Machine learning models, widely applied in landslide susceptibility assessment due to their powerful feature extraction capabilities, are continuously evolving in their algorithms to address the common issue of low accuracy. The GCNN (group convolutional neural network) model was introduced into landslide susceptibility assessment, and its results were compared with those of various common machine learning models to comprehensively evaluate the adaptability of these models in this field. Taking Hebei Province as the research area, 16 influencing factors were selected from three aspects: triggering factors, pregnant disaster environment, and susceptible bodies. GCNN model and other common machine learning models—CNN (convolutional neural network), Logistic (logistic regression), RF (random forest), and SVM (support vector machine)—were constructed to build corresponding susceptibility assessment models. The research area is divided into four categories of landslide susceptibility zones, and the accuracy of the zoning is comprehensively evaluated. The study indicates that compared with the other four machine learning models, the GCNN model achieves higher scores in various confusion matrix indicators and is more suitable for landslide susceptibility zoning. The resulting zoning of landslide susceptibility is consistent with the actual occurrence of landslide points, indicating a more accurate delineation of landslide-prone areas.

Acoustic wave is one of the important means to realize the fast and accurate transmission of downhole information. The drill string serving as information transmission channel has obvious periodic pipe structure characteristics. In order to study the frequency spectrum quality of drill string channel in actual working conditions, a multilevel evaluation method of acoustic frequency spectrum based on improved radar chart was provided. The influence of axial tension stress on the frequency spectrum characteristics of acoustic wave in pipe structure was studied and analyzed by the method, and the criteria for judging the frequency spectrum characteristics were established. Practice shows that, the existence of tensile stress has a significant impact on the acoustic frequency spectrum and passband characteristics. With the increase of tensile stress, the evaluation index of frequency spectrum characteristic increases first and then decreases, and there exists a peak point with the best frequency spectrum characteristic. This method can comprehensively reflect the influence of different factors on the frequency spectrum characteristics of acoustic wave in drill string channel, and comprehensively evaluate the distortion degree of frequency spectrum characteristics from the multiple perspectives. It provides a basis for optimizing carrier frequency and designing the installation position of repeater when dealing with multi-factors interference in the field application of downhole information acoustic transmission technology.

The sedimentary environment of Cardium formation in western Canada basin is the shallow sea coastal face. The conventional oil and gas reservoir was formed from the conglomerate and sandstone deposited on the coastal muddy seafloor. The unconventional tight oil reservoir was formed from the low-permeable argillaceous sandstone around the conglomerate. Faced with the coexistence of different types of resources, the development of SINOPEC oversea blocks with benefit needs to be realized. Firstly, the member A of Cardium formation was divided into three types according to the core observation and experiment test. Then the development features of different types of reservoirs were compared based on the production dynamic data. Thirdly, the geological knowledge was verified via single well theoretical models. Finally, the development potential of different types of reservoirs in the interest block were evaluated. The development strategies of different types of reservoirs were put forward. The results show that the member A of Cardium formation can be classified into type I conglomerate reservoir, type Ⅱ conglomerate reservoir and type III tight sandstone reservoir according to the lithology differences. From type I to type Ⅲ, the reservoir physical properties gradually weaken. The development way changes from vertical well development to multistage fracturing horizontal well development. The productivity controlling factors gradually complicates. Currently, type I and II reservoir in the interest block have a limited potential, which can be further released through reperforations on some old wells. Type III reservoir has a certain potential, which can be effectively released through deployment of large numbers of horizontal wells.

The enhancement of oil recovery by altering the salinity and ion composition of injected water has become a focal point of numerous studies. However, there is relatively less attention given to techniques combining surfactants with the quality injected water. To investigate the synergistic effects of different cations and surfactants on recovery efficiency, micro-scale displacement experiments were conducted to simulate the displacement process, along with experiments measuring interfacial tension and viscoelasticity modulus at the oil-water interface. Results from the micro-scale displacement experiments show that 10 000 mg/L NaCl solution and 50 000 mg/L CaCl₂ solution exhibite the best oil recovery efficiencies, reaching 64.51% and 59.27% respectively. After adding surfactants, the efficiency improved further with 10 000 mg/L NaCl +0.2% dodecyl dimethyl ammonium betaine solution and 50 000 mg/L CaCl₂+0.2% hexadecyl trimethyl ammonium bromide solution achieving the highest recovery rates at 87.28% and 80.92% respectively. Results from the interfacial tension and viscoelasticity modulus experiments indicated that when anionic and nonionic surfactants were added to NaCl and CaCl₂ solutions, the interfacial tension reached the magnitude of 10^-1 (m·N)/m. However, with the addition of amphoteric and cationic surfactants, the interfacial tension decreased to the magnitude of 10^-2~10^-3 (m·N)/m, accompanied by a significant decrease in viscoelasticity modulus. This study explores the mechanisms of the synergistic effects of different cations and surfactants on the displacement process, considering factors such as interfacial tension, viscoelasticity modulus, and wettability, and microscale oil displacement behaviors thus providing a comprehensive analysis of the relationship between multiple factors and recovery efficiency.

Oil booms play a vital role in dealing with oil spills on water. Aiming at the single problem of existing oil booms in fast-flowing rivers, a new type of double-layer mesh fence was designed for oil spill recovery in fast-flowing rivers based on the parameters of traditional oil booms. Based on the mainstream CFD (computational fluid dynamics) software FLUENT, a two-dimensional numerical flume model was established to simulate the transient distribution of oil and water under the action of the new oil containment boom with VOF (volume of fluid) as the computational model, and the volume of oil intercepted was used as the monitoring data to explore the direction of optimizing the oil containment performance of the oil containment boom. Monitoring data was used to explore the optimization direction of oil containment performance of the oil containment boom. The results show that the optimised oil containment boom has a grid radius of 30 mm and a porosity of 0.3. Compared with the traditional boom, the new oil containment capacity of the new oil containment boom is better than that of the traditional boom, which provides an effective reference for the design of oil containment boom for fast-flowing rivers.

In order to detect the abnormal working conditions such as overpressure and leakage, that may occur in pipelines and installations in the process of natural gas regional production, the current industrial control and alarm systems cannot accurately reflect the real state of the equipment, and the single-parameter early warning has a higher rate of error judgement, which is insufficient in practicality. A collaborative prediction and warning method for process parameters related to upstream and downstream stations in a natural gas production area was tested. Aiming at the characteristics of natural gas region with many stations, complex production process and diverse monitoring data, firstly, the parameters of each station were downgraded to extract the key process parameters of each station. Then, the key parameters are evaluated and grouped by correlation, and a multivariate nonlinear lasso regression prediction model was established with the highly correlated parameters in the same group as the independent variables. At the same time, a long and short-term memory prediction model was established for the key parameters, and a comparison analysis of the prediction results was performed to determine the dynamic prediction and early warning of natural gas production. Comparative analysis of the prediction results of the two models was used to determine the dynamic thresholds for coordinated early warning of regional production. The results show that the method can not only effectively reduce the misjudgment of single-value anomalies, but also locate the anomalous stations and points, which is of high practical value.

To address the issues of low accuracy in rolling bearing life prediction and the difficulty of constructing health indicators, a bearing remaining life prediction model based on ASFF (adaptively spatial feature fusion) and AAKR (auto associative kernel regression) combined with CNN (convolutional neural networks) and BILSTM (bi-directional long-short term memory networks) was proposed. Firstly, the multidimensional features were extracted in the time domain, frequency domain, and time-frequency domain, and the sensitive features were screened using monotonicity and trend. Secondly, the sensitive features were feature fused using ASFF-AAKR to construct the health indicators. Finally, the health indicators were inputted into CNN and BILSTM to realize the life prediction of rolling bearings. The results show that the constructed life prediction model is better than other models, and the method has lower error and higher life prediction accuracy.

It will raise their feedwater temperature and then improve their operating economy to add No.0 HPH (high-pressure heater) in thermal power units. A steam-water distribution model for a thermal system coupled with No.0 HPH was established based on the mass and energy conservation laws. And a variable-condition calculation method for its heat economics was also proposed. Furthermore, a derivative characterization approach was developed to represent the heat economics impact of No.0 HPH extracted steam flowrate, which realize the quantitative evaluation before and after coupling with No.0 HPH. Taking a 600 MW unit for example to carry out calculations and analysis, it indicates that the index calculation error of the method proposed in this paper is less than 0.15%, which has high precision and can be used for thermal economic evaluation of large thermal power units coupled with No. 0 HPH. Furthermore, after coupling No.0 HPH, the feedwater temperature can be lifted by 19.1~32.3 ℃, the cycle heat efficiency raised by 0.18%~0.2%, and the heat consumption rate decreased by 29.3~34.6 kJ/(kW·h). Moreover, the sacrificial internal work will be even smaller, and the heat consumption decrease be even larger if the turbine load was smaller.

An analysis was conducted on the circulating flow process of coolant in the cooling water jacket of motorcycle single cylinder engines, twin cylinder engines, and four cylinder engines. The analysis of coolant flow velocity and water jacket wall heat transfer coefficient were conducted. Based on the analysis of the circulating flow path of coolant, the optimization of the cooling water jacket structure was studied. The results show that the coolant flow rate on the exhaust side and nose bridge area of a single cylinder engine is relatively low, and there is a zero flow rate area in the nose bridge area. The distribution of coolant flow rate in the two cylinders of a twin cylinder engine is uneven, and the coolant flow rate in the middle area of the connection between the two cylinders is relatively low. There is also an issue of uneven coolant flow rate in each cylinder of a four cylinder engine. By analyzing the flow path of coolant circulation, the flow direction and function of the coolant on the water holes on each cylinder gasket are clarified. Based on the design criteria that require key cooling in high-temperature areas, the layout of the water holes on the cylinder gasket and the local flow area of the water jacket are optimized for three types of engine cooling water jackets. After optimization, the coolant flow rate in the high-temperature areas such as the exhaust side and nose bridge area of the three types of engine cooling water jackets reached the requirement of not less than 1.5 m/s, and the difference in coolant flow rate between each cylinder is reduced. Through engine thermal balance verification, the optimization of the cooling water jacket structure for three types of engines can effectively reduce the temperature of the cylinder head spark plug gasket and reduce the temperature difference between the spark plug gaskets of each cylinder, verifying the effectiveness of the water jacket structure optimization design.

Radiation dose monitoring using thermoluminescent detectors is currently one of the main methods of personal or environmental dose monitoring in China. In order to solve the problem of uniformity screening before the use of thermoluminescent detector, and the complexity of the measurement process. Test dose and thermoluminescent peak counts normalization were used to optimize the measurement process of thermoluminescent detectors. With the simple irradiation device, the same batch of thermoluminescent dosemeters for radiation environment monitoring were measured using the optimized and general measurement processes. The relative error of the dose values of the two was within ±5%, which satisfied the accuracy requirements of thermoluminescent dosemeters in the process of monitoring the dose of ionizing radiation to the individual or the environment. The results show that the optimized thermoluminescent dosimetry process reduces detector uniformity performance requirements and improves the applicability of the process. It provides a high-precision, high-efficiency and low-cost measurement method for personal or environmental dose monitoring in China.