Laser-Induced Breakdown Spectroscopy-Based Coal-Rock Recognition: An in Situ Sampling and Recognition Method

• Published in: IEEE access Vol. 9; pp. 164732 - 164741
• Main Authors: Liu, Cong, Luo, Yimin, Zhang, Qizhi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">in situ; Atomic properties; Coal; Coal mining; Coal-rock recognition (CRR); Discriminant analysis; Face recognition; Laser induced breakdown spectroscopy; Laser modes; laser-induced breakdown spectroscopy (LIBS); Neural networks; Real-time systems; Recognition; Rocks; Sampling methods; Silicon; Spectroscopy; Spectrum analysis; unmanned coal mining
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3133886

Coal and rock recognition (CRR) has important theoretical and practical significance in unmanned coal mining. Laser-induced breakdown spectroscopy (LIBS) is considered a cutting-edge technology in the field of material analysis due to its real-time analysis capability, minimal to no sample preparation scheme, high sensitivity to low atomic weight elements, and ability to perform nearby and distant detection. In this research, a new fast and accurate coal-rock recognition method for unmanned coal mining based on LIBS is presented. The LIBS in situ sampling method of the coal mining face and the LIBS-based CRR method are discussed. Partial least squares discriminant analysis (PLS-DA) is used to analyze the LIBS spectrum and to construct a simplified spectral model (SSM). Finally, SSM and neural network classifiers are used to recognize coal and rock, and the results are presented and discussed. These results show that the CRR method proposed in this research has a high recognition accuracy rate.