To address the challenges posed by high data dimensionality and class imbalance during intrusion detection, which result in increased computational complexity, resource consumption, and reduced classification accuracy, this paper presents an intrusion-detection algorithm based on an improved Random Forest approach. The algorithm employs the Bald Eagle Search (BES) optimization technique to fine-tune the Kernel Principal Component Analysis (KPCA) algorithm, enabling optimized dimensionality reduction. The processed data are then fed into a cost-sensitive Random Forest classifier for training, with subsequent model validation conducted on the reduced-dimension data. Experimental results demonstrate that compared to traditional Random Forest algorithms, the proposed method reduces the training time by 11.32 s and achieves a 5.59% increase in classification accuracy, an 11.7% improvement in specificity, and a 0.0558 increase in the G-mean value. These findings underscore the promising application potential and performance of this approach in the field of network intrusion detection.

Negative obstacles such as potholes and road collapses on unstructured roads in open-pit mining areas seriously affect the safe transportation of autonomous trucks. In this paper, we propose a real-time negative obstacle detection method for self-driving trucks in open-pit mines. By analyzing the characteristics of road negative obstacles in open-pit mines, a real-time target detection model based on the Yolov4 network was built. It uses RepVGG as the backbone feature extraction network, applying SimAM space and a channel attention mechanism to negative obstacle multiscale feature fusion. In addition, the classification and prediction modules of the network are optimized to improve the accuracy with which it detects negative obstacle targets. A non-maximum suppression optimization algorithm (CIoU Soft Non-Maximum Suppression, CS-NMS) is proposed in the post-processing stage of negative obstacle detection. The CS-NMS calculates the confidence of each detection frame with weighted optimization to solve the problems of encountering obscure negative obstacles or poor positioning accuracy of the detection boxes. The experimental results show that this research method achieves 96.35% mAP for detecting negative obstacles on mining roads with a real-time detection speed of 69.3 fps, and that it can effectively identify negative obstacles on unstructured roads in open-pit mines with complex backgrounds.

In order to respond to the theme of national green and healthy sustainable development and in response to the problems of large block rates and pollution of the environment after the blast mining of underground rocks in alpine areas, we conducted research on the joints of underground rocks and the blastability of frozen rocks. According to the actual geological conditions of an underground mine blasting in Heilongjiang Province, three kinds of joint blasting geometric models were established. The rock mass blasting process of different types of joints was simulated by LS-DYNA software and the influence law of joints on rock mass blasting was summarized. The blasting crater test and the triaxial compression test of frozen rock were carried out. Combined with the blasting fragmentation characterization function (R-R and G-G-S), the blasting fragmentation, strength and stiffness of frozen rock at different temperatures were obtained. Based on the above, the blasting parameters of a multi-joint underground rock mass in an alpine region were optimized: hole spacing 4.0 m, row spacing 2.5 m, hole depth 11.5 m, V-type initiation network. The optimized blasting parameters significantly improved the mining efficiency and reduced the large lump rate to 3.1%. In order to promote the sustainable exploitation of resources in alpine regions, this study optimized the blasting technology of underground rock mass.

The layout of industrial construction projects is crucial in meeting production requirements while minimizing operational costs. The purpose of this study is to answer the question of whether the proposed discrete block model and spatial meshing (DBSM) algorithm can improve transportation efficiency and reduce total direct transportation costs. The DBSM algorithm was implemented in 20 different investigation scenarios that considered the uncertainty in the model variables for a construction materials production company based on its geological, transportation, and production data. These analytical scenarios varied the grid sizes of spatial meshing, vertical distance of computational topology blocks, and practical transportation distance at each dimension increment throughout the initial design and planning period. The algorithm was then validated by statistically comparing its performance with that of a contemporary location-selection model that does not consider three-dimensional (3D) spiral transportation routes and differential material quality while maximizing the model performance. The DBSM algorithm outperformed the existing model due to its ability to select an optimized location. The algorithm resulted in a reduced total weighted sum of distances (WSD) for all trucks and an annual savings of 1.62% on direct transportation costs. This research contributes a new method that integrates spatial block modeling and location meshing to solve the construction-materials stationary plant site-selection problem with uncertain routes and dynamic loading points. It is an effective and practical method of location optimization for real-world production problems.

During the molybdenite mining process, conveyor belts stretching for miles are used to transport ore between the blasting sites, crushing stations, and the concentrator plant. In order to ensure the safety and stability of the industrial production process, this paper introduces a foreign matter detection method based on deep learning for the belt conveyor. Aiming at the problems of insufficient feature extraction capabilities in existing machine vision-based foreign body detection methods and poor detection accuracy due to imbalanced positive and negative samples, an improved foreign body detection method for anchorless frame-type metal mine belt conveyors is proposed. This method introduces atrous convolution in the pooling layer to increase the receptive field of feature extraction and improve the ability of extracting feature details of foreign objects. By optimizing the ratio of positive and negative samples in the training process, the overall loss function value of the algorithm is reduced to ensure the accuracy of foreign body recognition. Finally, the improved model is trained after enhancing and labeling the sample dataset. The experimental results show that the average mean accuracy of foreign body detection (MAP) is 90.9%, better than existing methods. It can be used as an effective new method for detecting foreign objects on molybdenum mine belt conveyors.

Capillarity influences the long-term stability of the dam greatly and affects the sustainable development of tailings dam. The online monitoring capillary water rise test system was independently developed by SM3001B temperature and humidity sensor, SU9101B RS485 converter, SV3010 data acquisition system, and other equipment to carry out the whole process test of water absorption and water release of tailings with different particle sizes. The results show that the capillary rising trend of tailings with different particle sizes is basically consistent, the relationship between the rising height and the diameter are negatively correlated, and the logarithm function can better fit the height of capillary rising over time well enough. The water content of tailing capillary zone decreases with the height, and the smaller the size of tailings, the greater the change of water content. The water release process of tailings is an unsaturated permeability process, which largely depends on the saturation before water release. The larger the particle size of tailings is, the smaller the water content after water release. Based on the above results, the relationship between capillary diameter and tailings particle size was discussed, and the relationship formula between water content change and particle size was deduced. The research results systematically show the water migration law under the tailing capillaries. It is suggested that the unsaturated tailings water content index should be added in the monitoring of the saturated surface of tailings dam.