When Candidate Pools Miss Active Constraints: Evidence from Electromagnetic and Thermal Design
Yucheng Liu, Chuncheng Zhao
原文摘要
Finite candidate pools can limit surrogate-assisted design when good designs lie near intersecting active constraints. For independent uniform candidates in a normalized box, the typical minimum sum of gaps to k active bounds scales as (k!/N)^(1/k) for a pool of size N. This geometric limitation persists even with an accurate surrogate. We examine it through a controlled synthetic study and two finite-element design problems with inexpensive analytic constraints: a seven-variable electromagnetic coil and an independent six-variable heat spreader. The budget permits 25 initial observations and 50 further evaluations. On ten matched seeds, replacing pool EI with continuous constrained EI refinement raises mean coil response from 0.9120 to 0.9745 mT and lowers mean thermal resistance from 12.688 to 11.905 K/W. Standard continuous LogEI performs better than this refinement on nine coil seeds and all ten thermal seeds, reaching 0.9770 mT and 11.860 K/W. GP-mean search has the highest nominal coil mean but exhibits a thermal outlier on one seed. Mesh and domain checks preserve the substantial continuous-search advantage over the pool; they do not establish a resolved physical ranking among the closely performing continuous policies. Together, the sampling analysis and matched simulations identify when finite-pool search restricts the use of an FEM budget. The results support continuous constrained acquisition search, with stable LogEI as an effective existing implementation, when finite pools poorly represent high-value boundary designs. Bayesian optimization; acquisition optimization; active constraints; simulation-driven design; finite-element method; Gaussian-process surrogate; electromagnetic coil design; heat conduction
cs.LG