In order to solve the problem of difficulty in determining the optimal measurement points for bearing signal acquisition. Taking the NU306 bearing-housing system as the research object, the bearing housing to carry out multi-measurement points vibration test experiment. The local linear embedding algorithm was used to linearly reduce the multi-dimensional space data of the bearings to obtain the sensitivity matrix of the measurement point. The optimal position of the measuring point under varying load and rotation speed was studied when the inner or outer ring are defective. The results show that for bearings with outer ring failures, the optimal measurement point is the one closest to the location of the failure when the load or rotational speed increases. For bearings with inner ring failures, the optimal measurement point is the one at lower loads far from the center of the housing when the load or rotational speed increases. The results can provide an effective reference for the selection of measurement points under different operating conditions.

In response to the problem of insufficient analysis of the risk impact on system components and inadequate classification management in civil aircraft maintenance, which leads to sudden failures during component operation, a comprehensive risk impact factor was introduced to accurately evaluate the importance and potential hazards of civil aircraft system components, and a component preventive maintenance strategy considering the comprehensive risk impact of multiple factors was established. A chance maintenance decision model for civil aircraft systems was established with the objective of optimizing the maintenance cost of components, taking into account the comprehensive risk impact of multiple factors on components. The model comprehensively considers the time correlation between system components and the cost generated by the comprehensive risk impact of multiple factors on components. Example verification shows that compared to preventive maintenance decisions that do not consider the impact of component risks, the maintenance decision proposed in this article reduces the total maintenance cost of civil aircraft systems by about 20.20%, and the reduction rate of preventive maintenance and replacement frequency is about 41.23%.

Aiming at the problem of poor model accuracy caused by poor stability and strong randomness of wind power output. A short-term prediction model of wind power based on quadratic decomposition error compensation was proposed. Firstly, BiLSTM (bidirectional long short-term memory) prediction model is established to predict wind power and output prediction errors. Secondly, an IDBO (improved dung beetle optimizer) algorithm was used to initialize the population by using chaotic mapping, update the position of rolling dung beetles by introducing golden sine strategy, and update the position of thieving dung beetles by adding dynamic adaptive weight coefficient to optimize the parameters of the prediction model. Prevent the network from falling into the local optimal solution, and adaptively search the optimal parameter combination. Then, using the decomposition-reconstruction-decomposition strategy, CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise) was used for the first decomposition. In addition, SE(sample entropy) and K-means are introduced to reconstruct the sequence according to frequency, and the high-frequency error sequence was decomposed into error sequences of different frequency bands by VMD(variational mode decomposition). Improve the prediction efficiency and accuracy of subsequent models. Finally, the input error compensation model of each component was used to predict and the Attention mechanism was introduced to learn the feature relationship of different time steps and give different weight values to enhance the attention to key information. Through the measured data of a wind farm in Xinjiang, the prediction accuracy of the proposed model is proved to be high and has significant advantages.

The rheological parameters of drilling fluid have an important impact on accurately predicting the hydraulic parameters of deepwater and ultra-deepwater drilling wells. The rheological experiments were carried out on commonly used HEM(high efficient mud) drilling fluids and synthetic-based drilling fluids in the deep waters of the South China Sea under conditions of 4 to 210 ℃ and 30 to 180 MPa. The variation laws of rheological parameters such as apparent viscosity, plastic viscosity, and dynamic shear stress with temperature and pressure were revealed in a wide range of temperature and pressure. Based on the experimental data, nine existing rheological models were compared and evaluated. It was found that the Ross model is suitable for synthetic-based drilling fluid, and the Herschel-Bulkley model is suitable for HEM drilling fluid. On this basis, a general predictive model for rheological parameters of HEM and synthetic-based drilling fluids was created, which is applicable to alternating high and low temperatures, high and low pressures. The maximum error of this model is 11.95%, with an average error of 0.62%, which is better than existing models.The bottom hole pressure error is 0.28% when using HEM drilling fluid and 0.181% when using synthetic drilling fluid, which can meet the requirement of deep water drilling in the South China Sea.

In response to the common problem of secondary lining cracking in double-arch tunnel without middle drift, how to improve its mechanical characteristics to ensure the safety of tunnel construction and operation is the focus of this study. Based on the arch section of Yijin Expressway Huangjiaoping Tunnel Project, numerical simulation method was adopted, the influence of support parameters such as the thickness of the initial support, the spacing of the steel frame, and the thickness of the secondary lining of the advanced tunnel on the displacement of surrounding rock, the mechanics characteristics of the initial support and the secondary lining of the advanced tunnel were deeply studied, and reasonable and optimized support parameters were proposed. The results show that as the thickness of the initial support increases or the spacing of the steel frame decreases, the displacement of the surrounding rock of the advanced tunnel and the principal stress of the secondary lining continue to decrease, and the principal stress of the initial support continues to increase. Among them, the maximum tensile stress of the secondary lining decreases significantly. When the thickness of the initial support is 0.28 m or the spacing of the steel frame is 0.5 m, the maximum tensile stress decreases by about 15% compared with the most unfavorable condition. As the thickness of the secondary lining increases, the displacement of surrounding rock, the principal stress of the initial support and the secondary lining of the advanced tunnel decrease significantly. Compared with the thickness of the secondary lining of 0.7 m and the thickness of the secondary lining of 0.5 m, the maximum tensile stress of the secondary lining is reduced by 23.8%. Therefore, moderately increasing the thickness of the initial support or decreasing the spacing of the steel frame or increasing the thickness of the secondary lining can effectively improve the stress of the secondary lining. It is suggested that the thickness of the initial support of the advanced tunnel should be 0.28 m, the spacing of the steel frame should be 0.5 m, the corresponding steel frame type is I22b, and the thickness of the secondary lining should be 0.7 m under the shallow buried state of V-class surrounding rock.

As industry and agriculture continue to evolve, the threat of organic contamination in groundwater to human health is gaining attention. Following the health risk assessment method recommended by the USEPA, and considering local natural geographical and hydrogeological conditions, organic pollutants in Zhuzhou City’s groundwater were assessed. Using a health risk assessment model, non-carcinogenic and carcinogenic risks from three exposure pathways-drinking water, skin, and inhalation-were evaluated. Results show that key organic pollutants in Zhuzhou City’s groundwater include dichloromethane, 1,2-dichloroethylene, trichloroethylene, tetrachloroethylene, p,p'-DDE, and p,p'-DDD. Non-carcinogenic risks from these pollutants are below specified limits, but every sampling points exceed carcinogenic risk limits, with ZZS119 surpassing the maximum acceptable carcinogenic risk. Inhalation is the primary exposure pathway, contributing to approximately 81% of total risk. Tetrachloroethylene poses the highest carcinogenic risk at 81.08%, followed by trichloroethylene at 11.65%. Urban discharges, volatile organic compounds from chemical plants, insecticide use in forestry, and domestic wastewater discharge have severely contaminated Zhuzhou City’s groundwater, resulting in unacceptable carcinogenic risks for local residents.

Land ecological security is the core of sustainable use of land resources, and land use changes caused by human activities change the structure and function of ecosystems, which have a serious impact on the regional ecological security system. In order to explore the changes in ecological security in Chongqing in recent years and in 2030, Chongqing was taken as the research object and PLUS (patch-level land use simulation) model was employed to simulate land use changes under the scenarios of natural development, ecological priority and development priority in 2030. Based on the ecological perspective, an ecological security evaluation index system was constructed, and the mutation model was combined to quantitatively evaluate the level of land ecological security. The results show that the spatial distribution of land use types in Chongqing is quite different, the cultivated land area decreased by 3 995.14 km², and the construction land area increased by 1 147.36 km², realizing rapid urban development. At the same time, 64.53%, 67.31% and 55.97% were relatively safe or above under the three scenarios. The spatial pattern of ecological security in Chongqing is opposite to the spatial pattern of population density and GDP, and consistent with the spatial pattern of natural data such as vegetation cover and slope. Through the ecological assessment of land use changes in previous years and under different scenarios, it provides a basis for high-quality coordinated development of ecology and economy.

In order to reduce the panalkalisation of alkali-inspired materials for repair, the inhibition of panalkalisation of alkali-inspired materials for repair was investigated by means of surface spraying of admixtures, doping of glass powder, and doping of red mud. The inhibition mechanism was also analysed by scanning electron microscopy, nitrogen adsorption analysis and super depth of field image analysis. The results show as follows. After brushing PNC401 waterproof coating or organosilicon waterproofing agent on the surface of mortar specimen, the amount of alkali flooding is reduced by 61.3% and 26.7%, respectively. The dosage of glass powder and red mud within 15% meets the requirements of the performance of the repair mortar. The amount of alkali flooding was reduced by 60.7% and 52.0% after doping of 15% glass powder and red mud, respectively, and the number of pore spaces inside the mortar was less, no obvious cracks were produced, which reduced the dissolution of alkaline ions. The number of pores inside the mortar is less, and there is no obvious crack, which reduces the dissolution channel of alkaline ions, and it has a good inhibition effect on the alkaline flooding of alkaline stimulating materials for repairing.

In order to solve the problem of real-time monitoring and accurate prediction of structural deformation of platform doors on high-speed railway lines, an artificial intelligence-based neural network method was used. Structural deformation data of platform doors, involving 210 different conditions of train length, blocking ratio, installation distance, and speed, were selected as training samples for the network model. Two neural network models, CNN(convolutional neural network) and K-Fold(K-Fold cross-validation) optimized GRNN(general regression neural network), were used to establish predictive models for platform door structural deformation under different working conditions of high-speed railways. These models were compared and verified with the remaining sample data. The research shows that both models effectively predict the operation and maintenance data of railway platform door structures. The K-Fold optimized GRNN model is superior to the CNN model in prediction accuracy. The Mean Square Error of the K-Fold optimized GRNN model is maintained within 0.22, and theRoot Mean Square Error is within 0.27, which is at the leading level in the field. The K-Fold optimized GRNN model better predicts the structural deformation of platform doors when trains pass, providing data references for the design and maintenance of high-speed railway platform doors.

The rapid increase in highway tunnel mileage also signifies a gradual rise in operational costs, and the pressing issue of high electricity operation costs for highway tunnels urgently needs to be addressed. To reduce the electricity operation costs of highway tunnels and achieve energy conservation and emission reduction, it is essential to consider optimizing the energy structure under the “dual carbon” background. This involves exploring the application prospects of renewable energy supply systems in highway tunnels and establishing a wind-solar-storage complementary power generation system. Taking a 498 m long highway tunnel load as an example, an optimization based on an improved PSO (particle swarm optimization) algorithm was conducted. The goal was to minimize the full lifecycle costs of equipment construction and maintenance, with constraints on the power shortage load rate and storage capacity, specifically for the wind-solar-storage complementary system. The results show as follows. The improved discrete adaptive particle swarm algorithm obtained the optimal solution after the 20th iteration, while the standard particle swarm algorithm reached the optimal solution near the 300th iteration, indicating a stronger optimization capability of the discrete adaptive particle swarm algorithm. Compared to the standard particle swarm algorithm, the improved discrete adaptive particle swarm algorithm reduced the investment and usage costs of the wind, solar, and storage equipment by 578 300 yuan, approximately 17.37%.Compared to the annual electricity cost of the example tunnel, which is 515 000 yuan, the full lifecycle cost of the wind-solar-storage complementary system is 3 328 800 yuan. The investment cost will be recouped within 7 years, and the investment return rate of this wind-solar complementary system is 10.47%. Over the 20-year lifespan of the equipment, the wind-solar-storage complementary power generation system will save 6 971 200 yuan in electricity expenses.