February 07, 2021 | 7:00 pm

$99.00

Meeting the demand for reliable energy storage, this work presents a machine-learning model for precise cycle life prediction in lithium-ion batteries (LIB). It explores battery aging features, utilizes data-driven methods for health assessment, and applies machine learning to predict cycle life. To address data limitations, synthetic data generation is employed, enhancing prediction accuracy. The presentation concludes by demonstrating the practical deployment of the proposed ML model on a battery management system, showcasing its potential impact on power usage efficiency. Discussions cover crucial aspects such as battery aging, data-driven health measurement, and the model’s versatility in handling accidental effects during operation.

This webinar will focus on the following key topics:

• Unveiling Battery Aging: identifying key aging features
• Data-Driven Insights: machine learning for battery state of health assessment
• Cycle Life Precision: machine learning in Lithium-Ion battery predictions
• Addressing Data Gaps: synthetic data for enhanced prediction accuracy
• Real-World Impact: practical deployment of ML on battery management systems

Presenter
Meghana Sudarshan – Ph.D. Candidate at Purdue University

Meghana Sudarshan is currently pursuing a Ph.D. from the School of Aeronautics and Astronautics at Purdue University. Her research focuses on developing data-driven models agnostic battery management systems in UAVs and electric vehicles for predicting degradation of COTS (Commercial Off-The-Shelf) Li-ion Batteries as a function of operation parameters.

Comments are closed.