RESUMEN
Coals and gangues are the main surface dump in the coal mining process. Dynamic monitoring of those dumps using remote sensing technique is of great importance for mine environmental protection. In the traditional classification of visible and near-infrared remote sensing, part of the gangues might be misclassified as coal, due to the phenomenon of "different objects with the same spectrum", resulting in the decrease of classification accuracy. Thus, this study firstly acquired visible and near-infrared spectrums of 12 coal samples and 115 gangue samples from Tiefa mining area in China. Most of the gangue samples' spectrums are different from those of the coals, which can be easily distinguished. While, part of the gangues has the similar spectrum with coal which results in misclassification. With an effort to improve image classification accuracy, furthermore, we acquired the thermal infrared spectrum of the misclassified gangue and the coal samples. The results indicate that there are different spectral characteristics in thermal infrared band between coal and gangue samples, which can be identified easily. Therefore, we proposed a method to separate coal from gangue based on the combination of visible, near-infrared and thermal infrared spectrum. In the first palace, the method conducts measurement on the visible and near-infrared spectrums of all samples for the rough classification recurring to the MAO model. Next, the thermal infrared spectrums of the samples, mixed with gangue and coal are acquired, and the Spectral Absorption Ratio(SAR) is utilized as the evaluation index for the second classification. The fused result of classification originates in the two steps above. The method is further verified by using external samples from Tiefa, Yanzhou, Shendong and Jiangcang mining areas in China, whose results have demonstrated that the method has higher accuracy than that of the traditional classification method based on visible and near-infrared spectrum features. The research results indicates that the conjoint analytical method involving multiple spectrums can solve the phenomenon of "different objects with the same spectrum" in a single band, effectively, which will be of great referential significance in the field of terrain classification based on remote sensing technique.
RESUMEN
Due to the needs of industrial development, the different content and uncertain distribution of magnesite mineral lead to great difficulties in o determining its grade, therefore, we propose a combination of near-infrared spectroscopy and the ELM magnesite grade classification model. The model can achieve rapid classification of magnesite grade. Near infrared spectroscopy, considering that different types of H group in magnesite have different absorption degrees to near-infrared spectroscopy, is used to determine the composition and content of magnesite. It is simple, fast, accurate and efficient without destroying the sample. In this paper, we take magnesite 30 group from Yingkou City, Liaoning Province Dashiqiao for the study, collecting their magnesite NIR data samples at 30×973, using principal component analysis (PCA) for data dimensionality reduction process. The main element contribution rate is greater than 99.99% obtained characteristic variables of 10, established quantitative analysis ELM algorithm mathematical model, take 20 groups of samples as the training samples (including 6 super group, 14 groups non), 10 groups of samples for testing samples (including super grade4 groups, 6 groups non), ELM algorithm model hidden layer nodes selection 20. In order to further improve the classification performance, two kinds improved ELM algorithm models are proposed: conduct optimization selection ELM for the traditional ELM input weights and threshold using the circulation patterns and integrate integration-Featured ELM based on Featured ELM. And compare to which use the artificial method, chemical method and BP neural network model approach. The results showed that magnesite grade classification with the near-infrared spectroscopy and ELM model have a distinct advantage regardless of cost or time, and the accuracy rate can reach over 90%, which provides a new way to classify magnesite grade.
RESUMEN
A novel hybrid, composed of Co3O4 quantum dots supported on Ti3C2Tx (MXene) nanosheets, exhibits a strong synergetic effect, and shows superior lithium storage (capacity = 766.5 mA h g-1 at 2 A g-1 after 400 cycles) and oxygen evolution (overpotential = 340 mV at 10 mA cm-2) activities.