Researchers have developed new physics-informed machine learning strategies to improve sensitivity analysis in engineering systems. By fusing physics-based models with experimental data, these methods aim to enhance the accuracy of sensitivity estimates. The study explores deep neural networks (DNNs) and Gaussian processes (GPs), investigating techniques like physics-constrained loss functions and sequential training with simulation and experimental data. Results indicate that DNN-based models offer tighter bounds on sensitivity estimates compared to GP models, with applications demonstrated in additive manufacturing and lake temperature modeling. AI
IMPACT Introduces advanced machine learning techniques for more accurate engineering system analysis.
RANK_REASON The cluster contains an academic paper detailing novel research methods. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Daily Papers →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
