Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms

Ma, Xiangdong; Gao, Zhigang; Dong, Wenli; He, Shen; Xu, Zhongyuan; Wu, Xiao; Zheng, Wei; Wen, Jiongming; Yu, Yonghua

doi:10.3390/s26134014

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms

by

Xiangdong Ma

,

Zhigang Gao

,

Wenli Dong

,

Shen He

^*

,

Zhongyuan Xu

,

Xiao Wu

,

Wei Zheng

,

Jiongming Wen

and

Yonghua Yu

Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China

^*

Author to whom correspondence should be addressed.

Sensors 2026, 26(13), 4014; https://doi.org/10.3390/s26134014 (registering DOI)

Submission received: 15 March 2026 / Revised: 29 April 2026 / Accepted: 18 June 2026 / Published: 24 June 2026

(This article belongs to the Section Intelligent Sensors)

Download Versions Notes

Abstract

Currently, clustering algorithms are mainly used to classify fiber-reinforced composite cylinder damage. However, the number of clustering categories is heavily influenced by the evaluation criteria, and the real damage type categorization cannot be determined. Therefore, we propose a semi-supervised algorithm that obtains higher damage classification information with a small number of labels. Specifically, we first performed a phased fiber-reinforced composite cylinder pressurization experiment and collected damage signals through acoustic emission (AE) hits. We analyzed the damage types of the collected burst-type acoustic emission hits (each hit corresponds to a single waveform captured when the hit’s amplitude exceeds the preset threshold) and marked a small number of these hits. Then, we constructed a mean-teacher semi-supervised network structure based on transfer learning, achieving a classification accuracy of 85.92%. Compared to traditional supervised learning and clustering algorithms, the accuracy improved by nearly 30%.

Keywords: fiber-reinforced composite cylinder; prediction of damage distribution; semi-supervised; transfer learning algorithms; mean-teacher network structure

Share and Cite

MDPI and ACS Style

Ma, X.; Gao, Z.; Dong, W.; He, S.; Xu, Z.; Wu, X.; Zheng, W.; Wen, J.; Yu, Y. Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms. Sensors 2026, 26, 4014. https://doi.org/10.3390/s26134014

AMA Style

Ma X, Gao Z, Dong W, He S, Xu Z, Wu X, Zheng W, Wen J, Yu Y. Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms. Sensors. 2026; 26(13):4014. https://doi.org/10.3390/s26134014

Chicago/Turabian Style

Ma, Xiangdong, Zhigang Gao, Wenli Dong, Shen He, Zhongyuan Xu, Xiao Wu, Wei Zheng, Jiongming Wen, and Yonghua Yu. 2026. "Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms" Sensors 26, no. 13: 4014. https://doi.org/10.3390/s26134014

APA Style

Ma, X., Gao, Z., Dong, W., He, S., Xu, Z., Wu, X., Zheng, W., Wen, J., & Yu, Y. (2026). Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms. Sensors, 26(13), 4014. https://doi.org/10.3390/s26134014

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Prediction of Damage Distribution in Gas Cylinder Stages Based on Semi-Supervised and Transfer Learning Algorithms

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI