An Identification Method for Vulnerable Bridges Based on the SCPR Model

A massive number of early-constructed small-to-medium-span bridges are collectively entering an “aging” phase in China. Meanwhile, vast amounts of unstructured bottom-level inspection texts remain underutilized. To address them, this paper proposes a data governance method. Large Language Models were leveraged to process unstructured defect data from 18,238 real-world bridges nationwide. The data were structurally cleaned and mapped into discrete features, revealing multidimensional vulnerabilities. On this basis, the Stable Contrastive Pattern Risk (SCPR) intelligent decision-making model was developed. The results demonstrate that, following robust filtration, 6 nationwide common risk rules were extracted from 2064 initial candidate combinations. These rules converge into three core risk patterns: the heavy-duty aging pattern, the substructure-dominated pattern, and the over-water small-span low-seismic-design pattern. Guided by these robust rules and specific damage enrichment characteristics, risk stratification and differentiated management strategies were further formulated for Class III bridges. This research facilitates a paradigm shift in bridge maintenance. It moves from reactive, post-event symptom characterization toward data-driven, proactive early warnings. This shift provides a substantive scientific foundation for optimizing resource allocation and enabling precise investment decisions at the road network level.