Image deep learning-driven granularity effect correction: a novel approach to improve the accuracy of NIRS-XRF coal quality analysis
Deep learning with the SAM and CNNs corrects granularity effects in NIRS-XRF coal analysis, reducing errors and improving prediction accuracy of ash content for reliable online coal quality monitoring.
Authors
- Jiale Wang (ORCID: https://orcid.org/0000-0003-3938-9706)
- Jia‐Xin Yin (ORCID: https://orcid.org/0000-0003-2661-4206)
- Wangbao Yin
- Zhihui Tian
- Rui Gao (ORCID: https://orcid.org/0009-0004-0229-2753)
- Jiaxuan Li (ORCID: https://orcid.org/0000-0002-1267-5799)
- Yan Zhang (ORCID: https://orcid.org/0000-0001-5562-8215)
- Yang Zhao (ORCID: https://orcid.org/0000-0002-8187-9963)
- Lei Zhang (ORCID: https://orcid.org/0000-0001-7247-6348)
- Peihua Zhang
- Suotang Jia (ORCID: https://orcid.org/0000-0001-9610-3386)
Institutions
- North University of China (CN)
- Taiyuan Normal University (CN)
- Shanxi University (CN)
- Xi'an Technological University (CN)
- Hubei Engineering University (CN)
- State Key Laboratory of Quantum Optics and Quantum Optics Devices
Publication Details
- Journal
- Journal of Analytical Atomic Spectrometry
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d4ja00391h
- Primary Topic
- Mineral Processing and Grinding
- Type
- article
- Field-Weighted Citation Impact
- 0.00