Coal classification method based on visible-infrared spectroscopy and an improved multilayer extreme learning machine

Coal classification is an indispensable task in coal mining and production. The traditional method of coal classification has the disadvantages of high cost, low speed and low accuracy. Therefore, a rapid coal classification method based on visible-infrared spectroscopy is proposed in this research. First, we collected samples of different coal types and used spectrometers to measure the spectral data of these samples. Then, we proposed an improved multilayer extreme learning machine algorithm using this algorithm to build a coal classification model. The simulation results showed that the model has good classification results. Compared with the traditional coal classification methods, this method has an unparalleled advantage in economy, speed and accuracy. © 2019 Elsevier Ltd