AINeutralarXiv – CS AI · 7h ago6/10
🧠
Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation
Researchers benchmarked five machine learning uncertainty quantification methods for predicting turbine gas temperature in engine health management systems. The study reveals distinct trade-offs between prediction interval coverage, width, and stability, providing practical guidance for selecting appropriate methods in real-world prognostics applications.