Surrogate-Based Modeling of Induction Machines to Reduce the Computational Burden of Robust Multi-Objective Optimization
Bibliographic record
Abstract
One of the main obstacles to robust design optimization of Induction Machines (IM) is the high computational burden, which is mainly due to time-intensive nonlinear finite element (FE) simulations. The large multivariable design space of electric machine optimization typically requires running thousands of simulations taking many hours, if not days which is quite prohibitive. To overcome this bottleneck, hybridization of FE-based optimization with approximate models can lead to expedite the process. This paper is focused on accelerating the typical FE-based optimization scenarios by implementing and systematically studying an ensemble of surrogate models of IMs in terms of computational burden and performance. In this regard, after adopting the most significant surrogate model, a multi-points sequential sampling process with a two-step surrogate-based optimization approach is developed. Compared with direct FE-based robust optimization, competitive results are achieved by adopting the proposed hybrid surrogate-based approach and the overall runtime is reduced by 69%. Furthermore, as a case study, an optimization problem for an 11-kW IM is considered by applying the typical FE-based optimization task followed by the proposed hybrid technique. Hence, the achievable speed improvements, as well as further possible enhancing means are discussed. The detailed comparison of the presented surrogate models makes a comprehensive source for engineers and designers to follow.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".