Unmanned aerial vehicle (UAV) inspection technology has become an essential tool for monitoring wildfires in transmission line corridors due to its flexibility, cost-effectiveness, and adaptability to remote and complex terrains. However, current research lacks initial wildfire image datasets from the perspective of UAV inspections, and existing algorithms struggle to accurately identify early-stage wildfires. This study constructs an initial wildfire image dataset from a UAV perspective and proposes the YOLOv11n-MCC detection model for transmission line corridors.

Through the field inspections of national transmission line corridors for 174 h, covering 82 000 km with UAVs, 1 308 transmission line corridor inspection images were obtained, and a transmission line corridor inspection image dataset from the perspective of the UAV was constructed. This dataset was analyzed to identify the characteristics of the initial wildfire images. The early wildfire detection model, YOLOv11n-MCC, based on an enhanced version of YOLOv11n, was then proposed. First, part of the traditional convolutional network in YOLOv11n was replaced with multi-scale feature convolution(MFConv) to reduce computational load while improving feature extraction. Second, the C2PSA module in the backbone network was replaced with the spatialand channel synergy attention(SCSA) mechanism to improve target localization. Finally, C3k2_ABlock with convolutional additive token mixer(CATM) at its core was embedded to improve target representation and selection in complex backgrounds.

MFConv, SCSA attention, and C3k2_ABlock with CATM sequentially improved the YOLOv11n-MCC model's ability to detect targets in complex scenes. Comparative experiments revealed that the YOLOv11n-MCC model significantly outperforms the YOLOv11n baseline model in terms of accuracy, mAP50, parameter count, and giga floating-point operations per second(GFLOPS) for early mountain fire small-target detection, making it portable but still computationally efficient. Specifically, precision increased by 9.0 percentage point, recall by 3.8 percentage point, and mAP50 by 5.7 percentage point. In addition, the number of parameters and GFLOPS decreased by 0.149×10⁶ and 0.2, respectively. The YOLOv11n-MCC architecture achieves enhanced multiscale feature representation while maintaining reduced computational complexity, thereby improving operational efficiency without compromising detection performance.

The image dataset for transmission line corridor inspection constructed in this study can effectively support the training and testing of the improved fire detection algorithm. The proposed YOLOv11n-MCC model demonstrates stable performance in detecting small initial mountain fire targets and can be effectively applied to real-time wildfire detection in transmission line corridors using UAVs, thereby providing essential technical support for early wildfire detection. Future work will focus on examining the influence of varying smoke-to-fire ratios on model training to further enhance wildfire detection accuracy.

Leakage accidents in urban gas pipeline networks occur from time to time, and most of them are accompanied by secondary disasters, such as explosions, fires, and building collapses, which seriously threaten the safety of people's lives and property. Previous research on gas accident rescue capability primarily focuses on gas enterprises or indoor gas emergencies, and research on accidents associated with gas pipeline networks is lacking. Some studies have limitations, such as broad evaluation indicators, vague content, and limited scope of assessment objects, which cause difficulties in applying the evaluation system in practice. This study aims to identify the weaknesses in the emergency rescue process for accidents associated with urban gas pipeline networks, effectively assess the emergency rescue capabilities for such accidents, and help improve the emergency rescue efficiency and gas safety guarantee level.

Herein, the emergency rescue characteristics for accidents associated with urban gas pipeline networks were analyzed and summarized, and the rescue capabilities for these accidents were evaluated. First, based on an in-depth analysis of emergency plans and accident cases associated with gas pipeline networks, the emergency rescue elements of accidents were extracted and sorted. Furthermore, the emergency rescue process was constructed. By summarizing the limitations in emergency rescue, an indicator system comprehensively reflecting emergency rescue capabilities was established based on four aspects, namely humans, pipelines, materials, and management. The system included 4 first-level indicators, 12 second-level indicators, and 27 third-level indicators. Second, the subjective-Objective combination weighting method of the analytic hierarchy process (AHP) and the criteria importance through intercriteria correlation (CRITIC) method were used to calculate the weight of each indicator to reduce the possibility of excessive subjectivity caused by expert scoring to a certain extent. Combining the weight of each indicator can help identify and focus on the indicators with a high degree of importance. Finally, an emergency rescue capability evaluation model was established using the fuzzy comprehensive evaluation approach to realize the quantitative evaluation of the emergency rescue capabilities for accidents associated with gas pipeline networks in specific regions. The model was applied to Zhangwan District, Shiyan City, Hubei Province.

The Results show that indicators such as the "supply-demand ratio of rescue personnel", "effectiveness of information transmission", and "formulation and revision of emergency plans" account for a relatively large weight compared to other indicators. The indicators of "cooperation and coordination ability of rescuers", "equipment performance", and "emergency drill effect" are the weak links in the emergency rescue process of accidents associated with the gas pipeline networks in the region. Therefore, the departmental interaction needs to be strengthened, the construction of the rescue coordination mechanism needs to be improved, and joint prevention and control and coordinated rescue capabilities need to be enhanced. Furthermore, to standardize emergency drill training, the safety production investment guarantee for local gas companies should be increased, and to improve the design and planning of training content, online and offline integrated learning is necessary.

The feasibility and applicability of the evaluation system were verified through the application case. This evaluation system for the emergency rescue capability of accidents associated with urban gas pipeline networks offers a theoretical basis and feasible approach for establishing, improving, and evaluating emergency measures for accidents associated with urban gas pipeline networks.