With the improvement of intelligence, the drilling industry ’s demand for real-time identification of lithology while drilling was becoming more and more urgent. An intelligent inversion method of lithology while drilling is proposed based on the acoustic signal and vibration signal ( acoustic vibration signal ) of broken rock during drilling. Firstly, the original signal samples were obtained by drilling seven different types of rocks through indoor micro-drilling experiments. During the acquisition process, the drilling parameters ( drilling speed, rotation speed, bit size ) were changed and the corresponding signal data were obtained. According to the characteristics of the collected acoustic vibration signal, the time-frequency image with signal characteristics was obtained by short-time Fourier transform. On this basis, an improved VGG16 convolutional neural network model was constructed to realize the intelligent identification of lithology, and the training, evaluation and tuning of the model are realized by hyperparameter optimization. Then, the transfer learning training strategy is introduced, and different drilling parameters were used as data labels. According to the parameter values, the source domain and the target domain were divided to realize the rapid identification of the small sample target domain. The experimental results show that the transfer learning results of the model are different with the change of drilling parameters. The lithology inversion model based on acoustic-vibration signal training has high prediction accuracy and strong generalization ability. The accuracy of the acoustic signal test set is up to 99%, and the accuracy of the vibration signal test set is up to 100%. Under the change of penetration rate, the acoustic and vibration signals are least affected, which can achieve more excellent results when used as data labels for lithology inversion, and the accuracy of lithology inversion is the highest when the penetration rate is small as the target domain. In the process of lithology inversion, different signal types are suitable for different rocks. Among them, the sound signal has the highest applicability to coarse yellow sandstone, and the vibration signal is more suitable for granite. The research results have certain reference value for improving the intelligent degree of working face drilling.

In order to study the development law of pile top cumulative displacement of ring wing single pile foundation under horizontal cyclic load, a three-dimensional numerical model of the interaction between ring wing single pile and saturated clay was established through secondary development using ABAQUS, and also simulated the process of soil stiffness attenuation. Numerical results indicate that installing gravity type ring wings at the mud surface position of traditional single pile foundations can enhance the overall horizontal resistance of the ring wing single pile foundation, thereby reducing the cumulative displacement of the ring wing single pile under cyclic loads. The displacement of the pile top will decrease with the increase of the height and diameter of the gravity type ring wing, but increasing the diameter of the gravity type ring wing has a more significant effect on reducing the horizontal displacement of the pile top. Increasing the depth of the pile into the soil can significantly reduce the cumulative displacement at the top of a single circular wing pile under cyclic loading.

Further analysis is needed to comprehend how the trend of land subsidence in the Beijing plain area evolves following the implementation of a series of prevention and control measures. Based on the Sentinel-1A image data from 2017 to 2022, the PS-InSAR technique was employed to assess the current situation of land subsidence in the plain area of Beijing, and the geographical detector was utilized to analyze the main influencing factors of land subsidence and their interaction effects. The findings reveal the following: The main conclusions were as follows. The distribution of land subsidence in Beijing plain is uneven, and the maximum subsidence rate reaches 90 mm/a. The subsidence rate of non-funnel area shows a certain degree of slowing trend from 2020 to 2021, while the slowing trend of subsidence rate in funnel area is not obvious. Groundwater as the primary influencing factor of land subsidence, with the thickness of the compressible layer closely following. The interaction among all influencing factors demonstrates a factor enhancement relationship, with the interaction between groundwater and subway infrastructure exerting the most significant impact on land subsidence. This highlights that groundwater and urban construction jointly propel land subsidence in the Beijing plain area. These research findings provide a scientific foundation for the comprehensive assessment, precise prediction, and integrated prevention and control of land subsidence in the Beijing plain.

In order to analyze the design parameters and technology adaptability of multi-stage temporary plugging and fracturing in the Triassic Chang-6 reservoir of a block in Suijing Oilfield. Based on the geological and engineering design data of the block, the influencing factors of multi-stage temporary plugging and fracturing were quantitatively analyzed in terms of reservoir characteristics, technology parameters, and construction effect. The combined weighting method was used to determine the weights of each parameter, and the ridge-type membership function was used to determine the membership degree of each factor. Based on the principles of fuzzy transformation and maximum membership degree, a fuzzy comprehensive evaluation model for multi-stage temporary plugging and fracturing was established. This model transforms the traditional single-index qualitative development effect evaluation into multi-factor quantitative evaluation. The model was applied to evaluate and analyze the Triassic Chang-6 reservoir in a block of Suijing Oilfield. The results show that this evaluation model results have an adaptation rate of 89.13% when compared to the actual effect data in the field, which can effectively evaluate the effectiveness of the implementation of temporary plugging and fracturing measures in the oil wells of the study area. The evaluation system can provide valuable references for the next implementation of temporary plugging and fracturing measures in the study area, and even optimize parameters for multi-stage temporary plugging and fracturing transformation in similar reservoirs.

With the rapid development of the energy industry and technological innovation, a large number of professional terms and expressions are constantly updated, and new words continue to emerge. However, traditional neologism discovery methods often rely on dictionaries or rules, and it is difficult to efficiently process and update a large number of specialized terms, especially in the rapidly changing energy field. Therefore, combined with the characteristics of text data in the energy field, a new word discovery method in ENFM(energy field combining N-Gram and multiple attention mechanism) was proposed. Firstly, the N-Gram model was used to process the text data in the field of energy, and the candidate list of new words was generated by statistics and analysis of word frequency. Subsequently, the ERNIE-BiLSTM-CRF model integrating multiple attention mechanism was introduced to further improve the accuracy and efficiency of neologism discovery. Compared with the traditional neologism discovery technology, the accurate identification and overall efficiency of neologism have been significantly improved. The accuracy rate, recall rate and F₁ value of neologism in the data set of policy text in the energy field are 95.71%, 95.56% and 95.63%, respectively. The experimental results show that this method can accurately identify new words in a large number of text data in the field of energy, effectively identify the specific words and expressions in the field of energy, and significantly improve the recognition ability of professional terms in the field of energy in Chinese word segmentation tasks.

Due to the complex reservoir conditions and multi-scale pore structure of shale gas, the production shows significant nonlinear characteristics over time. Traditional production prediction methods, which rely on statistical analysis of geological and engineering data, find it difficult to adapt to the complexity of geological conditions and thus cannot achieve high accuracy. A method that combines the hyperbolic decline model with a composite function having time attributes was proposed. The improved A-PSO (adaptive particle swarm optimization algorithm) was used to find the optimal model parameters, establishing a composite time hyperbolic decline model. The research results show as follows. The A-PSO optimization algorithm can automatically adjust parameters and model structure according to the complexity of production data and data changes, finding the optimal parameter combination more quickly and accurately, thereby improving prediction accuracy. The production fluctuates greatly over time, making it difficult for conventional decline models to reflect its characteristics. The composite time decline model, with its strong flexibility, can consider the complexity and variability of oil and gas reservoirs, more accurately describe the production changes of shale gas wells at different stages, and provide higher fitting accuracy, making the production prediction closer to the actual value.

Accurately and in real-time understanding the changes in the scope and species communities of intertidal wetlands is an important foundation for achieving sustainable development and management of wetland intertidal zones. In recent years, global warming, rising sea levels, and human activities such as coastal development, reclamation, and aquaculture have caused serious damage to the intertidal zone. At present, there is a lack of systematic research on the classification of mangrove tidal flats in the intertidal zone of Guangxi. In order to achieve large-scale and high-precision extraction of intertidal resources in Guangxi, this article was based on GEE (Google Earth Engine) platform, using Landsat series image data of Guangxi coastal zone from 2012 to 2022, and threshold segmentation processing of the images. The various remote sensing features under the influence of tidal dynamic inundation were analyzed, and the intertidal zone range of coastal wetlands in Guangxi was extracted. Achieved the classification of tidal flats and water bodies, mangrove vegetation, and non-mangrove vegetation in the study area, with areas of 5 641.67 hm², 1 625.29 hm², and 2 156.04 hm² respectively. The overall classification accuracy reached 93.3%, with a Kappa coefficient of 0.9.

Aiming at the U-turn scenario of autonomous vehicles in two-way single lanes, a safety decision-making method was proposed by fuzzy reasoning, and a U-turn mathematical model was established based on the spatial distribution relationship of vehicles, seven key control points were determined, the search strategy of particle swarm optimization was improved, and an efficient and comfortable U-turn trajectory planning method was proposed. The safety decision-making method firstly establishes a membership relationship between the relative distance between the vehicle and the vehicle on the target lane and the minimum safety distance during steering when making a U-turn, and selects the time with higher safety to make a U-turn. The trajectory planning method combines the spatial distribution characteristics of vehicles, improves the constraints of particle swarm optimization, and proposes a new search strategy, which can quickly converge to the optimal extreme value and plan the optimal path of U-turn. The results show that the proposed decision-making and trajectory planning methods can complete the U-turn safely and efficiently.

In order to solve the problem of insufficient feature extraction of human dynamic skeleton features in abnormal behavior recognition, an unsupervised abnormal behavior recognition method based on enhanced spatiotemporal graph normalization flow was proposed. Transformer and convolution block attention module were employed to enhance the feature expression capability of the model and the performance of the abnormal behavior recognition algorithm in the global and spatiotemporal domains. Firstly, the Transformer module was incorporated into the affine layer of the normalized flow to augment the efficacy of dynamic skeleton feature information at the global level. Subsequently, the convolution attention was introduced into the convolution module of space and time graphs respectively to effectively enhance the spatial and temporal representation of dynamic skeleton features. Finally, simulation verification was conducted on the ShanghaiTech and UBnormal datasets, and the recognition accuracy attains 86.4% and 70.2% respectively, thereby demonstrating the effectiveness of the method.

The variation law of C₄AF and C₃A corrosion products and the formation rate coefficient of CaCO₃ of cement single ore were quantitatively analyzed by SEM, XRD and TG analysis and test methods. The experimental results showed that both C₄AF and C₃A produced a large number of flocculent phases after CO₂ corrosion, but C₃A produced more lumpy and flocculent phases after corrosion than C₄AF corrosion. The relative crystallinity of C₃AH₆ decreases and the relative crystallinity of aragonite increases in the later stage of corrosion reaction, and the quantitative analysis results show that the content of CaCO₃ in C₄AF is higher than that of C₃A, and the molar formation rate of CaCO₃ in C₄AF is 28.36 mol/d and that of C₃A sample is only 4.23 mol/d after 1 day of corrosion reaction. With the extension of the corrosion reaction time to 28 days, the molar formation rate of corrosion products of C₄AF and C₃A continued to decrease, which was 1.83 mol/d and 1.48 mol/d, respectively. The coefficient of corrosion product formation α rate of C₄AF was 32.62 after fitting, which was much higher than that of C₃A single ore (2.74). The corrosion resistance of C₃A ore in CCUS environment is stronger than that of C₄AF, which not only provides theoretical guidance for the development of high performance cement materials resistant to CO₂ corrosion, but also provides a basis for the application of cement in CCUS environment.