Compressive strength is an important index to characterize the mechanical properties of filling body. It is of great significance to ensure the safety of stope by quickly and accurately determining the compressive strength of filling body. In order to explore the influence law of the strength of multi-source coal-based solid waste filling body and accurately predict the strength of coal-based solid waste filling body to guide the safe, efficient and green mining of coal mine, the influencing factors of the compressive strength of coal-based solid waste filling body were studied by orthogonal test with coal gangue as coarse material, desulfurization gypsum, gasification slag and bottom slag as fine material, fly ash and cement as cementing agent. The grey correlation degree analysis method was used to analyze the correlation between each test factor and the compressive strength of filling body. The strength prediction of coal-based solid waste backfill at different curing ages was carried out by using 5-11-3 three-layer back propagation(BP) neural network structure. The results show that the influence of concentration, gasification slag and desulfurization gypsum content on compressive strength increases with the increase of curing age, and the influence of fly ash and bottom slag content on compressive strength increases first and then decreases with the increase of curing age. Orthogonal test combined with BP neural network can reduce the number of tests without losing generality. The correlation coefficient R of strength prediction of coal-based solid waste backfill is 0.999 87. It can be seen that high concentration and high content of gasification slag and desulfurization gypsum are of great significance for filling body requiring high strength. At the same time, orthogonal test combined with BP neural network can accurately predict the strength of filling body.

The principle of particle damping energy consumption and inertial capacity efficiency increase are widely used in structural vibration reduction control. Based on the advantages of particle damping and inertial capacity, a particle damping inertial capacity shock damper (PID) was designed, which mainly contained particle damping unit, inertial mass unit and stiffness unit. Firstly, the working principle of PID was elaborated, the mechanical analysis model of single degree of freedom was established, a small PID mock-up was produced, a variety of working conditions were set up to test the mechanical properties of the PID. Then, the mechanical properties of PID were further explored by the combined simulation method of many-body dynamics software and discrete element software. Finally, to verify its engineering application value, dynamic time-course analysis of the damping structures configured with PID and tuned mass damper (TMD) by finite element structural analysis software SAP2000. The results show that PID has excellent damping performance, when the other conditions are certain, the energy consumption effect of PID increases with the increase of vibration displacement amplitude and vibration frequency. In the building structure, PID shows better damping than TMD, it has a high engineering application value.

The Chang 6₃ sand formation in Block A of Ordos Basin is an ultra-low permeability reservoir, which is difficult to be conventionally exploited. At present, horizontal well fracturing is widely used for development. According to the physical characteristics of ultra-low permeability reservoir, the geomechanical model and fracturing simulation software, combined with embedded discrete fracture method were used to characterize the artificial fractures generated by fracturing simulation of Chang 6₃ sand formation, and carried out numerical simulation research based on this. Through this integrated process, the integrated simulation of complex fracturing of horizontal wells were realized, and the efficiency of horizontal well development was improved. The results show that the embedded discrete fracture method can effectively combine fracturing and numerical simulation, and realize the integrated flow from fracturing to numerical simulation of horizontal wells. The accuracy of the numerical model was verified by the historical fitting of the production mode of fixed oil production. By adjusting the relevant parameters to optimize the model, it is more in line with the actual production situation of the well group, which is conducive to the subsequent development plan adjustment and production forecast.

Structural design is an important part of the architectural engineering design stage, which must ensure that the building is safe, reliable, economical, and durable. Artificial intelligence can replace structural designers with a lot of training and repetitive operations to find the optimal design results and improve design efficiency. In order to comprehensively understand the relevant research and application hotspots of artificial intelligence in structural design, the current research status of artificial intelligence in the three stages of scheme design, preliminary design and construction drawing design was summarized from the perspective of the entire structural design process. Through reviewing literatures, it is found that artificial intelligence methods such as expert systems, decision trees, annealing algorithms, genetic algorithms, neural networks, and linear regression have been widely used in the field of building structure design, which has brought new development directions and approaches. At present, artificial intelligence methods are more widely used in the design of aboveground structures, but less in underground structures (foundations, basements, etc.), and their application in underground structures needs to be strengthened. In addition, the quantitative translation technology of normative provisions is relatively mature, but the qualitative translation technology of normative provisions still needs to be broken, and it is necessary to strengthen the research on rule-based or machine learning-based natural language processing.

Sodium fire accidents in sodium technology room can generate harmful aerosols. To analyze the impact of sodium fire aerosol particle migration, a microchannel grid structure similar to real cracks was constructed using computational fluid dynamics(CFD) method based on the actual concrete crack characteristics to simulate the migration process of aerosol particles in the room wall. A two-dimensional horizontal microchannel flow model was established, considering gravity, inertial force, and the influence of Saffman lift and Brownian diffusion on particle motion was studied, and a microchannel particle motion model was constructed to numerically simulate particle retention characteristics for different gap structures. The results indicate that when the gap size is less than submillimeter, it is considered that there is no risk of causing a large amount of aerosol particle leakage in the gap. The branching corners and uneven micro structures within concrete gaps can effectively reduce the penetration coefficient of particles in the gaps and reduce leakage.

A deep learning based T-beam formwork polishing robot was designed for the problems of difficult and time consuming polishing of T-beam formwork for variable cross-section. Firstly, an adaptive polishing structure was proposed to solve the technical problem that the existing polishing device cannot fit the inner variable cross-section of the T-beam formwork, and the polishing roller was easy to get stuck in the T-beam formwork partition. Secondly, in order to realize the quantitative monitoring of the polishing quality, a YOLOv8n-DSE algorithm was proposed to identify concrete dirt and stains on the formwork, the DySample dynamic up-sampling module was introduced to enhance the anti-interference ability of the model and accelerate the calculation speed, to improve the accuracy of small target detection, the SOEP (small object enhance pyramid) module was designed to improve the detection performance of small target detection through the SPDConv(space to depth convolution) to obtain the information features of the small target and give them to the CSP(cross stage partial)-Omni-Kernel for the integration of the features. Finally, the EMA(exponential moving average)-SlideLoss was replaced to make the model more concerned with the quantitative monitoring of the concrete, allowed the model to focus more on difficult targets, which can improve the effect on difficult case detection. The accuracy, recall, and mAP(mean average precision) values are improved by 3.1%, 9.7%, and 3.2%, respectively, compared with those before the improvement. The improved model was deployed to the robot and tested in the field. The results show that the equipment meets the plant's needs for polishing variable-section T-beam formwork.

In order to analyze the instability and failure characteristics of earthquake landslides in the Loess Plateau, the Xinbaocun landslide induced by the 8.5-magnitude Haiyuan earthquake in 1920 was taken as an example. Based on satellite remote sensing interpretation and field investigation of landslides, the original terrain of the Xinbaocun landslide before sliding was restored using the numerical simulation function of MATLAB based on the principle that the volume of the landslide body before and after sliding is equal. On this basis, the numerical simulation method was used to analyze the instability, deformation and failure characteristics of the Xinbaocun landslide under the action of earthquakes and invert the minimum horizontal ground motion of the slope instability. The landslide restoration results show that after the restoration of the Xinbaocun landslide, the slope surface shape is generally concave, and the slope distribution range is 12°~18°.The numerical simulation results show that under natural conditions, the slope deformation of the restored landslide is small, there is no obvious plastic deformation zone,the stability is good, and the overall stability coefficient is 1.355. Under the action of earthquake, when the input earthquake motion is 0.4g, the stability coefficient is 0.887, the slope is in an unstable and damaged state, and the slope body has a large area of deformation. The maximum deformation area is located near the top of the slope,and gradually decreases from the top to the foot of the slope. It is speculated that the landslide is a push-type landslide. The inversion results show that the minimum horizontal earthquake motion for slope instability is 0.36g. The research results of this paper can provide certain basic data and reference for the prevention and control of earthquake disasters in the Loess Plateau.

CO₂ flooding is one of the most effective technical means to improve the recovery of low permeability reservoirs. However, the injected CO₂ will cause asphaltene precipitation in crude oil, resulting in the decrease of reservoir permeability and the change of reservoir heterogeneity. In order to clarify the effect of asphaltene differential precipitation on the heterogeneity of low permeability reservoirs under different pressure conditions, a low permeability reservoir in Jilin Oilfield was taken as the research object. Through the CO₂ long core displacement experiment, the CO₂ displacement characteristics under different pressures were clarified. At the same time, combined with the test results of crude oil and core properties, the changes of crude oil asphaltene content and reservoir properties before and after displacement under different pressure conditions were analyzed, and the distribution law of asphaltene precipitation was further clarified. The results show that under immiscible conditions, the degree of crude oil recovery is low, only 55.11%. The asphaltene precipitation increases first and then decreases with the increase of displacement distance. CO₂ mainly displaces the large pore throat crude oil, and the asphaltene precipitation also mainly occurs in the high permeability area, thus inhibiting the reservoir heterogeneity. Under miscible conditions, the degree of crude oil recovery is high, up to 81.84%. Asphaltene precipitation increases with the increase of displacement distance. CO₂ can displace small pore throat crude oil. Asphaltene precipitation occurs in high permeability and low permeability areas, but low permeability areas are greatly affected, and reservoir heterogeneity is further strengthened.

In order to solve the problem of unbalanced ratio of excavation and anchor and the difficulty of single transportation in fully mechanized excavation roadway, a cooperative anchor truck for fully mechanized excavation roadway was designed. Based on ADAMS, the kinematics model of the cooperative anchor truck was established, and the trajectory planning of the efficient support operation was carried out. The mechanical characteristics and ultimate support distance of each leg during the forward movement of the supporting device and the supporting monomer were analyzed. The results show that during the forward movement of the supporting monomer, when the four legs are fully supported, the force and moment of the front leg increase by 196% and 195% respectively, and the force and moment of the rear leg decrease from 73.5 kN and 238 kN · m to 0 respectively. The limit distance of the support is 15.3 m, which meets the design requirements of the support. When the three legs are supported and the right rear leg is not supported, the force and torque of the left front leg are increased by 566% and 572% respectively, and the force and torque of the left rear leg are reduced from 145 kN and 462 kN · m to 0 respectively. The constant force and torque of the right front leg are 150.8 kN and 569.4 kN · m, and the limit distance is 14.99 m. It can be seen that under the special working condition of three-leg support and no support for the right rear leg, the limit distance of the cooperative transport anchor vehicle exceeds the maximum length of the roadheader, which meets the requirements of efficient support.

In order to improve the accuracy of geological hazard susceptibility assessment, Fuyang District in Hangzhou, Zhejiang Province was taken as the research area and a random forest method was proposed for evaluating geological hazard susceptibility, considering buffer zone optimization strategies. Firstly, nine evaluation factors were selected: normalized difference vegetation index, distance to roads, distance to faults, rainfall during the flood season, slope, aspect, ruggedness, distance to water systems, and lithology. Multicollinearity analysis was conducted to ensure the independence of the factors. Secondly, buffer zones of 0.5 km, 1 km, 1.5 km, and 2 km were constructed. Negative sample points were generated using random sampling to avoid cross-contamination between positive and negative samples, enhance sample representativeness, and improve the model's discrimination capability. An additional set of random sampling points without buffer zones was also established for comparison. The random forest algorithm was then used to train and test the geological hazard susceptibility model. Results indicated that the buffer zone optimization strategy significantly improved the model's predictive accuracy and that there was an optimal boundary for the buffer zone. The model's AUC(area under curve) value was highest at 0.815 for the 1 km buffer zone, indicating that negative samples collected within this buffer zone could more accurately distinguish geological hazard characteristics. Finally, based on the susceptibility evaluation results of the optimal buffer zone and the random forest model, high susceptibility areas were mainly concentrated in the mountainous regions in the northwest and southeast. The frequency ratio increased with the susceptibility level, validating the scientific validity of this method. This approach can provide a basis for geological hazard prevention and control in Fuyang District.