Rock bursts have recently become a serious problem in the horizontal section mining of steeply inclined extra-thick coal seams (SIETCSs). However, few studies have been carried out to investigate their mechanisms and prevention. In this study, numerical simulation and field measurements were carried out to investigate the mechanism of rock bursts in the horizontal section mining of an SIETCS. A Universal Distinct Element Code (UDEC) Trigon model was built, based on the Yaojie No.3 Coal Mine, and calibrated through laboratory tests and RQD methods. The results demonstrate that the coal in the elastic zone around the roof is in a high static stress state, due to the asymmetric clamping and squeezing of the roof and floor. Strong dynamic loads are formed by breakage of the roof and the failure of multiple hinged beam structures during the evolution process of the overlying strata. Rock bursts occur on the roof side when the superimposition of the static stress ${\sigma }_s$ and stress increment ${\sigma }_d$ induced by such dynamic loads is greater than the critical stress ${\sigma }_{\min }$ of the coal and rock. We propose a technical prevention scheme for the considered mine. Field studies suggest that the proposed technology can effectively prevent and control rock bursts in the horizontal section mining of SIETCSs.

In the context of Industrial Anomaly Detection (IAD), ensuring the quality of manufactured products is critical. Traditional 2D based methods often fail to capture anomalies present in complex 3D shapes. For effective anomaly detection in 3D shapes, it is essential to incorporate global semantic context, local geometric structure, and color information of the object. To fully leverage these features, we propose a network named 2M3DF, that leverages knowledge from multi-view RGB images and corresponding point cloud information for enhanced anomaly detection performance. Our model initially employs pre-trained feature extractors that generate local features from multi-view RGB images and corresponding point clouds. The novel inter-modality feature representation and fusion module first adapts these inter-modality features and then effectively aligns and aggregates these multimodality features on a pixel-to-point basis. To learn the normality from point-wise fused multimodal features, we fit a multivariate Gaussian distribution to model the normal feature distribution. Comprehensive experimental evaluations using the MVTec3D-AD and Eyecandies dataset validate the effectiveness of our propose model and demonstrate significant improvements in comparison to existing state-of-the-art methods. Our model achieves a 96.6% mean I-AUROC while delivering real-time results.

Aiming at roadway rockbursts induced by near-field dynamic disturbances, this study explored the mechanical response and failure mechanism of anchored roadway surrounding rocks under this condition through the similarity simulation experiment and theoretical modeling analysis. Results show that the greater the disturbance energy is, the stronger mechanical response of surrounding rocks while the faster its attenuation. The starting acceleration amplitude is relatively smaller while the braking acceleration amplitude is larger in the bolt densification area, which has a better self-stabilizing ability. Anchored roadway surrounding rocks exhibit local impact failure characteristics, and the region facing disturbance is most seriously damaged. The bolt-mesh-cable support structure shows the good resistance to low-energy disturbances, while the impact failure is induced with damages inside support structure increasing abruptly under high-energy disturbances. The impact resistance of local surrounding rocks can be improved by bolt densification. Based on the failure criterion, the surrounding rocks only undergo impact failure in the region facing disturbance, while quasi-static failure occurs in remaining regions. The experimental and theoretical research results have been verified through in-situ measurements, which can provide an important reference for the mechanism and prevention of roadway rockburst under near-field dynamic disturbance.

At present, visual saliency prediction algorithms have been developed more and more mature, but most of the current saliency prediction algorithms are aimed at natural images. Due to the inconsistency of elements and features between natural images and advertising images, the existing saliency prediction algorithms show poor robustness and low inference speed to advertising images, which severely limits its commercial application in advertising design and evaluation. In view of this, a saliency prediction algorithm for advertisement images is proposed in this paper. In the feature extraction stage, two text candidate regions based on intensity feature and improved MESR algorithm are first obtained and further integrated to produce a two-dimensional text confidence score. Meanwhile, a saliency confidence score is also obtained by an improved natural image saliency prediction network. Then, the score level fusion strategy was adopted to fuse the two confidence scores to get the final saliency prediction map. The experimental results show that the proposed model has good accuracy and robustness in advertising images, as well as the most remarkable inference speed, which can meet the demand for real-time performance of advertising image saliency prediction, leading to great practical and commercial value.