Home Architecture News AI Pipeline Cross-Checks Structural Design Documents and Flags 253 Discrepancies
Architecture NewsArtificial Intelligence

AI Pipeline Cross-Checks Structural Design Documents and Flags 253 Discrepancies

A team at Seoul National University of Science and Technology built an AI pipeline that reads structural calculations and drawings, matches members and flags mismatches. On one South Korean housing project it found 253 discrepancies.

Share
Infographic titled An AI-Based Pipeline for Detecting Human Errors in Structural Design Documents, with workers, process boxes and result figures
The research team's summary of the pipeline and its case study results · Image: courtesy Jaewook Jeong, Seoul National University of Science and Technology
Share

Researchers at Seoul National University of Science and Technology (SEOULTECH) have built an AI-assisted pipeline that reads structural design documents, extracts the data on each member and checks whether the calculations and the drawings agree. The team, led by associate professor Jaewook Jeong of the Department of Safety Engineering, says the tool is meant for the many projects that still rely on conventional documents instead of building information modelling (BIM). The figures below come from the team’s own case study on one project.

The problem with paper-based coordination

On a typical project, structural calculations and structural drawings are produced by different people with different tools. When the same beam or column is described twice, its reinforcement or size can drift between documents, and in the worst cases such slips can affect safety. BIM can catch these conflicts by keeping everything in one shared model, but the release notes that cost, a shortage of skilled staff and technical barriers keep it out of many projects.

“Importantly, the system performs these checks without relying on Building Information Modeling (BIM), making it particularly relevant to construction projects that continue to use conventional design documents,” Jeong said.

A smiling worker in a hard hat and safety vest tying steel reinforcing bars on a building site
Reinforcement being assembled on a site in Mazatlán, Mexico; bar and stirrup details are among the items the pipeline compares · Photograph: Tomas Castelazo, CC BY-SA 3.0 via Wikimedia Commons

How the pipeline reads structural design documents

First, the documents are gathered and low-quality information is filtered out. For calculation reports, a document layout model called DocLayNet-YOLO finds the regions that hold member data, and the Surya-OCR model turns them into text. Drawings are harder because member schedules come in tables of uneven rows and columns, so the system first locates member codes and then uses OCR together with classic image processing (Canny edge detection, the Hough transform and morphological operations) to find the table cells around them.

Both data sets are standardised, matched using member codes and directions as keys, and compared. Mismatches and duplicates are listed and sorted by type, and the team built a web application so engineers can run the checks without writing code.

Results from one housing project

The pipeline was tested on a residential project in South Korea. It extracted information with 95.56% accuracy from calculation documents and 90.47% from drawings, and flagged 253 discrepancies: 224 missing entries, 15 mismatches in main reinforcement, three in stirrups, eight dimensional differences and three duplicate entries. The release’s image caption describes 29 of them as critical errors, the same as the sum of every category except missing entries.

A tall glazed university building with green vertical fins above a low wing and landscaped rocks
A building on the SEOULTECH campus in Seoul in 2009 · Photograph: A123321, CC BY 3.0 via Wikimedia Commons

The study, by Minsang Gu and colleagues, appears in volume 185 of Engineering Applications of Artificial Intelligence. A single case study cannot show how the method copes with other building types, drawing standards or languages, and no independent replication of the figures has been reported. Jeong suggests the tool “could be particularly valuable for small- and medium-sized construction projects that cannot implement BIM”, which is also where an extra automated check before site work might pay off most.

Share
Written by
Muhammad Abdullatef - Tifa Studio

Muhammad Abdullatef (Tifa Studio) is an architect and urban design researcher with an M.Arch from Istanbul Technical University and a PhD candidacy in Urban Design at Hong Kong Polytechnic University. He writes on architecture, urbanism and parametric design.

Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Articles
Software screen with a colour-coded 3D building model, a bar chart of element counts by level and the heading Model Overview
Architecture NewsBIM

Chaos Acquires Vyssuals to Bring Live BIM Data Dashboards Into Enscape

Chaos, the company behind Enscape, has acquired Vyssuals, whose live dashboards read...

A modern office building with a curved glass top and a red Unite the Union sign over the entrance, behind trees and railings
Architecture NewsCareer

Architecture Workers’ Union Writes to Practices About Staff’s Right to Join a Union

The Section for Architectural Workers has sent a mailshot to UK practices...

A grid comparing hand sketches of a two-storey house with elevations and floor plans drawn by eight Anthropic models, from a blank refusal to detailed sheets
Architecture NewsArtificial Intelligence

An Architect Tested 13 AI Models on a House Drawing Set and Found a Sudden Leap

In a Substack essay, architect Stephen Gallagher describes giving 13 AI models...

A glazed entrance hall with a deep overhanging roof and the words Union Square, fronted by a cobbled forecourt with traffic cones
Architecture NewsConstruction

BDP and Galliford Try Fail to Have Aberdeen Hotel Cladding Claim Dismissed

Lord Richardson refused to throw out Leonardo Hotel Management's claim over the...

Learn Architecture is a global architecture learning platform and marketplace for content creators.

Subscribe to Our Updates

Enjoy a daily dose of architectural projects, tips, hacks, free downloadble contents and more.

Copyright © Learn Architecture Online. All rights reserved.
Made with ❤️ by learnarchitecture.online

iA Media's Family of Brands