Intelligent advisor for the design of preforms in stretch blow molding
Bibliographic record
Abstract
Stretch blow molding is the process of choice for the production of PET containers, for the food and beverage industry as well as the pharmaceutical sector. The stretch blow molding process involves three stages, the reheat stage where previously injection molded preforms are heated to desired forming temperature distribution, followed by the forming and the solidifcation stages. The process is a high volume process with costly tooling for both the preform and the container. The design of the tooling, via virtual technologies is preferable so as to minimize costly tooling reworks. Industry has readily accepted the use of finite element technologies in the prediction of the stretch blow molding process. This acceptabce is now generating large amounts of information that are invaluable for future designs. The challenge is now to structure and make use of this information in an efficient way as possible. A design database structure has been set up for information representation from past designs, including a design, preform and bottle databases. Mathematical methodology has been established to represent preform design. The design database and a series of user-defined heuristic design rules for stretch blow molded containers are used to extract unknown input needed in the design methodology. The heuristic knowledge represents the different product characteristics based on mechanical requirements. Those rules and the data extraction will evolve and adapt themselves taking into account new design database, new rules and modified rules. The model inputs are the bottle fill level capacity, bottle diameter, bottle length and bottle transition length, whereas the outputs of the model are the preform shape and weight.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.068 | 0.024 |
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".