To accurately and comprehensively explore the entire process of physical fatigue development in rescue team members during weighted walking, a multidimensional fatigue assessment method based on eye movement characteristics, electromyographic signals, and subjective evaluation is proposed. Eight volunteers were recruited for the weight-bearing walking fatigue induction experiment. The glasses eye tracking was used to extract the eye movement data about ST (saccade time), average SS (saccade speed) and maximum SA (saccade amplitude). The correlation between the characteristics of eye movement and the degree of fatigue estimated by subjective evaluation was -0.857±0.059, -0.938±0.092, not correlated, respectively. The correlation with iEMG to judge fatigue degree was -0.782±0.090, -0.942±0.030, -0.928±0.026, respectively. Multiple linear regression analysis was performed on subjective score, iEMG value and eye movement parameters. The regression model yielded a coefficient of determination R²=0.989, with the following standardized coefficients: iEMG signals=0.27, ST=-0.16, SS=-0.513, and SA=-0.124. This study makes new explorations and attempts in the monitoring and evaluation methods of fatigue during weighted walking.

To investigate the mechanism and influencing factors of soil heating with coupled in situ thermal technology, a two-dimensional experimental setup was used to simulate the heat treatment process, and the effects of coupled steam injection on thermal conductive heating as well as the effects of steam injection rate and heating mode on the application of the thermal conductive heating and steam injection technology were investigated. The results show that coupling steam injection on the basis of thermal conductive heating treatment can accelerate heat transfer, reduce heat loss, shorten the heating time by 35.67%, and reduce energy consumption by 24.53%. The main mechanism of steam injection enhanced heating is as follows. The additional heat injection increases the temperature difference, which in turn enhances convective heat transfer in the liquid phase driven by buoyancy. The upward migration of steam under buoyancy or pressure to enhance convective heat transfer in the gas phase. In thermal conductive heating and steam injection treatment, changing the steam injection rate or heating mode had a small effect on the treatment energy consumption, increasing the steam flow rate from 0.18 to 0.54 kg/h can shorten the heating time by 22.05%, but increase the water consumption by 132.43%. Compared with the thermal conductive heating and steam injection heated at the same time, thermal conductive heating heated for 30 min and then coupled with steam injection can reduce the water consumption by 28.57%, but will extend the heating time by 3.84%. In engineering applications, suitable restoration solutions should be selected based on duration, cost, etc.

A method for diagnosing AC series arc faults based on the Inception module and BiLSTM (bidirectional long short-term memory) was proposed to address the challenge of identifying small current changes caused by arc faults in aviation cables. First, features of the raw current data were extracted by calculating the discrete sum of squares of the autocorrelation coefficient, Shannon entropy, and wavelet energy entropy. These features are then combined to form a new feature matrix, enhancing the original data's feature representation. Subsequently, the Inception-BiLSTM network learns from the feature matrix and ultimately completes the arc fault diagnosis. To validate the diagnostic performance of the model in practical environments, a series of experiments were conducted, including vibration tests, stress tests, and wet cable tests, based on an aviation cable arc fault simulation platform, with the experimental data being integrated as detection samples. The experimental results show that the proposed method achieves a high accuracy rate of 99.69% in identifying arc faults.

As an important firefighting equipment, fire cylinders need to undergo regular safety evaluations during their service period. In order to efficiently and accurately evaluate the safety status of fire steel cylinders, a safety evaluation model suitable for fire steel cylinders was established based on the analytic hierarchy process and fuzzy comprehensive evaluation method. The feasibility of the model was verified through case evaluation. Secondly, the BP neural network based on MPGA (multi population genetic algorithm) is used to optimize the safety evaluation model of fire steel cylinders. This method improves the process of updating weights and thresholds of the BP neural network through multi population genetic algorithm, improving the accuracy of BP neural network prediction results and the efficiency of fire steel cylinder safety evaluation. Finally, the construction of safety evaluation models for fire steel cylinders based on BP, GA-BP, and MPGA-BP was completed using Python. By comparing and analyzing the prediction results of three models, it was found that the MPGA-BP neural network has the smallest prediction error, proving that the proposed MPGA-BP safety evaluation model has high accuracy and can more efficiently and accurately evaluate the safety of fire steel cylinders.

Aiming at the problem that ViBe (visual background extractor) algorithm is prone to ghosting during moving target detection, an improved algorithm, ViBe-BR (ViBe with background restoration) was proposed by adding a background restoration stage to the original algorithm. First, the foreground region within the background image was pre-extracted by combining three-frame differencing. Then, the interior of the region was filled using the background pixels around the foreground region to obtain the restored image; Finally, the restored image was corrected and ViBe detection was performed based on the reduced background to achieve the effect of suppressing ghosting. The experimental results show that the ViBe-BR algorithm achieves good detection results in four different scenes, and compared with the ViBe algorithm, the average precision, recall, and F₁ value of foreground detection have been improved by 0.222, 0.03, and 0.123 in that order, which effectively eliminates the influence of ghosting, and it can be applied to practical geo-localization tasks in order to obtain the geographic location information of the moving targets.

The study focused on wrap-around reinforced soil retaining walls and proposed a calculation method for panel displacement. The horizontal displacement was divided into two components for calculation: the horizontal displacement caused by the strain of reinforcement and the overall horizontal displacement generated by the horizontal earth pressure acting on the back of the reinforced zone. When calculating the horizontal displacement caused by the reinforcement strain, the reinforced zone was divided into subzones through the potential failure surface of reinforced soil retaining wall and the natural repose angle of soil. The horizontal distribution of the reinforcement load was assumed, yielding a simplified calculation model for the horizontal displacement caused by reinforcement strain. For the calculation of the overall horizontal displacement of the reinforced zone, the zone was treated as a ‘cantilever beam’, taking into account the variation in elastic modulus of the reinforced zone with height. The theoretical results obtained through the proposed method were compared with experimental and numerical simulation results. The distribution trend of the displacements was basically consistent, indicating that the proposed method can effectively calculate the panel displacement of wrap-faced reinforced soil retaining walls.

In response to problems of rapid excavation of deep shafts, such as lining cracking and high support costs, based on the engineering background of -906~-1 158 m section of an overseas copper and gold mine, the support parameters of shaft were studied by theoretical calculations, numerical simulations and field tests. In order to restrict deformation of the shaft and reduce the cost of support reasonably and effectively, a shaft model was established based on the engineering practice, the stability of surrounding rock with the different parameters was analyzed by FLAC^3D numerical software combined with fluid-structure interaction. The results demonstrate that for the class Ⅲ surrounding rock, “anchor net spraying+steel fiber concrete” support is adopted, and its parameters are as follows: bolt diameter 22 mm, length 2.3 m, shotcrete thickness 50 mm, row spacing 1 m×1 m, steel fiber concrete thickness 550 mm. For the locally existing class Ⅳ~Ⅴ surrounding rock, “anchor net spray+foam board+steel fiber concrete” support was proposed, and the thickness of buffer layer foam board is 100 mm, and the thickness of steel fiber concrete is 600 mm. Field test results show that the average convergence rate of surrounding rock is 0.18~0.31 mm/d after 412 h excavation, which meets the requirements of air inlet shaft construction, and the construction efficiency is improved by about 23.5% compared with the domestic deep shaft. This work can provide a guidance for the support design of shaft in soft-fractured strata with water-rich.

CO₂ flooding technology, recognized as a mature tertiary recovery method, is widely applied in complex small fault-block oilfields with strong heterogeneity. However, severe gas channeling is commonly observed during CO₂ flooding. As a result, the improvement in oil displacement efficiency remains low, typically below 10%. To address this, effective methods were explored to enhance oil displacement efficiency. Foam profile control and plugging were utilized as key techniques to achieve this enhancement.In the experiment, the JS oilfield was used as an example. The foam performance of the gas-soluble foaming plugging agent G-CF4 and the water-soluble foaming plugging agent W-CF1 was compared. The plugging agent with better foam performance was selected. Its plugging ability and oil displacement efficiency were tested.The results show that under target reservoir conditions, the optimal foaming plugging agent is 0.25% G-CF4.Moreover, the greater the permeability difference within the core combination, the stronger the plugging effect of G-CF4 in high-permeability cores.For a core combination with a permeability difference of 88 mD, the resistance coefficient of high-permeability cores is 2.5 times higher than that of a core combination with a permeability difference of 50 mD. In the core combination with 88 mD permeability difference, G-CF4 can maintain the resistance coefficient of high permeability cores above 9.2.The injection of 0.25% G-CF4 solution for 0.3 PV, followed by CO₂ flooding, improves oil displacement efficiency by 15% compared to CO₂ flooding alone.This study provides laboratory evidence supporting the optimization of foaming plugging technology in the JS oilfield.

Filling phase change capsules in a container to form a packed bed heat storage unit is a typical applica-tion of phase change capsules. Phase change capsules are usually stacked in a specific layout in the packed bed flow channel. Studying the heat storage and release characteristics of a single phase change capsule in a packed bed flow channel can help optimize the design of a medium-temperature phase change heat storage system. Therefore, a two-dimensional packed bed numerical model of phase change cap-sules was established. The heat transfer and flow characteristics of the external heat transfer fluid flowing through the phase change capsules in the direction of gravity, counter gravity and vertical gravity were compared and studied. The effects of flow rate, temperature and capsule diameter on the melting process of phase change capsules were studied. The results show that the heat transfer rate of the windward side of the phase change capsule in the packed bed channel is faster. Due to the thermal resistance of the cavity air and the natural convection, the complete solidification time is the shortest when the heat transfer fluid flows countercurrently. Compared with the downstream flow, the complete solidification time of the up-stream flow is shortened by 8.9%. When the diameter of the phase change capsule is 12 mm, the melting speed of the phase change capsule with PTFE as the wall material in the center is 1.45% slower than that of the 304 stainless steel phase change capsule, and the average heat storage rate is 1.5% lower. The melting rate of the phase change capsule with modified PTFE as the wall material cavity in the center is 6.9% faster than that of the 304 stainless steel phase change capsule, and the average heat storage rate is 5.8% higher. Increasing the HTF inlet velocity and temperature can increase the average heat storage rate of the phase change capsule and shorten the melting time of the phase change capsule. The heat storage and release characteristics of the capsule have important guiding significance for the design optimization and practical application of the capsule monomer and the medium temperature phase change heat storage system.

The data-driven approach of machine learning enables the intelligent construction of TBM(tunnel boring machines), which is crucial for optimizing the tunneling process, improving the safety of tunneling and reducing labor costs. In order to solve the problems of excessive noise, redundant parameters and difficult effective feature extraction in TBM operation data, a data-driven machine learning method was used to mine the complex machine-soil interaction contained in the data and realize the classification and prediction of TBM surrounding rock mass. First, for the large amount of operational data generated during TBM tunneling, the KDE (kernel density estimation) method was used to extract features from typical tunneling parameter curves, and the maximum probability of the key operating parameters during stable tunneling stage of TBM is obtained. Then, based on the actual TBM operation data, an integrated learning algorithm for surrounding rock classification stacking was proposed. The algorithm is further optimized through k-fold cross-validation, and the complex relationships in the data are mined by using the two-layer learning framework of base classifier and meta-classifier. Finally, a data set of 5 868 TBM segments was used to verify the effectiveness of the proposed algorithm. The results show that the average F₁ of the four-classification problem is 0.705, and the average F₁ of the two-classification problem is 0.797, which are better than the four selected base classifiers.