Stock design in hybrid manufacturing using a constrained clustering approach
Bibliographic record
Abstract
Hybrid Manufacturing (HM) is a key pillar of smart manufacturing, enabling the production of complex parts with high precision and superior surface quality while minimizing costs and enhancing sustainability. A key challenge in HM systems is selecting the appropriate stock geometry to initiate processing both additive and subtractive features while achieving these benefits. Poor stock design can lead to increased waste and energy consumption, whereas an optimized configuration improves operational efficiency and maximizes sustainability. This paper addresses finding stock designs in HM, a problem that has not been tackled before using hybridized machine learning optimization techniques. A constrained clustering machine learning approach to determine stock dimensions for prismatic end parts is proposed. Given the geometry of the features included in these end parts, a novel combinatorial optimization model is developed to assign these features to pre-defined clusters such that the Hausdorff distance between features within clusters is minimized. Multiple scenarios are explored by evaluating different numbers of clusters. The proposed optimization model is validated, and its computational efficiency is evaluated through a case study that includes two test parts extending an existing test part from the literature. The first test part includes 22 additive and subtractive features while the other one includes 27 features. Due to the intractability of this combinatorial optimization clustering problem, problem instances representing small and medium-sized scenarios can be solved to optimality within a short time, whereas for large instances, only feasible solutions are obtained within a limited computational time of two hours.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".