Dynamic entropy-based feature extraction of piezoelectric vibration signals for cotton-knot defect detection in yarn

In response to the issues of poor signal stability and low defect feature extraction accuracy in yarn defect detection within the textile industry, this study proposes a dynamic entropy signal processing method based on piezoelectric sensing to efficiently and accurately extract yarn defect features. By designing a piezoelectric yarn defect detection platform, the yarn vibrations are converted into high-sensitivity electrical signals, enabling high-frequency signal acquisition. A dynamic entropy feature extraction method is introduced, which uses a sliding window and dynamic binning probability distribution model to capture local features of the yarn signal. Experimental results demonstrate that this method achieves a defect recognition accuracy of over 95% for cotton knots, with an average processing time only half of that of the comparison method. A nonlinear regression model is established to map the entropy value to the cotton knot severity, with the nonlinear asymptotic regression model achieving a fitting degree of 0.996. Finally, the influence of key dynamic entropy parameters (window width, bin width) and sensor sensitivity on detection performance is discussed. This study provides an effective solution to improve the accuracy and efficiency of yarn defect detection, with potential applications in online quality control.

Authors

Institutions

Publication Details

Journal
Measurement Science and Technology
Published
2026-11-19
DOI
https://doi.org/10.1088/1361-6501/aec469
Primary Topic
Industrial Vision Systems and Defect Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Dynamic entropy-based feature extraction of piezoelectric vibration signals for cotton-knot defect detection in yarn

Yubao Qi, liangmei Hou, Y Zhong, Laihu Peng et al.
Measurement Science and Technology
Industrial Vision Systems and Defect Detection
article

Dynamic entropy-based feature extraction of piezoelectric vibration signals for cotton-knot defect detection in yarn

Yubao Qi, liangmei Hou, Y Zhong, Laihu Peng, Zaixin Zhang
article en

Abstract

In response to the issues of poor signal stability and low defect feature extraction accuracy in yarn defect detection within the textile industry, this study proposes a dynamic entropy signal processing method based on piezoelectric sensing to efficiently and accurately extract yarn defect features. By designing a piezoelectric yarn defect detection platform, the yarn vibrations are converted into high-sensitivity electrical signals, enabling high-frequency signal acquisition. A dynamic entropy feature extraction method is introduced, which uses a sliding window and dynamic binning probability distribution model to capture local features of the yarn signal. Experimental results demonstrate that this method achieves a defect recognition accuracy of over 95% for cotton knots, with an average processing time only half of that of the comparison method. A nonlinear regression model is established to map the entropy value to the cotton knot severity, with the nonlinear asymptotic regression model achieving a fitting degree of 0.996. Finally, the influence of key dynamic entropy parameters (window width, bin width) and sensor sensitivity on detection performance is discussed. This study provides an effective solution to improve the accuracy and efficiency of yarn defect detection, with potential applications in online quality control.

Measurement Science and Technology
Zhejiang Sci-Tech University (CN)
Industrial Vision Systems and Defect Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon