8 papers
Calculation and rejection diverge in language models tested at known mechanical limits
Shaoliang Yang, Jun Wang
When a language model returns engineering quantities with the status "solved", software that trusts it passes them on, even when the requested design is physically impossible. Such…
How the Classical Baseline Shapes Machine-Learning Speed Claims in Topology Optimization
Shaoliang Yang, Jun Wang
Topology optimization places material in a design domain to optimize a structure's performance, such as its stiffness or heat conduction. Machine-learning methods often report larg…
Language models can notice an impossible engineering problem yet still report it as solved
Shaoliang Yang, Jun Wang
Language models draft engineering calculations, but answer accuracy does not show whether they reject an impossible problem. We tested 14 models on 30 pairs of mechanics problems,…
SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration
Shaoliang Yang, Jun Wang
Industrial inspection pipelines often restore a measured image before a detector acts on it, yet restoration can suppress detector-supported defect structure or create clean-region…
When a positive SIMP density floor is not enough: solver admissibility and guarded floor selection in matrix-free 3D topology optimization
Shaoliang Yang, Jun Wang, Yunsheng Wang
In a matrix-free geometric-multigrid FGMRES solver for three-dimensional SIMP topology optimization, a reported converged solve is not always a converged solve. On four of 102 held…
Does Super-Resolution Preserve Defect Evidence? A Low-False-Call Benchmark for Semiconductor Inspection
Shaoliang Yang, Jun Wang
Super-resolution can make inspection images appear sharper without preserving the evidence needed to detect a defect. We study this failure mode with a benchmark that separates rec…
Empirical Calibration and Conditional-Reliability Diagnostics for Bearing RUL Prediction under Operating-Regime Shift
Shaoliang Yang, Jun Wang, Yunsheng Wang
Remaining useful life (RUL) estimates support reliability and maintenance decisions only if both point accuracy and prediction intervals remain trustworthy when operating condition…
Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization
Shaoliang Yang, Jun Wang, Yunsheng Wang
We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuatio…