Coal Classification Method Based on Improved Local Receptive Field-Based Extreme Learning Machine Algorithm and Visible–Infrared Spectroscopy

Abstract

In the process of using coal, if the type of coal cannot be accurately determined, it will have a significant impact on production efficiency, environmental pollution, and economic loss. At present, the traditional classification method of coal mainly relies on technician’s experience. This requires a lot of manpower and time, and it is difficult to automate. This paper mainly studies the application of visible-infrared spectroscopy and machine learning methods in coal mine identification and analysis to provide guidance for coal mining and production. This paper explores a fast and high-precision method for coal identification. In this paper, for the characteristics of high dimensionality, strong correlation, and large redundancy of spectral data, the local receptive field (LRF) is used to extract the advanced features of spectral data, which is combined with the extreme learning machine (ELM). We improved the coyote optimization algorithm (COA). The improved coyote optimization algorithm (I-COA) and local receptive field-based extreme learning machine (ELM-LRF) are used to optimize the structure and training parameters of the extreme learning machine network. The experimental results show that the coal classification model based on the network and visible–infrared spectroscopy can effectively identify the coal types through the spectral data. Compared with convolutional neural networks (CNN algorithm) and principal component analysis (PCA algorithm), LRF can extract the spectral characteristics of coal more effectively.

A Review of Machine Learning for Near-Infrared Spectroscopy

“…Deep architectures can reduce the variance introduced by solid samples, which have variable path lengths due to scattering. Deep architectures are used in NIR to determine the quality of medicines [125][126][127]157], meats, vegetables and fruits [128][129][130][131][132], the contents of soil and minerals [13,[133][134][135]158], cracks in water pipes [136], the manufacturing date of paper [159], and water pollution [137], as well as in the cursory evaluation of malady [160]. Experiments conducted on four distinct datasets containing solid samples demonstrated that the number of training samples influences the generalization ability of deep learning algorithms [140,141].…”

Optimized identification of cheese products based on Raman spectroscopy and an extreme learning machine

“…This method has the advantages of fast learning speed and good generalization performance. [18][19][20] Taking the Raman spectra of the samples of various brands collected with the integration time of 80 s as an example, the original data were first introduced into an extreme learning machine algorithm, with 72% of the samples as test sets (54 samples) and 28% as training sets (21 samples). The sample selection was random and ran 200 times.…”

Reflections on the Innovation of University Scientific Research Management in the Era of Big Data

“…Literature [18] holds that internal control should be taken as the starting point to improve the management level of SR projects and the use efficiency of funds. Literature [19] holds that strengthening the performance evaluation of SR funds should start from two aspects: the use benefit evaluation of SR funds and the benefit of SR work. Paying attention not only audits compliance, legality, rationality, and authenticity of the income and expenditure of SR projects but also comprehensively evaluates their economic benefits, technical benefits, and social benefits.…”