A knowledge-driven intelligent agent for automated quantity checking of concrete bridge structures that integrates 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.
Abstract
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.
This work is the first to apply an agentic vision-language layer to structural-component detection and model drafting from framing-plan PDFs without task-specific detector training or fine-tuning.
To address spatial confusion and semantic collapse in maintenance knowledge graph construction for long-distance belt conveyor systems, this study proposes a linear topology-aware alignment framework driven by large language models. The framework constructs a Physical–Space–Fault–Rule ontology and introduces a normaliz...
Xin Li, Yu-Tong Wang, Cong Han et al.· Italian National Conference...· 0 citations
Handoff-H1 is presented, a takeoff system built from three layers: purpose-built computer-vision models that extract primitives; tool-using agents equipped with image operations and in-house visual-task tools, including CV-model-backed counting, detection and plan decomposition; and a persistent, hierarchically structu...
Bruno Chicelli, H. Alves, R. Anselmo et al.· 0 citations
Construction progress monitoring is increasingly combining Computer Vision (CV) and semantic technologies, yet schedules, site photographs, and monitoring outputs often remain disconnected. This limits the interpretability, traceability and reuse of progress-verification results in construction reporting. This research...
F. Madaschi, Jacopo Cassandro, M. Trani· Journal of Information Techn...· 0 citations
This paper introduces Knossos, a benchmark of 19,200 diagrams across six diverse domains, and presents Ariadne, a structured framework that decomposes the task into node inventory extraction and source-conditioned edge prediction, and achieves the highest average Edge F1 among the evaluated methods.
Bang-Wei Guo, Xu-Jiang Zhao, Sheng-Yu Chen et al.· 0 citations
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and depend on process-specific context. We present SciKGExtract, a schema-guided framework that combines large-language-model e...
Sameer Sadruddin, Jennifer D'Souza· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.