Part Data Mining for Information Re-Use in a PLM Context
Bibliographic record
Abstract
Difficulty in locating existing information in order to reuse it constitutes a major challenge to productivity. The use of PLM systems (Product Lifecycle Management) aims in particular to reduce the time and cost of developing a product by facilitating the re-use of existing parts or related information (process plans, tools, FEM, estimates, etc.). When information is alphanumerical, using search engines, such as those made popular on the internet, is efficient. However, a significant portion of information used in engineering rests within CAD (Computer Aided Design) models, making such search tools irrelevant. To aid in the re-use of information, two problems must be resolved: it is first necessary to be able to locate similar parts in the electronic database of the company, and then be able to systematically identify their differences. This article presents some of the results from our work on part, product and process data mining (P3DM). It focuses on tools developed to search similar 3D geometric models and to identify their differences. The PartFinder application locates similar parts by comparing signatures extracted from their solid representations. The 3DComparator aims to identify the differences in terms of Form and Fit between the identified parts. In both cases, the recommended approach is independent of the CAD system, and can also deal with parts represented by IGES or STEP files. Moreover, the approach does not require that the parts occupy the same position and have the same orientation in space. These two points, CAD and position independence, are the main benefits of our approach compared to other existing applications. Lastly, if the comparison takes place between two evolutions of the same geometrical representation of a part, a third tool allows the comparison of the specification trees. The SpecComparator is also presented briefly. An example based on industrial data illustrates the benefit that could be generated.
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 | 0.008 | 0.027 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.015 | 0.014 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 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".