Co-PiLOT：面向目标驱动逆向设计的约束物理信息潜空间优化
Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
浏览论文内容
中文总结 AI 辅助
针对昂贵黑箱模拟器下的高维物理系统逆向设计，提出Co-PiLOT潜空间优化框架，结合ViT编码器与扩散解码器学习有效性先验，并引入MERIDIAN主动优化器，在镁合金微结构设计中以160次模拟实现相对目标误差降低3%-22%。
中文摘要 AI 辅助
物理系统（分子、器件、微结构）的逆向设计通常归结为针对昂贵的黑箱模拟器优化高维结构。直接搜索困难重重，因为空间是非欧几里得的，可行性难以编码，且每次评估代价高昂。我们提出Co-PiLOT，一种潜空间优化方法，通过生成式编码器-解码器映射候选方案，将解码器用作学习到的有效性先验，并利用物理信息黑箱优化搜索潜空间。该框架应用于镁合金微结构/织构的逆向设计。我们开发了基于视觉Transformer的编码器；与潜扩散、扩散Transformer和整流流Transformer解码器配对，在约80,000个EBSD衍生的微结构数据集上学习最小瓶颈z。ViT-FMDiT模型（z=768）重建高保真微结构图像（FID 27.86，MS-SSIM 0.178），我们的自分割取向编解码器将其转换为晶体塑性求解器的输入网格。最后，我们引入MERIDIAN，一种由深度核高斯过程不确定性、故障感知可行性预测、流形感知信任区域和目标感知采集驱动的主动潜空间优化器。在160次模拟的预算内，ViT-FMDiT与MERIDIAN的组合取得了最佳的目标驱动目标分数，与七个基线（DANTE、TuRBO、BAxUS、CMA-ES、DDOM、SEIKO、DDPO）在同一解码器上相比，相对目标误差降低了3%至22%。
英文摘要
Inverse design of physical systems (molecules, devices, microstructures) often reduces to optimizing a high-dimensional structure against an expensive black-box simulator. Direct search is difficult because the space is non-Euclidean, feasibility is hard to encode, and each evaluation is expensive. We present Co-PiLOT, a latent optimization approach that maps candidates through a generative encoder-decoder, uses the decoder as a learned validity prior, and searches the latent space with physics-informed black-box optimization. The framework is applied on the inverse design of magnesium alloy microstructure/texture. We develop a vision transformer based-encoder; paired with latent diffusion, diffusion transformer and rectified-flow transformer-based decoders on $\sim80{,}000$ EBSD-derived microstructure dataset to learn a minimal bottleneck, $z$. The ViT-FMDiT model ($z$=$768$) reconstructs high-fidelity microstructure images (FID $27.86$, MS-SSIM $0.178$), which our self-segmenting orientation codec converts into input grids for crystal plasticity solver. Finally, we introduce MERIDIAN, an active latent optimizer driven by deep-kernel Gaussian-process uncertainty, failure-aware feasibility prediction, manifold-aware trust regions, and target-aware acquisition. Within a budget of $160$ simulations, the ViT-FMDiT and MERIDIAN combination yields the best target-driven objective score, reducing the relative target error by $3$--$22\%$ against seven baselines (DANTE, TuRBO, BAxUS, CMA-ES, DDOM, SEIKO, DDPO) on the same decoder.
发表机构
- Helmholtz-Zentrum Hereon（亥姆霍兹-盖斯特哈赫特研究中心）
- Leuphana University Lüneburg（吕讷堡洛伊法纳大学）
- German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
- Saarland University（萨尔大学）
机构由 AI 辅助整理，请以论文原文为准。
