A Preliminary Investigation into Automated Identification ofStructural Steel Without A Priori Knowledge
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
One of the most prohibiting factors when attempting to reuse structural steel members or systems of members is the time and labour required to accurately determine dimensions. Current practices dictate that all required measurements are recorded by hand using tape measures and calipers which adds a significant cost to reused steel. To mitigate this cost, a semi-automated method for identifying structural steel components and systems is proposed that uses data acquired in the form of a 3D point cloud. Current research in the field of automated object recognition currently has two major limitations: (1) a priori knowledge, such as a building information model (BIM) is required, or (2) only simple, flat surfaces can be identified. The purpose of this study is to preliminarily investigate the possibility of automating the process of (1) cross section identification, (2) end connection geometry of bolted connections, and (3) relative component position of multi-component, planar structural systems such as trusses. Cross section identification is performed by creating filters that match standard structural sections and then convolving them over images of the cross section data. The end connection geometry is identified using Hough algorithms to detect lines and circles representing the limits of the component and the bolt holes, respectively. Planar structural systems are identified using Hough algorithms to detect lines which represent the components of the system. The results from the proposed methods show a strong potential for fully automated processes to be able to identify structural steel components and systems without a priori knowledge.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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