Buried pipeline is an important part of oil and gas transportation. The subsidence of gob area will cause the corresponding subsidence of the pipeline passing through the gob area, resulting in pipeline deformation, fracture and other accidents. Taking Puxian-Hejin pipeline crossing coal mining subsidence area as the research background, 3D printing technology was used to make up for the mismatch in mechanical similarity between pipeline simulation materials and geotechnical simulation materials, and the coupling simulation experiment between pipeline and rock and soil was constructed. The mining response of buried pipeline caused by coal mining was analyzed, and the correlation between pipeline movement deformation and stratum movement deformation was established. The research shows that the buried pipeline and the underlying rock strata do not synchronously settlement, resulting in delamination between the overlying rock strata and the underlying rock strata. The pipeline bends and deforms under the overlying rock load and its own weight. When the delamination span is large enough, the bending tensile stress on the bottom of the pipeline exceeds the allowable stress, resulting in tensile failure. The subsidence value of the buried pipeline is about 1.21 times of the formation subsidence value, and only 18% of the horizontal deformation of the formation is transmitted to the pipeline. The research results have guiding significance for the safe laying and daily maintenance of pipelines in subsidence area.

Aiming at the problems of nonlinearity, large delay, uncertain model parameters and weak anti-interference ability in the temperature control system of variable air volume air conditioning supply air, a closed-loop control system of supply air temperature based on active disturbance rejection control (ADRC) was designed. In order to overcome the difficulty in parameter adjustment of active disturbance rejection controller, an improved grey wolf optimization (IGWO) algorithm was proposed to optimize controller parameters. By introducing chaotic mapping, nonlinear convergence factors, dynamic weights and dimensional learning strategies into grey wolf optimization (GWO), the population diversity was increased and the balance between search and exploitation was taken into account. The advantages and feasibility of the proposed algorithm were verified by MATLAB simulation. The experiment further proves that compared with the traditional proportional integral derivative (PID) controller and the traditional gray wolf algorithm, the IGWO algorithm can shorten the supply air temperature overshoot by 45.3% and 8.9%. The adjustment time is reduced by 34.8% and 11.2%, the steady-state error is smaller, and the system is more energy efficient.

Aiming to address the issue of accurately measuring the slurry pH value during the operation of limestone-gypsum wet flue gas desulfurization (WFGD) system, which hinders the efficient operation of WFGD, a prediction model for FGD system pH based on bi-directional gated recirculation unit(BiGRU) has been developed. Firstly, the raw data were cleaned and normalized. Secondly, based on the maximum information coefficient analysis, 13 characteristic values were obtained as input variables and pH as output variables, and a slurry pH model was established. Finally, the model was run and the results were evaluated. Compared to LSTM and GRU, the results indicate that the mean absolute error of this mathematical model decreases by 11.95% and 24.92%, while the root mean square error decreases by 10.64% and 19.49%. Additionally, the coefficient of determination improves by 1.79% and 3.08% respectively. This demonstrates that the BiGRU-based pH predictive model exhibits high accuracy and stability, making it valuable for engineering applications and providing an important reference for predicting pH models in existing desulfurization tower systems.

In the intersection scenario, the running state of social vehicles, the control state of traffic lights and the accurate identification of track components have become the technical bottlenecks restricting the promotion and application of track inspection robots. Aiming at the requirements of track health inspection, firstly, the vision inspection system of the track inspection robot and the technical scheme of the navigation system was presented based on “Beidou +5G”. Secondly, the vision detection system model was built based on YOLOv8 algorithm, and the web crawler technology was innovatively used to capture sample data about traffic lights and car taillights from open source video resources to train the vision detection model. Then, transfer learning method and early stop method were used to optimize the detection accuracy of the trained model. The research results show that after adopting YOLOv8 algorithm and optimizing the model with transfer learning method and early stop method, the inspection robot can effectively detect the track components, vehicles and traffic lights at the switch junction, and effectively improve the inspection efficiency and accuracy.

To solve the problem that the wire rope swing angle is too large during the load lifting and lowering process of the bridge crane, a fuzzy layered sliding mode control method was proposed with the single pendulum model of the bridge crane as the research object. The method firstly establishes the bridge crane single pendulum model system, designs the two-layer sliding mode surface joint control based on traditional sliding mode control, combines the layered sliding mode surface with fuzzy control to create the controller, proves the Lyapunov stability of the closed-loop system of the bridge crane under the method through theory and carries out simulation experiments. The simulation results show that compared with the LQR controller and the multi-sliding mode controller, the trolley arrives at the desired position in 68% less time, and the maximum swing angle of the load is reduced by 15%, which achieves a good anti-swing effect.

In the practice of energy renovation of existing buildings, the uncertainty of renovation parameters has a significant impact on the renovation results. To support energy renovation decision-making, a Monte Carlo method combined with Latin hypercube sampling was proposed to evaluate different renovation schemes, and a tree-based Gaussian method was used to screen key variables that affect the renovation process. The results show that uncertainty analysis can quantitatively evaluate renovation schemes at the preliminary design stage. The energy-saving rates of two typical renovation scenarios fluctuate between 32.7%~55.2% and 55.5%~108.4%, respectively, with higher uncertainty in schemes with better energy-saving effects. The cumulative probability distribution was used to assess the probability of renovation success, with the probabilities of meeting renovation targets being 58% and 96.4%, respectively. The integration of renewable energy technologies ensures the renovation results. Sensitivity analysis results show that infiltration rate and equipment power density are the most important factors in office building energy consumption, accounting for 80% of the output variance, which provides a theoretical basis and methodological reference for the selection of more building energy renovation schemes in the future.

When a tunnel crosses a water-rich fault fracture zone, it is very easy to produce a water surge accident under a series of construction disturbances. In order to study the effects of fault zone width, dip angle and water pressure on tunnel water inflow, Yingshan tunnel was used as the engineering background, field tests were carried out, and an orthogonal test scheme was designed to carry out numerical simulation of coupled flow-solidity in the fault zone under multifactorial conditions, so as to analyze the sensitivity of the fault zone width, dip angle and water pressure on the water inflow of the tunnel. The results show that the tunnel water inflow increases with the increase of fault zone thickness, dip angle and water pressure, and the factors affecting the tunnel water inflow are water pressure, dip angle and width of the fault zone. The numerical simulation results are in good agreement with the field monitoring results. The results can provide theoretical references for the prediction of water influx in water-rich tunnels and the prevention and control technology.

In order to research the effect of rotation on the flow and heat transfer characteristics of heat convection system in a closed cavity, a series of numerical simulations were carried out on the air flow and heat transfer characteristics in a closed cavity. The distribution characteristics of velocity field and temperature field by different Rayleigh numbers and rotating Rayleigh numbers by horizontal and vertical temperature gradients were obtained, as well as the local and average Nusselt numbers on high temperature walls. The effect of rotation on the thermal convection system by two kinds of thermal boundary conditions was discussed. The results show that for the heat convection by horizontal temperature gradient, the gradual enhancement of rotation makes the flow characteristics change from single-cell to multi-cell, and enhances the heat transfer performance of heat convection. For heat convection by vertical temperature gradient, the enhancement of rotation makes the flow tend to the steady-state flow characteristics, that is, the flow stability is enhanced, and at a large Rayleigh number, the enhancement of rotational action will first inhibit and then strengthen the heat transfer performance. Given the same conditions, the convective heat transfer performance by horizontal temperature gradient is better than that by vertical temperature gradient, and the stronger the rotation effect is, the more obvious the feature is.

Existing voice-driven facial generation methods still face challenges in feature extraction and generation quality, and have yet to fully explore the deep correlation between audio and facial features. To address above mentioned issues, a research approach that combines Mel frequency cepstral coefficients (MFCC) was proposedfor audio feature extraction with the image generation capabilities of the second generation of style generative adversarial networks (StyleGAN2) was proposed. In terms of audio processing, MFCC was employed as the feature extraction method. To more effectively extract and transmit features from the audio, a ResNet18-based residual module was designed and integrated with the squeeze-and-excitation (SE) attention mechanism. Additionally, the activation function in the original residual blocks was optimized and improved by using the Mish activation function, aiming to mitigate the gradient vanishing problem in deep networks, maintain the integrity of feature information, and enhance the accuracy and generalization ability of the model. The StyleGAN2 model was then utilized as the facial image generation model. Experimental results demonstrate that the integration of the designed audio processing network with the StyleGAN2 facial generation model exhibits outstanding performance in the task of voice-driven facial generation. Through comprehensive evaluation using metrics such as Fréchet inception distance (FID) and path length, the proposed method shows a significant improvement in generation quality compared to existing methods, thus fully proving its effectiveness and superiority.

The construction of the pile-beam-arch-method(PBA method) exhibits a cluster-tunnel effect, which readily induces surface subsidence. To achieve safe construction and minimize surface settlement, the MatDEM discrete element software was employed to simulate the construction process of the PBA method. The potential deformation mechanism and metastable microstructure of soil were considered in the training of formation micromechanics parameters, and the variation rule of surrounding rock pressure under multi-guide tunnel construction was summarized. The research findings indicate that when adopting a construction sequence of “top-to-bottom and sides-to-center,” surface settlement is relatively small. When using the “center-to-sides” approach, the initially excavated central pilot tunnel leads to the formation of slip planes at 1.5 times the tunnel width. Conversely, with the “sides-to-center” method, the initially excavated side tunnels provide vertical support to the inner soil, reducing the surface settlement caused by the subsequent excavation of the central tunnel. During the construction of the upper pilot tunnels, the surrounding rock pressure at the vault and arch waist exhibits an increasing trend. The construction of the lower pilot tunnels results in stress concentration at the vault and inner arch waist of the upper tunnels. Approximately 72.65% of surface settlement occurs during the construction of the lower pilot tunnels, and the adoption of staggered construction can significantly mitigate soil disturbance.