Research on identification method of bituminous coal based on terahertz time-domain spectroscopy

The traditional coal type identification method needs to measure a variety of parameters of coal samples to obtain more accurate results, and the detection process is time-consuming and laborious, and can not realize the rapid identification of coal types. In this paper, a bituminous coal species identification method based on terahertz time-domain spectroscopy combined with machine learning-principal component analysis Principal component analysis (PCA) and cluster analysis (CA) was proposed. The two types of bituminous coal samples were detected by the transmission terahertz time-domain spectroscopy system, and the spectral data of various bituminous coal samples were obtained, and then the absorption coefficient and refractive index of each sample were obtained after mathematical calculations such as fast Fourier transform (FFT). The results show that the PCA-CA classification model based on terahertz absorption coefficient spectrum can accurately identify different bituminous coals with an accuracy of 100%, while the PCA-CA classification model based on refractive index spectra cannot accurately identify different bituminous coals. The results show that the terahertz time-domain spectroscopy combined with machine learning algorithm can accurately identify different kinds of bituminous coal, and the model classification effect based on terahertz absorption coefficient spectrum is better than that of the model based on refractive index spectroscopy, which provides a new idea for coal mining and utilization.