In large coal preparation plants with a capacity of 30 million tons/year, the belt speed can reach 7 m/s and the thickness of the material layer can reach 500 mm. Therefore, in high-throughput and complex environments, the problem exists that harmful feeding materials such as iron and gangue are not easily detected, and thus fault diagnosis in the crushers lags behind. Therefore, it is necessary to extract the equipment operation signals from the noisy production environment and identify the feeding materials. Currently, there is no systematic research on signal processing and image classification of crusher feeding materials, while the convolutional neural network (CNN) is outstanding in computer vision. In this paper, sound and vibration signals of the feeding materials are denoised by spectral subtraction and transformed into feature images by continuous wavelet transforms. Then, an image classification model based on CNN is built for these feature images to study its classification mechanism and performance. The results show that the model classification accuracy is respectively 84.0%, 93.5% and 80.1% in coal–iron–wood classification, coal–iron classification, and coal–wood classification. The good classification performance for coal, iron and wood can satisfy the practical demands to remove the harmful feeding materials, which provides the core technical support for the establishment of operating status monitoring and fault diagnosis system of crushing equipment.

The reference value of the oil film thickness and friction coefficient of the slipper pair is critical to the development of the piston pump, especially for 750 mL/r displacement piston pumps. To explore the computing method and range of the reference value mentioned applicable to 750 mL/r displacement piston pumps, this study aims to propose the modified calculation model of the oil film thickness based on the real clearance flowrate and obtain the value range of the friction coefficient of the slipper pair. Through the friction test of the slipper pair, the mean deviation ratio of the oil film thickness between the modified value, theoretical value, and the measured value was calculated and compared, respectively. The variation law of the friction under the influence of different speeds and working pressures was analyzed. Finally, the range of the equivalent friction coefficient with the upper and lower limit surfaces was obtained. The results show that the mean deviation ratio between the modified oil film thickness value and the measured value is mainly within 6%, while that of the theoretical method is mainly from 6% to 8%, and the mean of the difference between the two deviation ratios is about 3%, verifying the feasibility of the modified model used for the calculation of the reference value. Meanwhile, the value of the equivalent friction coefficient fluctuates in the range of 0.006–0.018, which is affected more significantly by the working pressure than the speed, suggesting that the working pressure can be given priority as the design basis of the friction coefficient for 750 mL/r displacement piston pumps.