A fabrication-aware vectorized generative representation for topology optimization of path-defined MEMS microstructures
Gong-Zeng Liu, Lin-Feng Zhao, Jie Zhang, Xiang Liu, Yi-Meng Lv, Tian-Yu Geng, Zai-Fa Zhou · 2026
Read A fabrication-aware vectorized generative representation for topology optimization of path-defined MEMS microstructures by Gong-Zeng Liu, Lin-Feng Zhao, Jie Zhang, Xiang Liu, Yi-Meng Lv, Tian-Yu Geng, Zai-Fa Zhou (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13680617.txt.
Description
Tiny machines etched on chips need shapes that are both clever and actually buildable. Gong-Zeng Liu and co-authors present a design encoding for such shapes in this 2026 paper. Pixel-by-pixel designs offer freedom but often give broken or unbuildable layouts. Search methods that tweak designs step by step are prized when smooth math does not apply, yet they live or die by how compact the encoding is.
Their encoding turns a few smooth dials into full layouts that are connected and fit factory rules by construction. Line width, spacing, and smooth corners are baked into the generator. The shapes are defined by paths, like a drawn route, rather than by pixels. That built-in care lets the search spend its effort on performance instead of repairs. The work targets microstructures for MEMS devices.
Catalog record
| CREATOR | Gong-Zeng Liu, Lin-Feng Zhao, Jie Zhang, Xiang Liu, Yi-Meng Lv, Tian-Yu Geng, Zai-Fa Zhou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |