CAREER: : Advanced Thermal Management of Lithium-Ion Battery Packs: Combining Physics-Based and Machine Learning Models toward High Thermal Safety

点击翻译按钮获取中文摘要

Lithium-ion battery (LiB) packs play an essential role in electrified transportation, grid, renewables and energy-aware buildings. While the demand on the use of LiB is increasing everyday there are some safety issues that remain unresolved. These battery packs are susceptible to catching fire which pose a great danger to human life and property. The fire hazard in these batteries is caused by a continuous rise of temperature phenomenon (called "thermal runaway") that is not well understood. This Faculty Early Career Development Program (CAREER) project aims at developing reliable high-fidelity mathematical models that can help understand this phenomenon and help predict the thermal behavior more accurately. The success of this project will have huge impact on electrification happening in various industry sectors including transportation, grid, energy, and several others. This project will integrate research into diverse education and outreach activities, including curriculum improvement, community outreach, and research mentorship, to engage K-12, undergraduate, and graduate students. Despite its importance, LiB thermal management practices are largely empirical or coarse-grained with poor scientific rigor, thus inadequate for meeting the safety demands. To change this situation, this research will develop a foundational framework for characterizing and monitoring LiB packs' spatially and temporally distributed thermal behavior, which will build on a multi-disciplinary synthesis of ideas from first-principles modeling, machine learning, distributed estimation, and network systems. This will drive new knowledge advancement in: 1) a hybrid modeling methodology that integrates first-principles-based and data-driven machine learning models, 2) optimal estimation and machine learning theory based on hybrid models, and 3) hybrid-model-based principles, algorithms and tools for temperature field reconstruction and thermal runaway detection. The models and algorithms will be rigorously evaluated through a mix of theoretical analysis, software-based simulation, and experimental validation using a fully instrumented PEC SBT4050 battery tester. The results will open a new research avenue for LiB packs' thermal management while advancing the modeling, estimation and learning theories for complex spatio-temporal systems, with potential application to many other engineering fields.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.