As an important index to evaluate the internal properties of rock and rock mass, wave velocity is significantly affected by stress and porosity. In order to study the variation of rock wave velocity with porosity and stress, acoustic-wave combination tests of two kinds of sandstone with different pores under uniaxial loading are carried out. Test results show that: The mechanical properties of sandstone not only depend on the porosity of sandstone, but also are significantly affected by pore size. Pore closure and crack propagation are the main causes of the change of wave velocity in sandstones, and the former has a more significant effect on the change of wave velocity, while the latter mainly affects the change rate of wave velocity with stress. The wave velocity of sandstones with different pores increases synchronously with stress. At the same stress level, the wave velocity of sandstones with larger porosity decreases, and the wave velocity increment increases. In the whole loading process of sandstones, porosity has the most significant effect on the changing rate of wave velocity with stress at the first stage of pore compaction.

Rockburst is one of the common dynamic disasters in underground engineering. An unsupervised learning model of rockburst clustering is suggested with the help of a self-organizing feature map (SOFM) neural network to improve the prediction accuracy of rockburst and study the latent relation between rockburst-related evaluating indicators. Firstly, six parameters, including the maximum tangential stress, uniaxial compressive strength, uniaxial tensile strength, stress coefficient, brittleness coefficient, and elastic energy index are selected as evaluation criteria. Then, 46 typical rockburst cases chosen from the literature are trained by the proposed SOFM model with its competitive layer being a 2×2 topological structure. The results suggest that the SOFM model possesses reliable clustering ability, and its positive judgment rate for the test sample is 90%. Furthermore, compared with the existing supervised learning model for rockburst prediction, the superiority of the SOFM model in this paper is verified, and some suggestions on the application of the SOFM model are given. Finally, the analysis of clustering results shows that the brittleness coefficient has a high influence on the occurrence of mild, moderate, and strong rockburst types. In addition, the distinction between strong and moderate rockburst types is not obvious by using the six evaluating parameters considered.