Rock mass classification is a fundamental component in tunnel engineering construction. With the rapid advancement of mechanized and intelligent construction technologies in China, drilling-parameter-based intelligent rock mass classification methods have become crucial in facilitating smart mechanized tunneling. This need is especially pronounced in the mountainous regions of Western China, where complex terrain and challenging construction, combined with limited experience in mechanized tunneling and the restricted applicability of current intelligent rock mass classification methods, make mechanized construction crucial for improving project quality and effectively controlling construction risks. A predictive method was proposed for intelligent rock mass classification using drilling measurement parameters. Focusing on multiple long tunnels as research subjects, on-site drilling parameters were collected and rock mass mechanical tests was conducted to construct a drilling parameter database, then intelligent algorithms was applied, such as support vector regression (SVR) and particle swarm optimization-back propagation (PSO-BP), to develop a predictive model for rock mass classification. The result indicates that the absolute value of correlation coefficient |r_s| between drilling parameters and rock mass classification indices is greater than 0.6, demonstrating a significant correlation, where torque and rotational speed show the strongest correlation with rock mass classification indices. A standardized parameter index database with 574 ideal samples was established through data-cleaning tools. Comparative analysis of predictive accuracy across intelligent algorithms indicated that the PSO-BP model demonstrated the best performance. The PSO-BP neural network-based prediction model was validated by transient electromagnetic (TEM) and tunnel seismic prediction (TSP) advanced geological forecasting, confirming its accuracy in predicting rock mass classification and providing reliable support for mechanized tunnel excavation.

Aiming at the problem of high-precision, high-speed and efficient temperature control caused by multi-point measurement and asymmetric heating condition of input and output, a new algorithm (IGRO-FuzzyN-PID) based on IGRO-PID and multi-layer fuzzy nested algorithm was proposed. Simulation results show that IGRO algorithm is superior to CPO (crested porcupine optimizer)、IPSO(improved particle swarm optimization)、COA(crayfish optimization algorithm)、GA(genetic algorithm) in PID control system. Simulation and experimental results show that compared with the IGRO-PID algorithm, the overshoot, steady-state error and average error of the IGRO-FuzzyN-PID algorithm are optimally increased by 70.91%, 70.69%, 82.35% and 86.89%, 76.23%, 86.56% under symmetric and asymmetric input and output conditions. It is proved that the proposed algorithm meets the control requirements of high precision, high speed and high efficiency under symmetric and asymmetric input and output conditions.

In order to investigate the aging mechanism of high dosage rubber powder modified asphalt, with the help of 20%, 25% and 30% of three different dosages of rubber asphalt, using four-component analysis experiment and infrared spectroscopy experiment, evaluation of aging rubber asphalt four-component indexes change, and analyze the chemical composition and functional group changes before and after aging, through the comparative study, to reveal high dosage rubber powder modified asphalt aging mechanism under different aging conditions. The aging mechanism of high doped rubber powder modified asphalt under different aging conditions was revealed through comparative study. The results show that: the aging of high dosage rubber powder modified asphalt components more significant. 20% dosage, the saturation fraction, aromatic fraction and gum decreased by 4.4%, 3.4%, 4.3%, respectively, asphaltene increased by 117.7%; 25% dosage of rubber asphalt saturation fraction decreased by 5.0%, the aromatic fraction decreased by 8.4%, gum decreased by 4.9%, asphaltene increased by 119.3%, and 30% dosage, the decrease is greater, respectively, 7.4%, 9.5%, 6.0%, asphaltene increased to 128.9%; aging process, high dosage of rubber powder modified asphalt has less mass loss, the combination of light components of the asphalt and cracked rubber binding reduces the light component activity and enhances the resistance to aging; high dosage of modified asphalt in the aging conditions of carbonyl and sulfoxide group index growth is more significant, which may lead to a decline in the performance of the The compatibility of rubber and asphalt is more susceptible to aging, which is manifested by more intense vulcanization phenomena and changes in molecular chain cross-linking. The research results provide theoretical support for the aging mechanism of rubber asphalt, and for the practical application and maintenance of high dosage of rubber powder asphalt pavement, which is of great significance to improve the performance of rubber asphalt pavement.

Natural cooling is one of the more energy-efficient and widely used cooling methods in data center air conditioning systems. Based on the climatic characteristics of Suzhou, Beijing, Guiyang, Guangzhou and Urumqi, the natural cooling system model of data centers was established by TRNSYS, and then the energy saving effect of data centers under the same chilled water supply and return temperatures in different regions was studied. The results show that when the chilled water supply/return temperatures are 15/22 ℃, the longest time for complete natural cooling is in Urumqi, accounting for 67.4% of the year, and the shortest time is in Guangzhou, accounting for 10.2% of the year; the longest time for complete mechanical cooling is in Guangzhou, accounting for 63.0% of the year, and the shortest time is in Urumqi, accounting for 4.3% of the year; the longest time for part of natural cooling is in Guiyang, accounting for 31.8% of the year, and the shortest time is in Beijing, accounting for 4.3% of the year. The longest part of natural cooling time is in Guiyang, accounting for 31.8% of the year, and the shortest is in Beijing, accounting for 18.6% of the year. At full load, the lowest annual average system power usage effectiveness (PUE) was in Urumqi at 1.227, and the highest PUE was in Guangzhou at 1.299. The average annual PUE of the five cities decreases as the load factor increases, and the effect of air conditioning load on the average annual PUE becomes smaller as the load factor increases. The findings provide theoretical support for guiding the application of natural cooling technology in data centers in different regions.

The loess hilly area is one of the areas with a high incidence of geological disasters, and it is urgent to use appropriate evaluation factors and training models to conduct research on the susceptibility assessment of geological disasters. Kangdian Town, Gongyi City, the township hardest hit during the “7·20” extremely heavy rainstorm in Zhengzhou, was taken as the study area. Based on satellite remote sensing interpretation, field survey, UAV aerial photography and relevant data collection, an evaluation system covering 13 influencing factors of three main control factors, namely loess interface, human engineering activities and hydrodynamic effects, was constructed. CatBoost model, XGBoost model and LightGBM model were used to carry out the evaluation study of geological disaster vulnerability. Based on the machine learning model with the best performance, SHAP(shapley additive explanations) algorithm was used to complete the global interpretation of characteristics and dependency analysis. The results show that the CatBoost model has higher accuracy than other models (XGBoost and LightGBM), and performs the best in AUC(area under curve) value, accuracy, precision, recall, F₁ score, and field validation. The proportion of areas with extremely high, high, medium, low, and extremely low susceptibility is 3.19%, 1.40%, 2.04%, 5.93%, and 87.44%, respectively. The extremely high and high susceptibility areas are mainly distributed on both sides of gullies with strong human activities, and slope cutting and building are important causes of geological disasters. The aim of this study is to optimize the modeling approach, investigate the uncertainty and interpretability of the modeling process, explain and analyze the decision-making mechanism of machine learning susceptibility, and provide scientific basis for geological disaster prevention and control in the loess hilly area of western Henan.

A new anomaly sound detection algorithm was studied that combines attention mechanisms and domain generalization techniques to more accurately identify normal and abnormal sounds in mechanical equipment. Specifically, two neural networks were jointly trained using a sub-cluster Adacos loss function, with features modeled by a Gaussian mixture model (GMM). Anomaly scores were calculated using negative log-likelihood values, and a 90th percentile threshold was set for detection. The algorithm demonstrated strong performance across seven types of machines, including fans and bearings, achieving harmonic mean AUC(area under curve) and pAUC values of 76.69% and 87.99%, with the highest performance observed on valve data. Compared to two baseline systems, the algorithm improved AUC and pAUC by 24.08% and 20.68%, respectively. Ablation studies further confirmed the positive impact of the GMM, attention mechanism, and Scadacos loss function. When tested against eight other algorithms on the same dataset, the proposed method showed a 4.16% improvement in the harmonic mean of AUC and pAUC, highlighting its significant advantage in anomaly sound detection tasks.

In view of the position control accuracy and body chattering of small unmanned helicopter under large disturbance, an improved sliding mode controller (SMC) was proposed. Firstly, for the unknown parameters in the dynamic model of small unmanned helicopter named Align T-REX 300, three flight experiments were designed for the data acquisition, determining the comprehensive aerodynamic parameters. Then, the dual-channels control strategy with an improved SMC was designed to realized the helicopter hovering. The parameters ranges of SMC were presented by combining stability analysis, which can effectively suppress chattering. The model validation experiment shows that the aerodynamic parameters determined by the flight experiments have high fidelity. Moreover, the control simulations show that the steady state error of the step responses is less than 0.02 under the continuous large disturbance. Under the improved SMC with high control accuracy and weak tremor, the servos' control signal curves are smooth, which is more conducive for achieving the flight control of unmanned helicopter under the disturbance in actual engineering.

In order to study the effect of freeze-thaw cycle on the stability of lime-amended loess slope, the change rule of shear strength and soil-water characteristics of lime-amended loess under different numbers of freeze-thaw cycles was obtained by straight shear test and soil-water characteristics test, and the stability of high-fill loess slope was analysed by using the strength discount method with MIDAS GTS NX software. The results show that: the internal friction angle and cohesion of the soil samples both increase with the increase of the age of maintenance, and with the increase of the number of freeze-thaw cycles, the internal friction angle of the soil samples will first increase and then gradually tend to be stable, and the cohesion will first decrease and then gradually tend to be stable; the lime-amended loess has its matrix suction maximum at the lowest temperature of the first freeze-thaw cycle, and its matrix suction is minimum at the second freeze-thaw cycle, and after that the matrix suction of the soil body increased. Freezing and thawing cycles will cause the slope infiltration flow rate to increase; the trend of pore water pressure changes in the freezing and thawing slope model is the same as that of the unfrozen slope, and the pore water pressure is positive at the bottom of the slope model, and then decreases gradually near the top of the slope, and then reaches the minimum at the top of the slope. The freeze-thaw cycle will cause the strain of the slope to increase under rainfall conditions, which affects the safety and stability of the slope; the shallow freeze-thaw has little effect on the safety of high-fill improved loess slopes.

Exploring the spatiotemporal evolution of FVC(fractional vegetation cover) in the East Pamirs Plateau and the driving mechanisms of FVC by the driving forces, providing scientific data support and reference for vegetation protection in the study area. Based on Landsat remote sensing image data, meteorological data, DEM (digital elevation model)data and other data in 1993, 2000,2007,2014 and 2021, pixel dichotomous model, Markov transition model, spatial auto-correlation analysis and geodetector were used to research on the spatiotemporal evolution and detection driving forces of vegetation coverage in the East Pamirs Plateau. Results show as follows. The FVC in the East Pamirs Plateau is exhibiting a fluctuating upward trend, in terms of spatial distribution, is overall characterized by “higher in the east, lower in the west and extremely low in the medium”. The spatial autocorrelation analysis of vegetation coverage in the East Pamirs Plateau from 1993 to 2021 showed a significant positive spatial autocorrelation, with the global Moran's index of FVC 0.27~0.40. Local spatial autocorrelation shows that the vegetation coverage in local areas is dominated by low-low aggregation and high-high aggregation. Factor detection results showed that the explanatory power (q) of various driving factors on the spatial heterogeneity of vegetation coverage in the study area fluctuated to varying degrees from 1993 to 2021, with land use and DEM were the main driving factors of FVC in the East Pamirs Plateau. Results of the interaction detection showed that the influence of interaction between driving factors is greater than that of a single driving factor, and the interaction results are all enhanced.

The strength reduction method is an essential approach for calculating the slope safety factor, with its computation reliant on the criterion for slope instability during the process of strength reduction. Among the commonly employed criteria for slope instability, displacement mutation stands out; however, its determination remains relatively subjective at present. The maximum slope displacement was considered as a function of the strength reduction factor based on the strength reduction method. The standard deviations of the maximum slope displacements for different strength reduction factors were calculated. Consequently, a method for determining the slope safety factor within the strength reduction method, based on the standard deviations of the maximum slope displacements, was proposed. The method was validated through a typical case study and subsequently applied to a practical engineering project. The results demonstrate that the proposed method can objectively identify the occurrence of slope displacement mutation during the strength reduction process and effectively ascertain the slope safety factor. The proposed method is especially applicable for practical slope engineering projects requiring quantitative comparison of safety factors for different cases.