Rapid Classification and Quantification of Coal by Using Laser-Induced Breakdown Spectroscopy and Machine Learning

被引:6
|
作者
Zheng, Yanning [1 ]
Lu, Qingmei [1 ]
Chen, Anqi [2 ]
Liu, Yulin [2 ]
Ren, Xiaohan [2 ]
机构
[1] Hebei Acad Prod Qual Supervis & Inspect, Shijiazhuang 050227, Peoples R China
[2] Shandong Univ, Inst Thermal Sci & Technol, Jinan, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 14期
关键词
coal proximate analysis; laser-induced breakdown spectroscopy; machine learning; rapid classification and quantification; LIBS; SUBTRACTION; CARBON;
D O I
10.3390/app13148158
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Coal is expected to be an important energy resource for some developing countries in the coming decades; thus, the rapid classification and qualification of coal quality has an important impact on the improvement in industrial production and the reduction in pollution emissions. The traditional methods for the proximate analysis of coal are time consuming and labor intensive, whose results will lag in the combustion condition of coal-fired boilers. However, laser-induced breakdown spectroscopy (LIBS) assisted with machine learning can meet the requirements of rapid detection and multi-element analysis of coal quality. In this work, 100 coal samples from 11 origins were divided into training, test, and prediction sets, and some clustering models, classification models, and regression models were established for the performance analysis in different application scenarios. Among them, clustering models can cluster coal samples into several clusterings only by coal spectra; classification models can classify coal with labels into different categories; and the regression model can give quantitative prediction results for proximate analysis indicators. Cross-validation was used to evaluate the model performance, which helped to select the optimal parameters for each model. The results showed that K-means clustering could effectively divide coal samples into four clusters that were similar within the class but different between classes; naive Bayesian classification can distinguish coal samples into different origins according to the probability distribution function, and its prediction accuracy could reach 0.967; and partial least squares regression can reduce the influence of multivariate collinearity on prediction, whose root mean square error of prediction for ash, volatile matter, and fixed carbon are 1.012%, 0.878%, and 1.409%, respectively. In this work, the built model provided a reference for the selection of machine learning methods for LIBS when applied to classification and qualification.
引用
收藏
页数:19
相关论文
共 50 条
  • [41] Classification of aluminum alloy using laser-induced breakdown spectroscopy combined with discriminative restricted Boltzmann machine
    Dai, Yujia
    Ma, Qing
    Zhang, Tingsong
    Zhao, Shangyong
    Zhou, Lu
    Gao, Xun
    Liu, Ziyuan
    CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2025, 258
  • [42] Benchmark classification dataset for laser-induced breakdown spectroscopy
    Kepes, Erik
    Vrabel, Jakub
    Stritezska, Sara
    Porizka, Pavel
    Kaiser, Jozef
    SCIENTIFIC DATA, 2020, 7 (01)
  • [43] Laser-induced breakdown spectroscopy for the classification of unknown powders
    Snyder, Emily Gibb
    Munson, Chase A.
    Gottfried, Jennifer L.
    De Lucia, Frank C., Jr.
    Gullett, Brian
    Miziolek, Andrzej
    APPLIED OPTICS, 2008, 47 (31) : G80 - G87
  • [44] Benchmark classification dataset for laser-induced breakdown spectroscopy
    Erik Képeš
    Jakub Vrábel
    Sára Střítežská
    Pavel Pořízka
    Jozef Kaiser
    Scientific Data, 7
  • [45] Rapid Identification of Homogeneous Alloys Based on Laser-Induced Breakdown Spectroscopy Combined with Machine-Learning Algorithms
    Li, Wanxue
    He, Yaxiong
    Li, Yang
    Cai, Feinan
    Zhang, Yong
    LASER & OPTOELECTRONICS PROGRESS, 2024, 61 (17)
  • [46] Detection and quantification of Pb and Cr in oysters using laser-induced breakdown spectroscopy
    闫清霞
    田野
    李颖
    林洪
    贾自文
    卢渊
    俞进
    孙琛
    白雪石
    Vincent DETALLE
    Plasma Science and Technology, 2023, 25 (04) : 219 - 227
  • [47] Quantification of Calcium Using Localized Normalization on Laser-Induced Breakdown Spectroscopy Data
    Sabri, Nursalwanie Mohd
    Haider, Zuhaib
    Tufail, Kashif
    Aziz, Safwan
    Ali, Jalil
    Wahab, Zaidan Abdul
    Abbas, Zulkifly
    INTERNATIONAL CONFERENCE ON PLASMA SCIENCE AND APPLICATIONS (ICPSA2016), 2017, 1824
  • [48] Detection and quantification of Pb and Cr in oysters using laser-induced breakdown spectroscopy
    Yan, Qingxia
    Tian, Ye
    LI, Ying
    Lin, Hong
    Jia, Ziwen
    Lu, Yuan
    Yu, Jin
    Sun, Chen
    Bai, Xueshi
    Detalle, Vincent
    PLASMA SCIENCE & TECHNOLOGY, 2023, 25 (04)
  • [49] Detection and quantification of Pb and Cr in oysters using laser-induced breakdown spectroscopy
    闫清霞
    田野
    李颖
    林洪
    贾自文
    卢渊
    俞进
    孙琛
    白雪石
    Vincent DETALLE
    Plasma Science and Technology, 2023, (04) : 219 - 227
  • [50] Rapid Nuclear Forensics Analysis via Machine-Learning-Enabled Laser-Induced Breakdown Spectroscopy (LIBS)
    Bhatt, Bobby
    Dehayem-Kamadjeu, Alix
    Angeyo, Kalambuka Hudson
    WOMEN IN PHYSICS, 2019, 2109