HIGHLIGHTS
- What: The authors propose a framework for a hybrid approach for technology-agnostic customizations of a process for stochastic and domain-knowledge-informed failure distribution predictions. The authors show how to overcome this challenge by introducing a domain-knowledge-informed machine_learning approach with novel customization. The approach is entirely technology-agnostic, but the authors focus on batteries. The authors aim to tackle domain awareness, extrapolation capability, accurate uncertainty quantification, and early stopping by incorporating domain knowledge into a GP model to identify the minimum necessary testing effort while achieving accurate predictions.
- Who: Stephen J. Harris . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.