With the widespread application of artificial intelligence technology across various industries, our society has embarked on the journey towards the 4.0 intelligent era. To foster high-quality development in teaching reform at colleges and universities, which is empowered by information technologies such as artificial intelligence, in-depth interviews with 20 managers, implementers and educates involved in teaching reform across 11 colleges and universities were conducted. Qualitative analysis was performed using NVIVO software. Through analyzing the current application of artificial intelligence in teaching reform at colleges and universities, both achievements and challenges are identified. Finally, it is proposed to advance the intelligent application of teaching reform in colleges and universities from four perspectives such as people-oriented philosophy, talent support, financial support and institutional support.

In order to study the stability of the geological conditions of the water transmission and power generation system of Qichun pumped storage power station, and selecting the optimal scheme, engineering geological surveying, high-density electrical method, and geostress test were carried out in the engineering area to qualitatively and quantitatively describe the geological conditions of the engineering area. The advantages and disadvantages of multiple schemes of water transmission and power generation systems were analyzed based on the rock and soil stress state. The results showed that the three faults reduced the engineering geological stability of the western route plan, so the eastern route plan was selected. In addition, the stress conditions of both the central and tail underground power plants meet the requirements of engineering geology and hydrogeology. However, the stress distribution of the central power plant is more uniform and there are no fractures that restrict geological stability. Therefore, a better central power plant scheme is selected.

Multi-source heterogeneous geological big data is difficult to ensure accuracy during the structuring process. By constructing a standard stratigraphic system for Nanning basin and using the automatic borehole modeling method of the Nanning Geological Spatial Big Data Analysis System to create a 3D geological model, four factors were considered—engineering geological zoning, age strata, geological genesis types, and lithology—to assist in the rapid cleaning and processing of structured database entries. The results show that discontinuous areas, abrupt change areas, and topological error areas in the 3D geological model can quickly identify issues such as duplicate, abnormal, and missing structured data, effectively improving the speed and accuracy of error identification.

Based on the 151 ancient city sites from the Western Han Dynasty to the Ming and Qing Dynasties in the Hexi Corridor of Gansu Province, GIS(geographic information system) spatial analysis method was used to study the spatial and temporal evolution of ancient city sites and their distribution characteristics in the Hexi Corridor. The results show that the city sites in Zhangye City have the highest distribution numbers, and county-level city sites are the most numerous grade.They are concentrated in Zhangye City, Jiuquan City, and Wuwei City, the distribution of city sites in each period exists certain unevenness and concentration, which is mainly manifested in the Ming and Qing Dynasties, and may be related to the better preservation of the period. Zhangye has experienced multiple periods of high density nucleus of city sites,the directional trend and concentration trend of the distribution orientation of city sites become increasingly obvious with the distribution of time, showing a tendency of “east-southwest-northwest”.

The analysis of the change of rural residential land use and rural permanent resident population is helpful to better understand the relationship between rural people and land. The county area of Guangdong Province was selected as the research unit, based on the annual change data of land use and the third national land survey data, the dynamic coupling and decoupling model were used to analyze the rural residential land and permanent resident population. The results show that the coupling types of the rural resident population and rural settlements in Guangdong province are mainly negative and high level coupling types, and the coupling characteristics are obvious. The negative coupling area is located in the Pearl River Delta and northern Guangdong, and the high level coupling areas are mainly distributed in western Guangdong. The decoupling type is mainly strong negative decoupling and expansionary, which are distributed in northern Guangdong and western Guangdong respectively, which shows that the western Guangdong region has great development potential. The conclusion of the study shows that the change characteristics and coupling of rural residential land and permanent resident population is a direct reflection of the relationship between rural people and land, and the research results can provide reference for the reform of rural land system and the development of rural industry.

In order to study the impact of enterprise cost sharing and government subsidies on the green effort level, pricing and profit of green supply chain members, considering a green supply chain consisting of a manufacturer and a retailer, four models were established: no cost sharing and no government subsidy(NN), cost sharing but no government subsidy(CN), cost sharing and government subsidy manufacturer(CM) and cost sharing and government subsidy retailer(CB). The Stackelberg game was used to solve the problem, and calculation results were analyzed. The research shows that the manufacturer’s profit is positively correlated with the green R&D cost sharing ratio, and the green marketing cost sharing ratio and the government subsidy coefficient increase first and then decrease. The retailer’s profit is negatively correlated with the proportion of green R&D cost sharing and the proportion of green marketing cost sharing, and it increases first and then decreases with the government’s subsidy coefficient. Finally, based on the research conclusions, relevant suggestions are put forward to provide decision-making ideas for green supply chain cost sharing and government subsidy business.

At the present stage in China, the situation of rural domestic sewage collection and treatment is grim, and management is difficult. Rural domestic wastewater treatment has become one of the important tasks in the implementation of rural revitalization strategy. Focusing on rural MBR membrane treatment stations, the influence of water quality on their operating conditions was comprehensively analyzed. Key water quality parameters including chemical oxygen demand(COD), ammonia nitrogen (NH₃-N), total phosphorus(TP), and suspended solids (SS) were analyzed in detail to clarify the characteristics of wastewater quality. In terms of sludge characteristics, the capillary suction time (CST) was used to evaluate the sludge dewatering performance, and it is found that the change of water quality could change the difficulty of sludge dewatering. Using bioinformatic analysis, it is revealed that the structure of microbial community was intrinsically linked to water quality parameters, and the relative abundance of species under different water quality conditions showed obvious differences and was closely related to the treatment efficiency. With the help of membrane fouling monitoring methods, such as transmembrane differential pressure(TMP) measurement, the membrane fouling status can be grasped in real time. Through correlation analysis, it is found that there are complex associations between water quality parameters, sludge characteristics and biological information, which affect the operation of rural MBR membrane treatment stations, providing a comprehensive theoretical basis and data support for the precise control of the operation of the stations, which can help to improve the efficiency and quality of rural wastewater treatment and reduce the operating costs.

The emergence of “digital economy” is both a favorable and unfavorable factor, which brings many opportunities and challenges for the whole banking industry. In recent years, along with the rapid development of digital economy and network technology, the financial industry is experiencing a profound revolution. Selecting the data of 42 commercial banks in China from 2010 to 2021 as a sample, the effect of digital transformation on the business performance of commercial banks was examined from the aspects of profitability and safety respectively, and on this basis, examines whether the effect of digital transformation is heterogeneous. The empirical results show that digital transformation has a significant positive effect on the improvement of commercial banks’ profitability and security, and there is heterogeneity in the effects of digital transformation on commercial banks’ business performance across different types of banks and different regions. Therefore, commercial banks need to clarify their transformation strategies, upgrade their technology systems and realize product innovations to facilitate digital transformation.

The state of health(SOH) and remaining useful life(RUL) of a battery are key indicators for measuring battery performance degradation and remaining useful time. Predicting battery SOH and RUL is of great importance in practical applications. Usually, battery operation data is used to train machine learning algorithms, such as neural networks or deep learning, to capture the changing patterns of battery SOH and RUL and make predictions. Traditional machine learning models often use a single model to adapt to the entire dataset, which is inadequate when dealing with complex and highly heterogeneous data. Building a model for each prediction target incurs high training and maintenance costs. Sparse mixture of experts (SMoE) was used to construct a joint prediction model for battery SOH and RUL, and battery fusion data was used to simultaneously predict battery SOH and RUL. The results of testing on NASA’s public dataset show that the proposed joint prediction model can effectively predict battery SOH and RUL, with a mean square error of 0.069 for SOH prediction and 2.042 for RUL prediction. Tested on the EIS public dataset, the mean square error of the SOH prediction value of the joint prediction model was 0.118, and the mean square error of the RUL prediction value was 3.072, indicating a significant improvement in accuracy. The models and methods proposed in the text have certain reference and application value.

The safety cover thickness required for TBM (tunnel boring machine)tunneling in hard rock is such that it is too large to increase the total length of the tunnel design without increasing the cost. Therefore, the study of the minimum safety cover thickness for TBM tunneling in hard rock is of great engineering significance. In light of the aforementioned considerations,the Guangzhou-Dongguan-Shenzhen Intercity Railway Xixiang Station-Bao’an Station double-mode shield tunnel project case was drawn upon to investigate the minimum safe overburden thickness of varying parameters under the condition of changing rock grades. The results indicate that when the arch displacement method is employed, if the tunnel perimeter rock class is II or III, and the thickness of soft soil is between 0 and 3 times the diameter of the tunnel, then the minimum safe rock cover thickness is between 0.2 and 1.2 times the diameter of the tunnel. When the pressure arch method is employed for simulation, if the rock cover class is II or III, and the soft soil thickness is between 1 and 3 times the tunnel diameter, the ratio of the minimum rock cover thickness to the depth of burial exhibits a tendency to increase and then decrease with the increase of the hard rock thickness,reaching a maximum value of 0.39. When the overburden grade is grade IV and the thickness of the soft soil is 1 to 3 times the diameter of the tunnel, the ratio of the minimum rock cover thickness to the depth of burial is observed to decrease with the increase of the hard rock thickness, reaching a maximum value of 0.42. The conclusions can provide engineering guidance for TBMs to safely tunnel through hard rock.