{"slug": "knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for", "title": "Knowledge-Constrained Shape Optimization with a Mixture-of-Experts Neural Operator for High-Confidence Design", "summary": "Researchers proposed a knowledge-constrained shape-optimization framework using a Mixture-of-Experts Neural Operator (MoE-NO) for aerodynamic design, achieving up to 10% drag reduction in vehicle shape optimization. The framework translates expert constraints into quantifiable parameters and uses uncertainty estimation to improve surrogate model reliability.", "body_md": "arXiv:2607.09763v1 Announce Type: new\nAbstract: Engineering shape optimization faces challenges in both expert-dependent problem setup and surrogate-model reliability. In practical aerodynamic design, optimization settings such as editable regions, deformation ranges, and design-preservation constraints are typically specified manually by experienced engineers, while surrogate-based optimization may become unreliable for heterogeneous geometry databases and out-of-distribution designs. To address these challenges, we propose a knowledge-constrained shape-optimization framework that translates knowledge-based constraints and user intent into quantifiable parameters of DFFD-based deformation operators, enabling engineering-aware and controllable constrained optimization. We further develop a Mixture-of-Experts Neural Operator (MoE-NO) to improve drag prediction and trend consistency over heterogeneous aerodynamic datasets. Based on the MoE-NO encoder and Mahalanobis distance, an uncertainty-estimation strategy is introduced to detect out-of-distribution geometries and selectively trigger physics-solver feedback for local sample enrichment. Experiments on in-house MPV, SUV, and Sedan datasets show that MoE-NO achieves a test-set MAPE of $1.16\\%$ and a trend-prediction accuracy of $94.34\\%$, outperforming the best baseline results of $1.52\\%$ and $90.34\\%$, respectively. Vehicle shape-optimization experiments further yield CFD-validated drag coefficient reductions of approximately $4\\%$ to $10\\%$.", "url": "https://wpnews.pro/news/knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for", "canonical_source": "https://arxiv.org/abs/2607.09763", "published_at": "2026-07-14 04:00:00+00:00", "updated_at": "2026-07-14 04:03:24.756538+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["Mixture-of-Experts Neural Operator", "DFFD"], "alternates": {"html": "https://wpnews.pro/news/knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for", "markdown": "https://wpnews.pro/news/knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for.md", "text": "https://wpnews.pro/news/knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for.txt", "jsonld": "https://wpnews.pro/news/knowledge-constrained-shape-optimization-with-a-mixture-of-experts-neural-for.jsonld"}}