Combining Design of Experiments Techniques, Connectionist Models, and Optimization for the Efficient Design of New Product Formulations
Bibliographic record
Abstract
Product formulation design has seen an increasing attention because of the rising demand for application-specific products such as paints, adhesives, coating chemicals, detergents, disinfectants, pharmaceuticals, etc. However, new product formulation design is becoming increasingly difficult in today's markets due to tough competition. To survive and succeed, companies should be able to design new products in a short pace. Failure to do so can be very costly, not only in terms of market share lost, but also in the investment made to develop a product. Given that traditional product development methods are very slow, and cannot fulfill today's needs, a methodology is presented here to efficiently design new product formulations based on a combination of experimental designs, neural networks and optimization techniques. The methodology is applied on a case study that involves disinfectants' formulations. The framework takes advantage of all previous experiments for the next product formulation design, and archives experimental results of the existing project and uses them to retrain a model for future projects. The results show that the use of the proposed methodology significantly reduces the time and cost of product formulation. Although the methodology is applied to the case study of disinfectant formulation, it can be easily adopted to the design of other products.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".