In the event of a flood, the choice of evacuation routes is vital for personnel security. This is particularly true when road factors play an important role in evacuation time. In this study, the traditional Dijkstra algorithm for route planning is improved, and the evacuation model is improved from 2D to 3D. At the same time, the Lasso regression method is adopted to take the road factors into account in the pedestrian speed, and the location of shelter is selected and optimized through the calculation results, and then based on the improved 3D Dijkstra’s algorithm, an optimal evacuation route method in different flood disasters risk levels is proposed, which can make pedestrians reach the shelters within the shortest time. After taking into account road factors (road width, slope, non-motorized lane width, and pedestrian density), through the calculation of the pedestrian speed formula, the estimated evacuation time of pedestrians is obtained. By combining available shelters with evacuation routes, the optimized algorithm improves the evacuation efficiency facing different risk levels of flood disasters. The results show that when residents are confronted with flood disasters of once-in-20-year, once-in-50-year, and once-in-100-year, the proposed optimization algorithm can save 7.59%, 11.78%, and 17.78% of the evacuation time. Finally, according to the verification of the actual effect in Meishan Town, the proposed method of optimal evacuation route planning can effectively reduce the evacuation time of pedestrians, evaluate, and optimize the location of existing shelter, and provide suggestions for urban road reconstruction.

In order to achieve the prediction and early warning of city gas pipe network leakage accidents, as well as to provide rapid and precise support for emergency response to such accidents, this study focuses on a Gaussian diffusion model applied to a large urban gas pipeline network. Specifically, it investigates the gas gate wells, which are key nodes in the pipeline network, to develop a leakage model. The objective is to analyze the variation in internal gas concentration in the gate wells and determine the range of danger posed by external gas diffusion from the gate wells. In addition, Fluent simulation is utilized to compare the accuracy of the model’s calculations. The findings of this study indicate that the gas concentration inside the gate well, as predicted by the model fitting results and Fluent simulation, exhibit a high level of agreement, with coefficient of determination (R²) values exceeding 0.99. Moreover, when predicting the hazardous distance of gas leakage outside the gate well, the model’s results show an average relative error of 0.15 compared to the Fluent simulation results. This demonstrates that the model is highly accurate and meets the practical application requirements.

In this paper, an intelligent multiple Quality of Service (QoS) constrained traffic path allocation scheme with corresponding algorithm is proposed. The proposed method modifies deep Q-learning network (DQN) by graph neural network (GNN) and prioritized experience replay to fit the heterogeneous network, which is applied for production management and edge intelligent applications of smart factory. Moreover, through designing the reward function, the learning efficiency of the agent is improved under the sparse reward condition, and the multi-object optimization is realized. The simulation results show that the proposed method has high learning efficiency, and strong generalization ability adapting the changing of topological structure of network caused by network error, which is more suitable than the compared methods. In addition, it is also verified that combining the field knowledge and deep reinforcement learning (DRL) can improve the performance of the agent. The proposed method can achieve good performance in the network slicing scenario as well.

Erosion-corrosion is a predominant failure mechanism in the petrochemical, energy, and offshore engineering sectors, causing substantial economic losses and posing significant threats to equipment safety and personnel well-being. To address this critical issue, the present study employs a systematic approach to examine the current status and estimate the future trends in erosion-corrosion research. By utilizing bibliometric techniques, the study constructs a comprehensive knowledge map to analyze the chronological progress, research institutions, journal distribution, collaborative networks, research hotspots and cutting-edge trends in this field. The bibliometric analysis reveals that research hotspots are primarily focused on the erosion-corrosion mechanism, equipment, materials, coating structure reinforcement, and new process of anticorrosion strategies. These findings suggest an interdisciplinary integration trend and the emergence of intelligent prevention and control methods. By elucidating the evolution and future direction of erosion-corrosion research, this study offers valuable insights for advancing academic progress and technological innovation in this area.