With the continuous development of wireless communication technology, the wireless electromagnetic environment is increasingly complex, which results in the difficulty of modulation recognition of communication signals. In this paper, combining the advantages of ResNet and DenseNet, we propose a blind modulation recognition model based on deep learning. In this model, we reduce the two-dimensional convolution neural network in ResNet into the one-dimensional convolution neural network and then embed it into DenseNet. The identity mapping of ResNet and the dense connection of DenseNet, which strengthen feature propagation and encourage feature reuse and reduce the number of parameters, make the model take full advantage of multi-layer features to improve the ability of feature extraction and reduce the computational complexity. The experimental results on the RadioML2016.10b dataset show that the recognition accuracy of the model can reach 93.7% at high SNR.

No abstract

Aiming at the problem of severe vibration and abnormal wear and tear of various components in coal shearer under slant-cutting conditions, a non-linear dynamics model with 13 degrees of freedom for a coal shearer under slant-cutting conditions is developed using vibration mechanics and multi-body dynamics theory, and the characteristics of the slide shoes-middle groove contact, the ranging arm-haulage unit connection with gaps and the guidance sliding boots-pin rail multi-surface contact with gaps are described based on three-dimensional fractal theory and Hertz contact theory. Based on Huco's law, the ranging arm and the hydraulic rod are assumed to be flexible beams, the rigidity characteristics of the ranging arm itself, the connection characteristics of the haulage unit and the fuselage are described, a drum correction load with a traction speed correction factor is proposed as the external excitation of the system, and the model is solved and analyzed. The research results show that the change of traction speed has a greater influence on the vibration swing angle and displacement of the front drum, front ranging arm and front walking unit, and the vibration swing angle and displacement of the three increase with the increase of traction speed, while the change of coalface hardness coefficient has less influence on the vibration displacement of the key components of the coal shearer. Under the working parameters of v = 3 m/min and f = 3, the swing angle and displacement of the front ranging arm and front drum fluctuate in the ranges of − 0.4–0.1 rad and – 15–15 mm respectively; the vibration acceleration is – 300–300 rad/s2 and – 200–200 mm/s2 respectively, the main vibration frequencies are 16.63 Hz and 12.14 Hz respectively, and finally the results are verified by experimental methods.

To analyse the stability of a digging anchor machine under digging conditions, the dynamics model of the anchor machine and the interaction mechanics model between its tracks and the roadway floor are constructed with a Sandvik MB670-1 digging anchor machine in the context of the Zhang Jiamao 5–2 coal seam of the Shaanxi Coal and Chemical Industry Group. The discrete element method (DEM) and multibody dynamics (MBD) two-way coupling algorithm is used to simulate the cutting process of a full coal seam and coal rock containing gangue by using a digging anchor machine in a roadway. The changes in the cutting depth of the digging anchor machine drum, the sliding distance of the track and the stress‒strain pattern of the roadway floor are obtained. Finally, through shear slip testing, the stress distribution and deformation pattern of the roadway floor under different grouser parameters of the digging anchor machine track shoe, as well as the wear characteristics of the track shoe, are obtained. The results of this study can provide a theoretical basis for the control and reliability of the digging anchor machine and the life fatigue prediction of its tracks.

No abstract