Automating clash relevance filtering in BIM-based multidisciplinary coordination using machine learning
Bibliographic record
Abstract
In a context where Machine Learning (ML) is reshaping the construction industry and where normative frameworks such as ISO 19650 govern BIM data management, this paper aims to automate the filtering of true and false clashes in 3D models coordination process, using machine learning (ML). A metadata extraction plug-in is developed to gather the necessary data for training ML models. Tests are conducted on BIM models to evaluate the plug-in's ability to identify and classify clashes, followed by a reimplementation of the solution within an existing BIM software environment. Validation, carried out through both technical testing and feedback from industry professionals, demonstrates the plug-in's functionality and its ability to replicate the decision-making process of a BIM coordinator in clash filtering. Intended for construction professionals this paper highlights the potential of AI to enhance BIM quality control while complying with regulatory standards and meeting the practical needs of the industry. • Metadata extraction plug-in for training ML models. • Evaluation on BIM models for clash identification and classification. • Implementation within existing BIM software environment. • Validation through technical testing and industry feedback. • Demonstrated functionality replicating BIM coordinator decision-making in clash filtering.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".