Battery modeling can be greatly sped up by building simulation apps that contain surrogate models. Whereas the detailed Newman model provides accuracy at a significant computational cost, lumped models are faster but less accurate. For cases that call for both accuracy and speed, surrogate models are worth considering.
This 60-minute webinar will discuss the tradeoff of complexity versus speed of results as well as how battery applications may benefit from surrogate models. The session also will explore the process of training and using surrogate models for time-dependent battery models. Through an example of a simulation app that predicts the performance of a Li-ion battery undergoing a test cycle, the session will demonstrate functionality available in COMSOL Multiphysics® software for training deep neural network models. An audience Q&A session will follow the technical presentation.
Speaker:
Rasmus Karlsson, Ph.D., COMSOL
Since joining COMSOL as a Senior Software Developer in 2017, Dr. Rasmus Karlsson has contributed to the development of the company’s electrochemistry products. He holds a Ph.D. in chemical engineering from KTH Royal Institute of Technology, Stockholm.
Moderator:
Amanda Hosey, Editor, SAE Media Group
By registering for this event:
- You are providing us with some personal details, including an email address. SAE Media Group will process that information as described in our privacy policy https://saemediagroup.com/privacy-policy/.
- You agree that our carefully selected Sponsors may contact you. You may opt out from their communications at any time by contacting them directly.
- You agree that SAE Media Group may contact you about other events, news and promotions we believe would be of interest to you. You may opt out from our communications at any time by contacting us directly.