means clustering

Abstract

To systematically assess the performance differences among various fiber materials, experimental testing and statistical analysis were conducted on 164 flocculent cellulose fiber samples from diverse production sources, aiming to investigate the distribution patterns and variability of key performance indicators. For four critical indicators—oil absorption rate, heat resistance, ash content, and 0.15 mm sieve passing rate—a combined approach of principal component analysis (PCA) and K-means clustering was employed for quantitative analysis and classification of the fiber samples. The results show that over 90% of the samples met the qualification thresholds for oil absorption rate, heat resistance, and ash content, whereas the 0.15 mm sieve passing rate exhibited a relatively lower compliance. PCA compressed the multidimensional indicators into two principal components, cumulatively explaining approximately 62.9% of the total variance, effectively retaining the essential information from the original data. K-means clustering based on the principal component scores classified the samples into three distinct categories, each clearly separated in the PCA projection space, demonstrating high clustering effectiveness. These findings reveal the performance distribution characteristics of commercially available fibers from different production sources. The established model can identify primary performance differences among fiber samples and provide data-driven guidance for the selection and application of fiber materials.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bo Ding
AU  - Xueyong Zhu
AU  - Lei Song
AU  - Fangtao Liu
PY  - 2025
DA  - 2025/12/16
TI  - Performance-Based Classification of Industrial Flocculent Cellulose Fibers Using Multi-Index Testing, Principal Component Analysis, and K-Means Clustering
BT  - Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)
PB  - Atlantis Press
SP  - 536
EP  - 544
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-902-5_53
DO  - 10.2991/978-94-6463-902-5_53
ID  - Ding2025
ER  -