Design Optimization of Heat Transfer in Automotive Battery Using Generalized Neural Network Regression KPIT Technologies, Limited

Format:

Book

Conference/Event

Author/Creator:

Althi, Tirupathi Rao, author.

Contributor:

K, Manu

Manuel, Naveen

Conference Name:

International Automotive CAE Conference Road to Virtual World (2024-10-23 : Delhi, India)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2024

Summary:

Electrification is driving the use of batteries for a range of automotive applications, including propulsion systems. Effective management of thermal energy in lithium-ion battery pack is essential for both performance and safety. In automotive applications especially, understanding and managing thermal energy becomes a critical factor. Cells in the propulsion battery pack dissipate heat at high discharge rates. Cooling performance of battery can be realized by optimizing the various parameters. Computational Fluid Dynamics (CFD) model build and simulations are resource intensive and demand high performance computing. Traditionally, evaluating thermal performance involves time-consuming CFD simulations. To address this challenge, the proposed novel approach using Generalized Neural Network Regression (GNNR) eliminates complex CFD model building and significantly reduce simulation time. GNNR achieves up to 85% accuracy in predicting Heat Transfer coefficient. The benefits of GNNR extend beyond accuracy. Streamlining the parameter optimization process, it enhances the thermal efficiency and cost-effectiveness of battery pack design. This acceleration in design precision ultimately reduces development costs. GNNR-based solution offers a faster, acceptably accurate way to evaluate thermal performance in lithium-ion battery packs, paving the way for faster design process

Notes:

Vendor supplied data

Publisher Number:

2024-28-0024

Access Restriction:

Restricted for use by site license