EUVIMEDEUVIMED entdecken
Crossref

Terahertz coal–rock identification method based on multi-representation feature fusion

Changpeng Li iD, Zilong Chen iD, Tianbing Ma, Rui Shi, Dongdong Ye, Guoyong Su, Yanqing Yu, Qun Wang

Applied Optics · 10.11.2026 · 65 (32) · 11600

DOI: 10.1364/ao.613087 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Optics, online erschienen am 09.11.2026. Verfasst von Changpeng Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan 232001, China. Die Arbeit nennt 44 Literaturangaben. Gefördert von: Natural Science Research Project of Anhui Educational Committee, Scientific Research Foundation for High-level Talents of Anhui University of Science and Technology, Joint Funds of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the classification performance of coal–rock identification by enhancing spectral feature representation, this study proposes a terahertz-based multi-representation feature fusion model, termed THz-CVFusionNet. Terahertz time-domain signals of six types of coal–rock samples were acquired using a terahertz time-domain spectroscopy (THz-TDS) system. After frequency-domain transformation, the 0.1–2.0 THz range was selected for spectral analysis, and the effective absorption coefficient was extracted as the key feature parameter. A dual-branch network was developed to integrate complementary spectral representations. The 1D-CNN branch captures local spectral patterns from effective absorption coefficient sequences. The spectral sequences were further transformed into two-dimensional GAF representations for global correlation modeling using a 2D Vision Transformer. Feature-level fusion was then used to combine the two branches for classification. Experimental results show that the proposed model achieved accuracy, macro-precision, macro-recall, and macro-F1 score values above 97%, outperforming several mainstream models. These results demonstrate the potential of THz-TDS combined with feature fusion for accurate coal–rock identification.

Autor:innen und Institutionen

  • State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan 232001, China.
  • School of Mechatronics Engineering, Anhui University of Science and Technology, Huainan 232001, China.
  • School of Mining Engineering, Anhui University of Science and Technology, Huainan 232001, China.
  • Anhui Jixingyuan Technology Joint-Stock Co., Ltd., Huainan 232008, China.
  • School of Artificial Intelligence, Anhui Polytechnic University, Wuhu 241000, China.

ORCID-Profile: Changpeng Li, Zilong Chen

Förderung

  • Natural Science Research Project of Anhui Educational Committee
  • Scientific Research Foundation for High-level Talents of Anhui University of Science and Technology
  • Joint Funds of the National Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Open Fund of China State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines
  • Open Fund of Mechanical Industry Key Laboratory of Intelligent Mining and Beneficiation Equipment
  • The Coal-Major Project

Zitieren

APA

Li, C., Chen, Z., Ma, T., Shi, R., Ye, D., Su, G., Yu, Y., & Wang, Q. (2026). Terahertz coal–rock identification method based on multi-representation feature fusion. Applied Optics, 65(32), 11600. https://doi.org/10.1364/ao.613087

Vancouver

Li C, Chen Z, Ma T, Shi R, Ye D, Su G, et al. Terahertz coal–rock identification method based on multi-representation feature fusion. Applied Optics. 2026;65(32):11600. doi:10.1364/ao.613087

BibTeX
@article{Li2026,
  author = {Li, Changpeng and Chen, Zilong and Ma, Tianbing and Shi, Rui and Ye, Dongdong and Su, Guoyong and Yu, Yanqing and Wang, Qun},
  title = {Terahertz coal–rock identification method based on multi-representation feature fusion},
  journal = {Applied Optics},
  year = {2026},
  volume = {65},
  number = {32},
  pages = {11600},
  doi = {10.1364/ao.613087}
}
Kostenlos starten →