Cross-instrument coal quality spectral analysis via a PDS-assisted fine-tuning calibration transfer method
Analytica Chimica Acta · 2026-07 · 1405 · 345485
DOI: 10.1016/j.aca.2026.345485 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytica Chimica Acta, 2026-07. Verfasst von Junlong Gao und 11 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Quantum Optics Technologies and Devices, Institute of Laser Spectroscopy, Shanxi University, Taiyuan, 030006, China; Collabor…. Die Arbeit nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND Device-related variations in X-ray fluorescence (XRF) instruments often lead to spectral inconsistencies, which significantly degrade the accuracy and generalization of quantitative coal quality models, particularly for ash content prediction. Conventional calibration transfer methods or single-stage transfer learning approaches struggle to effectively handle large inter-instrument spectral discrepancies, especially under limited sample conditions. RESULTS In this study, a two-stage transfer learning framework integrating piecewise direct standardization (PDS) with feature fine-tuning (FT), termed PDS-FT, is proposed to enhance cross-instrument ash content prediction. Using 140 coal samples measured on two different XRF instruments, five approaches-PDS, FT, Domain-Adversarial Neural Network (DANN), PDS-DANN, and PDS-FT-were systematically evaluated. The results show that standalone PDS and FT exhibit limited test-set performance, achieving average R2 values of 0.33 and 0.51 with root mean square error (RMSE) of 1.86% and 1.55%, respectively. DANN improves cross-domain prediction performance (R2 = 0.74, RMSE = 1.36%) but is constrained by training instability. The hybrid PDS-DANN method further enhances performance, reaching R2 = 0.78 and RMSE = 1.0%. In contrast, the proposed PDS-FT framework achieves the best performance, with a test-set R2 of 0.95 and a substantially reduced RMSE of 0.59%, demonstrating superior accuracy, robustness, and cross-device generalization capability. SIGNIFICANCE By combining spectral-level physical correction with feature-level model adaptation, the proposed PDS-FT framework establishes a hierarchical domain alignment mechanism that progressively mitigates inter-instrument discrepancies. This dual-stage strategy significantly enhances the transferability and reliability of XRF-based ash content models, providing a practical and generalizable solution for coal quality analysis across heterogeneous XRF instruments in industrial applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- State Key Laboratory of Quantum Optics Technologies and Devices, Institute of Laser Spectroscopy, Shanxi University, Taiyuan, 030006, China; Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan,…
- School of Physics and Electronic Information Engineering, Hubei Engineering University, Xiaogan, 432000, China.
- School of Semiconductor and Physics, North University of China, Taiyuan, 030051, China.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Gao, J., Li, J., Yin, J., Gao, R., Tian, Z., Zhao, Y., Bai, Y., Dong, L., Ma, W., Zhang, L., Yin, W., & Jia, S. (2026). Cross-instrument coal quality spectral analysis via a PDS-assisted fine-tuning calibration transfer method. Analytica Chimica Acta, 1405, 345485. https://doi.org/10.1016/j.aca.2026.345485
Vancouver
Gao J, Li J, Yin J, Gao R, Tian Z, Zhao Y, et al. Cross-instrument coal quality spectral analysis via a PDS-assisted fine-tuning calibration transfer method. Analytica Chimica Acta. 2026;1405:345485. doi:10.1016/j.aca.2026.345485
BibTeX
@article{Gao2026,
author = {Gao, Junlong and Li, Jiaxuan and Yin, Jiaxin and Gao, Rui and Tian, Zhihui and Zhao, Yang and Bai, Yu and Dong, Lei and Ma, Weiguang and Zhang, Lei and Yin, Wangbao and Jia, Suoteng},
title = {Cross-instrument coal quality spectral analysis via a PDS-assisted fine-tuning calibration transfer method},
journal = {Analytica Chimica Acta},
year = {2026},
volume = {1405},
pages = {345485},
doi = {10.1016/j.aca.2026.345485}
}
EUVIMED