The image is an important way for people to understand the world. How to make the computer have image recognition function is the goal of image recognition research. In image recognition, image segmentation technology is one of the important research directions. This paper uses gray-gradient maximum entropy method to extract features from the image, uses K-mean method to classify the images, and uses average precision (AP) and intersection over union (IU) evaluation methods to evaluate the results. The results show that the method of K-mean can achieve image segmentation very well.

Using salt caverns for an underground strategic petroleum reserve (SPR) is considered as an ideal approach due to the excellent characteristics of low porosity, low permeability, self-healing of damage, and strong plastic deformation ability of rock salt. Salt deposits in China are mostly layered rock salt structures, with the characteristics of many interlayers, bringing great challenges for the construction of SPR facilities. Studying the microscopic pore characteristics of the rock surrounding SPR salt caverns in different environments (with brine and crude oil erosion) is necessary because the essence of mechanical and permeability characteristics is the macroscopic embodiment of the microscopic pore structure. In this paper, XRD tests and SEM tests are carried out to determine the physical properties of storage media and surrounding rock. Gas adsorption tests and mercury intrusion tests are carried out to analyze the microscopic pore structure, specific surface area variation and total aperture distribution characteristics of SPR salt cavern host rock. Results show that: (1) Large numbers of cores in interlayer and caprock may provide favorable channels for the leakage of high-pressure crude oil and brine. (2) The blockage of pores by macromolecular organic matter (colloid and asphaltene) in crude oil will not significantly change the structural characteristics of the rock skeleton, which is beneficial to the long-term operation of the SPR salt cavern. (3) The water–rock interaction will bring obvious changes in the micro-pore structure of rock and increase the leakage risk of the storage medium. The results can provide theoretical bases and methods for the tightness analysis of China’s first underground SPR salt cavern.

This paper uses an acoustic emission (AE) test to examine the energy dissipation and liberation of coal and rock fracture due to underground coal excavation. Many dynamic failure events are frequently observed due to underground coal excavation. To establish the quantitative relationship between the dissipated energy and AE energy parameters, the coal and rock fracturing characteristics were clearly observed. A testing method to analyze the stage traits and energy release mechanism from damage to fracture of the unloading coal and rock under uniaxial compressive loading is presented. The research results showed that the relevant mechanical parameter discreteness was too large because the internal structures of the coal and rock were divided into multiple structural units (MSU) by a few main cracks. The AE test was categorized into four stages based on both the axial stress and AE event parameters: initial loading stage, elastic stage, micro-fracturing stage, and post-peak fracturing stage. The coal and rock samples exhibited minimum (maximum) U values of 60.44 J (106.41 J) and 321.19 J (820.87 J), respectively. A theoretical model of the dissipation energy during sample fracturing based on the AE event energy parameters was offered. The U decreased following an increase in ΣE_AE-II/ΣE_AE.

Microseismic signals induced by mining activities often have low signal-to-noise ratios, and traditional picking methods are easily affected by noise, making accurate identification of P-wave arrivals difficult. To address this problem, this study proposes an adaptive denoising algorithm based on wavelet-threshold-enhanced Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and develops an automatic P-wave arrival picking method incorporating fractal box dimension features, along with a corresponding accuracy evaluation framework. The raw microseismic signals are decomposed using the improved CEEMDAN method, with high-frequency intrinsic mode functions (IMFs) processed by wavelet-threshold denoising and low- and mid-frequency IMFs retained for reconstruction, effectively suppressing background noise and enhancing signal clarity. Fractal box dimension is applied to characterize waveform complexity over short and long-time windows, and by introducing fractal derivatives and short-long window differences, abrupt changes in local-to-global complexity at P-wave arrivals are revealed. Energy mutation features are extracted using the short-term/long-term average (STA/LTA) energy ratio, and noise segments are standardized via Z-score processing. A multi-feature weighted fusion scoring function is constructed to achieve robust identification of P-wave arrivals. Evaluation metrics, including picking error, mean absolute error, and success rate, are used to comprehensively assess the method’s performance in terms of temporal deviation, statistical consistency, and robustness. Case studies using microseismic data from a mining site show that the proposed method can accurately identify P-wave arrivals under different signal-to-noise conditions, with automatic picking results highly consistent with manual labels, mean errors within the sampling interval (2–4 ms), and a picking success rate exceeding 95%. The method provides a reliable tool for seismic source localization and dynamic hazard prediction in mining microseismic monitoring.