基于A-Unet3+和便携式NIR光谱仪的煤炭灰分与发热量协同检测方法

doi:10.3964/j.issn.1000-0593(2025)08-2210-08

Abstract
References
Related Citation (4)

Download: PDF (4956 KB)
Export: BibTeX | EndNote (RIS)

Abstract Near-infrared spectroscopy (NIR) technology is increasingly being applied in coal quality analysis due to its rapid and non-destructive advantages. With their compact size and ease of operation, portable NIR analyzers are particularly suited for online coal quality monitoring. However, portable devices typically exhibit lower spectral signal-to-noise ratios than traditional laboratory equipment. Furthermore, existing modeling approaches often focus on individual indicators, overlooking the interdependencies between two coal quality parameters, limiting the models' robustness and prediction accuracy. To address these limitations, this paper proposes a multi-task Unet3+ network model incorporating a channel attention mechanism, aimed at processing the low signal-to-noise ratio and weak-feature spectral data collected by portable NIR analyzers, and achieving the simultaneous prediction of ash content and calorific value in coal. First, a data preprocessing method that combines second-order differentiation with Savitzky-Golay (S-G) convolution smoothing is utilized to effectively reduce noise and enhance spectral peak features, thereby improving the data quality for modeling. Next, a Unet3+ network suitable for spectral data is designed, employing encoders, decoders, and a multi-scale feature fusion module to extract shared features relevant to ash content and calorific value. A channel attention mechanism is introduced to enhance feature representation further. Finally, the model decouples the shared features via fully connected layers to independently learn the specific characteristics of ash content and calorific value, enabling joint prediction for both tasks. Experimental validation on 670 coal samples demonstrates that, compared to typical machine learning methods and conventional deep learning models, the proposed method yields root mean square errors (RMSE) of 2.590 4 and 1.176 3 for ash content and calorific value prediction, respectively. The mean absolute errors (MAE) are 1.964 4 and 0.872 6, with correlation coefficients reaching 0.944 4 and 0.874 3, significantly outperforming the comparison models. These results provide an efficient and accurate solution for the online analysis of coal quality parameters.

Key words：Portable near-infrared spectrometer; Rapid coal quality analysis; Channel attention mechanism; Unet3+

Received: 2024-12-10 Accepted: 2025-04-30

ZTFLH:

O657.3

Corresponding Authors: WU Jing-tao E-mail: 15131330516@163.com

Cite this article:

ZOU Liang,KOU Shao-ping,REN Ke-long, et al. A Collaborative Detection Method for Coal Ash Content and Calorific Value Based on A-Unet3+ and Portable NIR Spectrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2210-2217.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)08-2210-08 OR https://www.gpxygpfx.com/EN/Y2025/V45/I08/2210

[1] WANG Guo-fa, LIU He, WANG Dan-dan, et al(王国法，刘合，王丹丹，等). Bulletin of Chinese Academy of Sciences (中国科学院院刊), 2023, 38(1): 23.
[2] Yang Q, Zhang L, Zou S, et al. Energy Policy, 2020, 139: 111360.
[3] Xiao D, Le B T. Microchemical Journal, 2020, 157: 104880.
[4] ZHAO Zhong-hui, FANG Quan-guo(赵忠辉, 方全国). Coal Quality Technology(煤质技术), 2017, (4): 18.
[5] Liu K, He C, Zhu C, et al. TrAC Trends in Analytical Chemistry, 2021, 143: 116357.
[6] Rajavelu H, Vasa N J, Seshadri S. Determination of Ash Content in Coal Using Laser-Induced Breakdown Spectroscopy with Multivariate Analysis[C], ICOL-2019: Proceedings of the International Conference on Optics and Electro-Optics, 2021: 399.
[7] Yao S, Qin H, Wang Q, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 239: 118492.
[8] Tian J, Li M, Tan Z, et al. Chemometrics and Intelligent Laboratory Systems, 2024, 252: 105175.
[9] Mao Y, Xia W, Xie G, et al. Measurement, 2020, 155: 107564.
[10] Weng S, Yu S, Dong R, et al. International Journal of Food Properties, 2020, 23(1): 269.
[11] LENG Si-yu, QIAO Jia-hui, WANG Lian-qing, et al(冷思雨, 乔嘉慧, 王连庆，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(1): 303.
[12] Wang H, Chu X, Chen P, et al. Fuel, 2022, 309: 122224.
[13] Wang Y, Yang M, Wei G, et al. Sensors and Actuators B: Chemical, 2014, 193: 723.
[14] Begum N, Maiti A, Chakravarty D, et al. Fuel, 2020, 280: 118676.
[15] Van S, Moons K, Groot J, et al. Statistical Methods in Medical Research, 2019, 28(8): 2455.
[16] Harrell F E. Regression Modeling Strategies: with Applications to Linear Models, Logistic Regression, and Survival Analysis[M]. New York: Springer, 2001.
[17] Qin C, Wu Y, Liao W, et al. BMC Medical Imaging, 2022, 22(1): 14.
[18] GB/T 212-2022. Proximate Analysis of Coal (煤的工业分析方法) [S], Standardization Administration of the People's Republic of China (中国国家标准化管理委员会)，Standards Press of China (中国标准出版社) ,2022.
[19] GB/T 212-2008. Determination of Calorific Value of Coal (煤的发热量测定方法) [S], Standardization Administration of the People's Republic of China (中国国家标准化管理委员会) . Standards Press of China (中国标准出版社) , 2008.
[20] Zou L, Yu X, Li M, et al. IEEE Transactions on Instrumentation and Measurement, 2020, 69(10): 8043.
[21] Huang H, Lin L,Tong R, et al. UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation[C], 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020: 1055.
[22] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C], Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015: 234.
[23] Lei M, Rao Z, Wang H, et al. Fuel, 2021, 294: 120475.
[24] Niu Z, Zhong G, Yu H. Neurocomputing, 2021, 452: 48.
[25] Guo M H, Xu T X, Liu J J, et al. Computational Visual Media, 2022, 8(3): 331.
[26] Hu J, Shen L, Sun G. Squeeze-and-Excitation Networks[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018:7132.