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.

The total organic carbon content in shale reservoirs is a crucial parameter for assessing hydrocarbon generation potential and shale gas enrichment. Accurate prediction of TOC(total organic carbon) is essential for oil and gas exploration and development. Conventional linear regression methods are limited in their predictive accuracy due to the complex nonlinear relationships among regional and well logging data. To address this issue, a prediction model based on Adaboost-WOA-BP was proposed for predicting TOC content. This model integrates WOA(whale optimization algorithm) optimized Backpropagation neural networks as weak learners within the Adaboost framework to construct a strong learner. Use of optimal natural gamma, density, acoustic time difference, and other sensitive logging parameters associated with TOC content calculation as inputs for the prediction model. Compared to conventional linear regression, BP neural networks and WOA-BP neural networks, the Adaboost-WOA-BP model demonstrates higher predictive accuracy, achieving a 95% match between predicted and measured TOC values.

Aiming at the problems that the large-scale pre-training language model faces when dealing with news headlines, such as huge parameters, inefficient use of contextual semantic features and circular convolution neural network’s neglect of the importance of initial input elements, a news headline classification method that combines ERNIE(enhanced representation through knowledge integration) of mixture-of-expert model and recurrent convolution neural network with attention mechanism were proposed. Firstly, the text was encoded with the help of MoE’s improved ERNIE technology, and then the text was classified with attention RCNN (recurrent convolutional neural networks)on the basis of preserving the word order and characteristics of the text. In order to improve the classification ability, RCNN was improved by calculating the input fusion context weight. In the process of calculating the weights of experts in MoE, Gumbel-Softmax was selected as a new gating function to improve the traditional Softmax function, so as to better control the smoothness. According to the experimental results, it is found that compared with the traditional classification methods, the classification method proposed in this study shows significant advantages and greatly reduces the number of parameters. On this basis, the F₁ value is increased by 0.51% compared with the traditional model. After the ablation experiment, the feasibility of this classification method in the classification task has been confirmed.

In order to study the effect of temperature on the shear strength of fully weathered mudstone with different saturations,fully weathered mudstone specimens from a typical seasonal frozen region were used as the object of study.The GDS dynamic triaxial test system and the GDS unsaturated test system were used to conduct indoor triaxial tests on specimens with different saturations to investigate the trends of the shear strength parameters of fully weathered mudstone in the seasonal frozen region under different temperatures and surrounding pressures, and to compare and analyse the shear strength parameters of the two different saturations of the fully weathered mudstone were compared and analysed. The results show that the fully weathered mudstone is strongly influenced by saturation and temperature.The cohesion of both soil samples increases with decreasing temperature, and the internal friction angle increases and then decreases. The cohesion of the unsaturated mudstone specimens is consistently greater than that of the saturated mudstone specimens when the temperature and test system conditions are consistent. Saturation has a low effect on the internal friction angle of the specimens, which peaks at -5 ℃ and 0 ℃for the two soil samples respectively.

In order to improve the trajectory tracking accuracy and stability of the aircraft in the traction process, taking the four-wheel steering aircraft traction system as the research object, the kinematics model of the aircraft traction system is established, and the four-wheel steering trajectory tracking control method of the tractor based on the model predictive control was proposed. Taking the double lane changing condition as the reference trajectory, the motion control simulation model of the aircraft traction system was built in MATLAB/Simulink, and the four-wheel steering trajectory tracking controller was established by combining the speed of the tractor and the angular distribution relationship of the four wheels. The controller was compared and analyzed with the traditional PID control to derive the superiority of the controller, and the tractor four-wheel steering and front-wheel steering trajectory tracking controllers were simulated and compared and analyzed at the speeds of 1.5 m/s, 3 m/s and 4 m/s, respectively. The designed controller was simulated and verified by changing the initial positional attitude of the aircraft traction system at a speed of 1.5 m/s. The results show that at three different speeds, the airplane lateral error, the heading angle error, and the tractor heading angle error under the four-wheel steering trajectory tracking control of the tractor are smaller than those under the front-wheel steering trajectory tracking control. In the case of initial deviation, the four-wheel steering trajectory tracking controller can enable the aircraft to complete the correction of the initial deviation in time, reduce the trajectory tracking error, and at the same time improve the stability of the aircraft's traction system in the driving process.

With the continuous integration of urban Bridges into a variety of traffic forms, various traffic vehicles and pedestrians interfere with each other, affecting the safety and comfort of pedestrians. To research the pedestrian response on single-level rail-cum-road bridges, a pedestrian-road vehicle-train-bridge coupling vibration model was established. The acceleration difference between the bridge panel and pedestrian SMD model was researched, and the influence of trains and road vehicle passing the bridge in different ways on pedestrians was calculated. The results show that, compared with bridge panel, the amplitude of acceleration fluctuation of pedestrian SMD model is smaller, but the walking pedestrian model may experience abrupt and significant acceleration peaks. Each moving subsystem in the coupling model has a speed-sensitive interval, in which the pedestrian acceleration increases significantly. The further vehicles are away from the bridge center, the greater the acceleration of pedestrians become. When train and road vehicle pass the bridge simultaneously, the peak acceleration of pedestrian caused by them will be superimposed, and the peak acceleration caused by road vehicles increases significantly due to the train.

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.

To address the bottleneck issues in vehicle access efficiency for horizontal shifting mechanical parking garages, an access vehicle scheduling optimization model based on the PSO-OBL algorithm was proposed. The model aims to shorten vehicle access operation time and reduce user average waiting time by precisely controlling vehicle access strategies and time management. To enhance the optimization performance and convergence rate of the traditional particle swarm optimization algorithm, an innovative approach incorporating inter-particle collaboration and information exchange mechanisms was embedded into the algorithm framework, along with the integration of an opposition-based learning mechanism for efficient problem-solving. Experimental data indicates that, compared to the traditional particle swarm optimization algorithm, the PSO-OBL algorithm achieves significant improvements in customer average waiting time, average service time, average queue length, and average energy consumption. The findings of this study are expected to provide theoretical support and practical reference for optimizing access efficiency in horizontal shifting mechanical parking garages.

In order to study the effect of basalt fiber on the durability of recycled concrete under the erosion of salt solution, the durability of recycled concrete specimens with different basalt fiber contents after salt-dry-wet cycle coupling erosion was studied. A comprehensive durability index D value was established to evaluate the durability of recycled concrete based on the entropy weight method. The effects of dry-wet cycle period of salt solution and basalt fiber content on D value were analyzed. A GM (1,1) mean model was constructed to reveal the time-varying law of the D-value of recycled concrete, and the predicted life of recycled concrete under different conditions was obtained. The results show that the D value can reflect the influence of different salt solution dry-wet cycle cycles and basalt fiber content on the durability of recycled concrete. As the salt solution's dry-wet cycle increased, the D value of the specimen gradually decreased, indicating a severe change. However, adding basalt fiber to the recycled concrete can effectively enhance its D value and durability. When the content of basalt fiber is 1.0%, the durability of recycled concrete is the best. The GM(1,1) model can more accurately predict the time-varying pattern of D values of recycled concrete under coupled salt-dry-wet cycle erosion when the amount of data is small.

To address the voltage fluctuations caused by the integration of renewable energy into the distribution network, a voltage coordinated control method based on MPC (model predictive control) was proposed to ensure safe operation. Aiming at the uncertainty of wind and photovoltaic output, the AP-K-Medoids clustering algorithm was proposed to generate and reduce output scenarios, and a model was established with the optimization objective of minimizing system network loss. Adopting multi time scale voltage control through the integration of on load voltage regulating transformers, capacitor banks, static reactive power compensators, wind solar reactive power output, and energy storage charging and discharging coordination. Long term scale optimization control solves the output of each device in the system through multi-step rolling optimization, with wind solar output and load demand prediction as the premise. On the basis of short-term and long-term rolling optimization, the increment of output is solved. The optimization control model is a non convex and nonlinear model, which utilizes a second-order cone programming model to solve nonlinear problems. Using an improved IEEE33 node distribution network system for case analysis, the research results demonstrate the feasibility of the proposed voltage optimization control strategy.