SBIR Phase II: Real-time predictive battery pack diagnostics and algorithms

这项小企业创新研究（SBIR）第二阶段项目的更广泛影响/商业潜力是支持锂离子电池（LIB）技术的可持续性。LIB的使用正在增长，因此导致了电池浪费的潜在增加。第二阶段项目将开发新的诊断技术，使汽车制造商和储能供应商能够快速准确地测量其电池在现场的性能和退化情况。它将进一步利用机器学习为现场应用开发更准确的电池模型和预测健康算法。即使没有特定系统的历史信息，这些算法也有能力做出健康预测，并且硬件可以移植到不同的应用程序中。更准确的实时电池退化评估可以为车载算法提供信息，提高整体电池组效率，并降低成本。这个小企业创新研究第二阶段项目解决了测量和预测大尺寸电池退化的挑战，将新硬件与机器学习和电化学相结合。该项目将进行全面的电池老化研究，量化电池老化的领先和滞后指标。领先指标包括利用率、日历老化和环境影响，滞后指标包括交流阻抗、直流内阻和电池的特定充放电模式。预期结果包括，即使在没有历史数据的情况下，也能在两分钟内准确预测电池的剩余使用寿命。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to support the sustainability of lithium-ion battery (LIB) technologies. LIB use is growing and has consequently led to the potential of increased battery waste. The Phase II project will develop novel diagnostic technologies that enable automakers and energy storage providers to quickly and accurately measure how their batteries perform and degrade in the field. It will further use machine learning to develop more accurate battery models and predictive health algorithms for field applications. These algorithms will have the capability to make health predictions even without historical information for the specific system, and the hardware will be portable for different applications. A more accurate assessment of battery degradation in real time can inform on-board algorithms, improve overall battery pack efficiency, and reduce costs. This Small Business Innovation Research Phase II project addresses the challenge of measuring and predicting degradation of large-format batteries, blending new hardware with machine learning and electrochemistry. The project will conduct a comprehensive battery aging study to quantify leading and lagging indicators of battery degradation. Leading indicators include utilization, calendar aging, and environmental effects, and lagging indicators consist of AC impedance, DC internal resistance, and a battery’s specific charge/discharge patterns. Anticipated results include the ability to accurately predict the remaining useful life of a battery in under two minutes, even in the absence of historical data.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.