AI-assisted 3D model generation for discontinuum-based analysis of URM buildings
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This research presents a novel framework for the discontinuum-based analysis of unreinforced masonry (URM) buildings, integrating artificial intelligence (AI) assisted object detection and segmentation into the structural analysis workflow. Recent advancements in machine learning, particularly Convolutional Neural Networks (CNNs), are utilized to digitize a URM building, and the most relevant construction quality parameters (e.g., block size and staggering ratio) are automatically captured from the vision-based data. The collected information is used to inform the implemented block generation algorithm, which places masonry units into wall sections that are not documented (or poorly detected) due to various on-site obstructions. Then, the digital replica of the building is turned into an evidence-based computational model using the discrete element method (DEM), where detected masonry units are represented as discrete rigid blocks in a fully discontinuous setting. The mechanical interaction between rigid blocks is predicted using a cohesive frictional contact model to capture the unit-mortar interface (bond) behavior. The AI-assisted DEM-based model is later used to perform nonlinear pushover analysis to predict the seismic behavior and collapse mechanism of the analyzed building. Hence, it is demonstrated that the proposed approach offers a great potential for discontinuum-based analysis of URM buildings by eliminating the time-consuming model generation process and providing the most representative construction quality features in the structural analysis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it