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

A near-infrared spectroscopy dataset of coal and coal-measure rock under diverse conditions

The identification technology for coal and coal-measure rock is required across multiple stages of coal exploration, mining, separation, and tailings management. However, the construction of identification models necessitates substantial data support. To this end, we have established a near-infrared spectral dataset for coal and coal-measure rock, which includes the reflectance spectra of 24 different types of coal and coal-measure rock. For each type of sample, 11 sub-samples of different granularities were created, and reflectance spectra were collected from sub-samples at five different detection azimuths, 18 different detection zeniths, and under eight different light source zenith conditions. The quality and usability of the dataset were verified using quantitative regression and classification machine learning algorithms. Primarily, this dataset is used to train artificial intelligence-based models for identifying coal and coal-measure rock. Still, it can also be utilized for regression studies using the industrial analysis results contained within the dataset.

Coal Classification Based on Reflection Spectroscopy and the IAT-TELM Algorithm

As a principal energy globally, coal's quality and variety critically influence the effectiveness of industrial processes. Different coal types cater to specific industrial requirements due to their unique attributes. Traditional methods for coal classification, typically relying on manual examination and chemical assays, lack efficiency and fail to offer consistent accuracy. Addressing these challenges, this work introduces an algorithm based on the reflectance spectrum of coal and machine learning. This method approach facilitates the rapid and accurate classification of coal types through the analysis of coal spectral data. First, the reflection spectra of three types of coal, namely, bituminous coal, anthracite, and lignite, were collected and preprocessed. Second, a model utilizing two hidden layer extreme learning machine (TELM) and affine transformation function is introduced, which is called affine transformation function TELM (AT-TELM). AT-TELM introduces an affine transformation function on the basis of TELM, so that the hidden layer output satisfies the maximum entropy principle and improves the recognition performance of the model. Third, we improve AT-TELM by optimizing the weight matrix and bias of AT-TELM to address the issue of highly skewed distribution caused by randomly assigned weights and biases. The method is named the improved affine transformation function (IAT-TELM). The experimental findings demonstrate that IAT-TELM achieves a remarkable coal classification accuracy of 97.8%, offering a cost-effective, rapid, and precise method for coal classification.

A Review of Machine Learning for Near-Infrared Spectroscopy

The analysis of infrared spectroscopy of substances is a non-invasive measurement technique that can be used in analytics. Although the main objective of this study is to provide a review of machine learning (ML) algorithms that have been reported for analyzing near-infrared (NIR) spectroscopy from traditional machine learning methods to deep network architectures, we also provide different NIR measurement modes, instruments, signal preprocessing methods, etc. Firstly, four different measurement modes available in NIR are reviewed, different types of NIR instruments are compared, and a summary of NIR data analysis methods is provided. Secondly, the public NIR spectroscopy datasets are briefly discussed, with links provided. Thirdly, the widely used data preprocessing and feature selection algorithms that have been reported for NIR spectroscopy are presented. Then, the majority of the traditional machine learning methods and deep network architectures that are commonly employed are covered. Finally, we conclude that developing the integration of a variety of machine learning algorithms in an efficient and lightweight manner is a significant future research direction.

Coal identification based on a deep network and reflectance spectroscopy

The rapid identification of coal types in the field is an important task. This research combines spectroscopy with deep learning algorithms and proposes a method for quickly identifying coal types in the field. First, we collect field spectral data of various coals and preprocess the spectra. Then, a coal identification model that uses a convolutional neural network in combination with an extreme learning machine is proposed. The two-dimensional spectral features of coal are extracted through the convolutional neural network, and the extreme learning machine is used as a classifier to identify the features. To further improve the identification performance of the model, we use the whale optimization algorithm to optimize the parameters of the model. The experimental results show that the proposed method can quickly and accurately identify types of coal. It provides a low-cost, convenient, and effective method for the rapid identification of coal in the field.

Identifying Balls Feature in a Large-Scale Laser Point Cloud of a Coal Mining Environment by a Multiscale Dynamic Graph Convolution Neural Network

In the process of coal mining, a certain amount of gas will be produced. Environmental perception is very important to realize intelligent and unmanned coal mine production and operation and to reduce the accident rate of gas explosion and other disasters. The identification of geometric features of the coal mine working face is the main part of the environmental perception of the working face. In this study, we identify geometric features in a large-scale coal mine working face point cloud (we take the ball as an example) so as to provide a method for the environmental perception of the coal mine working face. On the basis of previous research, we upgrade the dynamic graph convolution neural network (DGCNN) for directly processing point clouds from two aspects: extracting local features and global features of point clouds. First, a multiscale dynamic graph convolution neural network (MS-DGCNN) is proposed, and the combination of max-pooling and average-pooling is used as the symmetry function. Second, we use MS-DGCNN to learn the features of a variety of geometric point clouds in the point cloud data set we make and then look for the ball in the large-scale point cloud of the coal mining working face. Finally, we compare the performance of MS-DGCNN with that of other deep neural networks directly processing point clouds. This study enables MS-DGCNN to obtain more powerful feature expression ability and enhance the generalization of the model. In addition, this study provides a solid foundation for the geometric feature identification of MS-DGCNN in the environmental perception of the coal mine working face and creates a precedent for the application of MS-DGCNN in the field of energy. At the same time, this study makes a beneficial exploration for the development of a transparent coal mine working face.