Summary:
Researchers in the UCLA Department of Chemical and Biomolecular Engineering have developed a new battery management system to improve lithium-ion battery lifetimes.
Background:
Lithium-ion (Li-ion) batteries are crucial for powering many modern devices, from smartphones to electric vehicles due to their high energy density, long life cycle, and rechargeability. Over time, Li-ion batteries degrade, reducing performance and posing safety risks. Regular monitoring of the battery during its operational lifetime is critical, as fine-tuning the rate of charge and discharge can substantially improve Li-ion battery lifetimes. To meet the growing demand for high performance and durable batteries, there is an urgent need to develop rapid and accurate systems that characterize Li-ion cell quality to tightly control charging rates to preserve battery integrity.
Innovation:
A research team led by Professor Yuzhang Li of the UCLA Chemical and Biomolecular Engineering Department have developed an AI-powered battery management system to enhance the lifetimes of Li-ion batteries. By using a machine learning model trained on a large data set of lithium battery cells, the researchers can quickly assess whether lithium plating, the harmful build-up of lithium metal on battery anodes, is occurring. Their machine-learning based algorithm responds to this by reducing the charging rate of the battery, limiting lithium deposition while still charging the cell. The researchers have demonstrated a significant improvement in battery life by alleviating capacity decay via Li plating. This innovation could be applied to a wide-range of lithium battery systems by simply re-training the algorithm for different Li-ion battery formats. As demand continues to grow for safe and cost-effective solutions for improved battery life, this technology has the potential for widespread adoption in a vast array of industries.
Potential Applications:
• Li-ion battery life preservation
• Electronic vehicle charging stations
• Utility-scale battery storage systems
• Smartphone/computer chargers
• Grid infrastructure monitoring
• Consumer electronics (IoT, wearable devices)
Advantages:
• Dynamic response
• Independent charge decision-making
• Improved charging safety
• Provides fast charging with existing battery architecture
Development-To-Date:
Researchers have validated their neural network architecture to accurately predict battery life using graphite materials.
Reference:
UCLA Case No. 2024-209
Lead Inventor:
Yuzhang Li, PhD, Assistant Professor UCLA Department of Chemical and Biomolecular Engineering