Structural Plan-to-Model Conversion with Deterministic Geometry and Guarded Agentic Vision-Language Refinement

Converting structural framing plans into editable finite-element model drafts remains labor-intensive and prone to transcription error. Existing drawing-understanding systems for building components rely on task-specific trained neural detectors, and language-model agents in structural engineering operate on text or model data rather than the drawing itself. This paper presents, to the authors' knowledge, the first framework applying an agentic vision-language layer to structural component detection and model drafting from framing-plan PDFs, without task-specific detector training or fine-tuning. A deterministic stage extracts primitives, estimates scale by dimension-ratio consensus, recognizes five entity classes with a drafting grammar, and assembles an editable layout. The agentic stage proposes typed corrections constrained by deterministic candidates, operation-specific admission tests, change-level review, and fail-closed transactions. Evaluation used an author-generated benchmark of 100 plans: a development half that informed every rule revision, and a seed-disjoint held-out half generated after the rules froze, evaluated once. All reported scores are end-to-end results of the complete framework on the held-out half. Scale was estimated within 0.1% of the generator reference for every drawing. Recall and precision were 0.922/0.997 for columns, 0.886/0.990 for beams, 1.000/1.000 for walls, 1.000/1.000 for braces, and 1.000/0.964 for openings. A controlled study repeated two corruptions three times on three development drawings. Calibration passed all nine trials; member repair met every strict end-state predicate in five of nine. Guarded review corrected missed framing and false marks within explicit bounds. The held-out half shares the development generator, so the study excludes independently drafted plans, raster evaluation, analytical connectivity, and solver validation.

An Open-Source Framework for Coupled Vehicle-Bridge Interaction Analysis Using OpenSees

Vehicle-bridge interaction (VBI) is important for simulating bridge response under moving vehicular loads and supports applications such as dynamic amplification studies, weigh-in-motion, and indirect bridge monitoring. Although VBI theory is well established, many existing implementations use custom finite element code or research-specific solvers, which limits their reuse. This paper presents an open-source Python framework for VBI analysis built on OpenSees. The bridge and vehicle are modeled as separate OpenSees subsystems and connected through an iterative scheme that exchanges displacement and force values at each time step until convergence. Five vehicle model types are supported, from a single axle spring-mass system to two-axle composite half-cars with body pitch and separate tyre and suspension elements. A decoupled mode is also provided: the vehicle static weight is applied as a moving load on the bridge, and the resulting bridge motion is then used as base excitation for the vehicle. Validation against three published benchmarks (quarter-car, half-car with pitch, and full composite models) shows close agreement, with R2 above 0.998 in all cases. A parametric study reports the accuracy of the decoupled mode as a function of vehicle-to-bridge mass ratio, span length, speed, road roughness class, and background traffic density, and indicates when the decoupled mode is adequate and when full coupling is needed. The complete framework and benchmark configurations are released as open-source software to support reproducible research in vehicle-bridge dynamics.