Laser-induced breakdown spectroscopy (LIBS) combined with PCA-RBF for the classification of different types of coal

Coal is a key component of the global energy structure and plays a central role in various industrial and civil fields. The chemical and physical properties of coal determine the applicability of different types of coal. Therefore, precise coal classification and management are crucial for promoting resource efficiency and environmental sustainability. However, due to the high similarity in composition between different types of coal, traditional classification methods are challenging to apply. In light of this, this paper proposes a Laser-Induced Breakdown Spectroscopy (LIBS) method combined with Principal Component Analysis (PCA) and Radial Basis Function network (RBF) for the classification and identification of 12 types of coal samples. Firstly, the spectral data of the coal samples are collected after laser ablation, followed by preprocessing steps such as noise removal, background correction, and normalization. Then, PCA is used to reduce the dimensionality of the preprocessed spectral data, and RBF is employed to classify and train the reduced-dimensional data. The research results show that the PCA-RBF model can classify coal samples with an accuracy rate of 98.96%. The combination of LIBS with the PCA-RBF model achieves rapid and accurate classification of different varieties of coal samples, providing an accurate and efficient data processing method that helps to promote the optimal allocation of coal resources and the sustainable development of the economy and environment.