A Study of Structured/Semantic Data Extraction from Mechanical Engineering Drawings
Bibliographic record
Abstract
Mechanical engineering drawings are essential documents for designing, manufacturing, and maintaining industrial systems. However, their complex structure-combining graphical elements, annotations, tables, and text-makes manual interpretation costly, time-consuming, and error-prone. Usual document management approaches store engineering drawings as digital files but lack efficient methods for retrieving and utilizing their semantic data. This paper explores recent computer vision and artificial intelligence advances to automate information extraction from engineering drawings. State-of-theart methods for processing symbolic, tabular, and geometrical data are reviewed, highlighting the challenges of low-level (e. g., OCR, vectorization) and high-level (e. g., 3D reconstruction, semantic annotation) interpretation. A deep learning-based case study is presented for extracting title blocks, bills of materials, and general notes. Finally, a conceptual framework is established for understanding engineering drawing and integrating multimodal data to enable applications in supply chain management and manufacturing optimization. Our findings underscore the need for open datasets, robust benchmarks, and novel AI-driven methodologies to bridge the gap between raw engineering drawings and structured, actionable information.
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 | 0.003 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.001 |
| 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".