Spatial Parameterization of Non-Semantic CAD Elements for Supporting Automated Disassembly Planning
Bibliographic record
Abstract
Digital data and associated semantics play a fundamental role in supporting the vision of Construction 4.0. Advancements in digitization workflows such as scan-to-BIM and automated meta-data generation are being used for data-driven decision making. A challenge with collecting and processing raw, non-semantic data is the process of integrating intelligence into and characterizing data automatically. This paper demonstrates how spatial parameterization (i.e., extracting, modifying and analysing parameters that define the spatial properties of a component) can be used as a method for automating steps in disassembly planning for buildings. The potential use cases of disassembly planning include adaptive building reuse, robotic assembly programming, reconfigurable prefabricated assemblies and selective disassembly for rehabilitation and repairs. This paper presents spatial parameterization in a framework to disassemble building components via a rule-based algorithm that comprises three dimensional Cartesian properties and clash detection between non-semantic CAD elements. Demonstration of the framework is carried out using a case study where the interior wall of a building on the University of Waterloo campus was disassembled for adaptive reuse purposes. Comparison of the case study results to the actual disassembly sequence demonstrates how spatial parameterization is effective for automating key steps in disassembly planning. A discussion is provided to identify key barriers to increased automation which relate to modelling accuracy, Level of Development (LOD) for Building Information Modelling (BIM), and global spatial constraints for disassembly.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".