To evaluate the earthquake disaster resistance capability of highway tunnels, it is necessary to study an index system for the earthquake disaster resistance capability of highway tunnels. This paper uses a literature research method. The damage of highway tunnels in 12 earthquake disasters recorded in detail in China and abroad was investigated. According to the types of hazard-beating bodies and damage forms, 17 seismic damage scenes of highway tunnels are classified. According to different damage scenes, the fault tree analysis model is used to identify the damage-causing factors. Combined with the industry standards, norms and research results related to the earthquake resistance of highway tunnels, the evaluation indices are analyzed from three perspectives: engineering geological factors, tunnel structural factors and operation management factors. According to the principle of index system construction, a four-level index system is constructed, which takes the earthquake disaster resistance capability of highway tunnels as the target layer; engineering geological factors, tunnel structural factors and operation management factors as the criterion layer indices; 12 indicators as the index layer and 35 specific indicators. The established index system for the earthquake disaster resistance capability of highway tunnels has strong scientific, rational and application value and can provide a reference for the evaluation of the earthquake disaster resistance capability of highway tunnels and can also provide important support for the safe operation and sustainable development of highway tunnels.
Automated quantity checking directly from two-dimensional bridge drawings remains challenging because the required information is distributed across structural views, detail drawings, and tables, while recognition errors may propagate into deterministic engineering calculations. This study proposes a knowledge-driven intelligent agent for automated quantity checking of concrete bridge structures. A task-specific dataset containing 1362 drawing images is constructed with region-level and parameter-level annotations. A two-stage YOLO method first locates functional regions and then detects parameter-related objects within cropped structural views. The agent coordinates detection, OCR, and table-parsing tools, associates recognized values with parameter types, spatial locations, and bridge components, and organizes them into a unified representation for deterministic rule execution. Human-in-the-loop verification is introduced before calculation to control error propagation. Compared with single-stage detection, the two-stage method increases mAP@0.5 from 0.769 to 0.908, mAP@0.5:0.95 from 0.471 to 0.656, and Recall from 0.664 to 0.792. After verification by bridge design professionals, parameter accuracy increases from 82.77% to 100%, and the overall mean concrete volume error decreases from 23.94% to 2.98%. The framework also produces lower concrete volume errors than three prompt-based large-model baselines across all six evaluated structural types. The methodological novelty lies in integrating region-to-parameter drawing perception, agent-orchestrated heterogeneous information organization, parameter-level human verification, and deterministic engineering rules into a controlled workflow for concrete quantity checking and reinforcement information consistency checking.