Surrogate-Assisted Multi-Objective Design Optimization of a Lorentz Force Actuator
Bibliographic record
Abstract
Micro-electromechanical systems (MEMS) sensors and actuators are widely used in a variety of applications, from medical imaging to space telecommunications, making their optimal design crucial. Designing MEMS is a time-consuming process that requires numerous iterations of resource-intensive simulations to evaluate potential designs. As the number of design variables and objectives grows, the complexity and required computational time for this process also increase significantly. Consequently, most efforts to tackle this challenge have focused on scenarios with limited design parameters and a single objective, leaving the area of efficient multi-objective optimization (MOO) for MEMS devices relatively unexplored. In this study, we employ surrogate-assisted design optimization for a MEMS Lorentz force actuator. During an iterative multi-objective optimization process, surrogate models are utilized for performance evaluation of designs instead of numerical simulations. This approach enables us to achieve optimal designs that satisfy all objective constraints using as low as 2% of the number of simulations required compared to case surrogate models are not used, greatly facilitating design optimization. Additionally, we investigate how the number of training simulations and their preprocessing impact the accuracy of the surrogate models and the optimization results.
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 | 0.002 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 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".