Identification of coal and gangue is one of the important problems in the coal industry. To improve the accuracy of coal gangue identification in the coal mining process, a coal gangue identification method based on histogram of oriented gradient (HOG) combined with local binary pattern (LBP) features and improved support vector machine (SVM) was proposed. First, according to the actual underground working environment of the mine, a machine vision platform for coal gangue identification was built and the coal gangue image acquisition experiment was carried out. Then, the images of coal and gangue were denoised by median filtering, and the coal and gangue features were extracted by using the HOG combined with LBP feature extraction algorithm, and these features were normalized and principal component analysis (PCA) reduced dimension to remove the correlation and redundancy between the features. Finally, SVM, SVM optimized by genetic algorithm (GA-SVM), SVM optimized by particle swarm optimization (PSO-SVM) algorithm, and SVM optimized by grey wolf optimization (GWO-SVM) algorithm were used as classifiers for identification and classification, respectively. The experimental results show that the GWO-SVM classification model has the highest accuracy, and the average classification accuracies were 96.49% and 94.82% of the training set and test set, respectively, which shows that grey wolf algorithm to optimize support vector machine has a good effect on classification of coal gangue images, which proves the feasibility and accuracy of the proposed method.

The temperature effect caused by high slip has an important influence on the operation performance and reliability of magnetic coupling. Taking the self-developed single disk asynchronous magnetic coupling as the research object, the heat loss equation of the magnetic coupling is established. Based on the three-dimensional transient magnetic field simulation model of the magnetic coupling, the eddy current loss, torque, and eddy current distribution law of the magnetic coupling are obtained through simulation. The space flow field and structure temperature field distribution of the magnetic coupling are analyzed by using the fluid-thermal coupling simulation method, and the heat dissipation coefficient and temperature distribution law of the structure surfaces such as copper disk, the back lining yoke iron disk, and the aluminum disk are obtained. The test platform was built to test the torque and temperature of the magnetic coupling. The results show that the error between the test and simulation is 4.8% in the torque aspect, and the maximum error between the test and simulation is only 8.1% in the temperature aspect of each component, which further verifies the effectiveness of the simulation method. On this basis, three heat dissipation improvement schemes are proposed, including installing heat dissipation blocks, setting semicircular grooves on the back lining yoke iron disk, and a hybrid design. The results show that the degree of improvement for each scheme is in the following order: hybrid design, setting semicircular grooves on the back lining yoke iron disk, and installing heat dissipation blocks. Under the hybrid design, the temperature of the back lining yoke iron plate and a copper plate of the magnetic coupling is reduced by about 8.5 °C compared with the original model, and the effect is ideal. The research results can provide an optimization reference for high-speed magnetic coupling and the temperature effect caused by an overload-locked rotor.