摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑-机器学习的最新研究结果已经发表。根据NewsRx编辑在康涅狄格州斯托尔斯的新闻报道，研究表明，“随着锂离子电池内部部件老化，监测它们的健康状况对于优化电池设计和使用控制策略至关重要。然而，量化部件级退化通常涉及老化许多电池，并在整个测试过程中对它们进行破坏性分析，将量化退化的范围限制在测试条件和持续时间内。”我们的新闻记者从康内蒂克特大学的研究中获得了一句话，“幸运的是，物理信息机器学习(PIML)在建模和预测电池健康状态方面的最新进展表明，通过杠杆老化物理，仅使用短期老化测试数据，建立模型预测锂-I在电池主要部件上的长期退化是可行的。”本文提出了四种建立物理机器学习模型的方法,并综合比较了它们的准确性、复杂性、易实现性以及它们对未经测试条件的外推能力。我们深入研究了每种物理机器学习方法的细节。我们的研究利用了24个Impliantab LE级锂离子电池在过去几年中经受不同温度和C率的长期循环老化数据。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Machine Learn ing have been published. According to news reporting out of Storrs, Connecticut, by NewsRx editors, research stated, “Monitoring the health of lithium-ion batte ries’ internal components as they age is crucial for optimizing cell design and usage control strategies. However, quantifying component-level degradation typic ally involves aging many cells and destructively analyzing them throughout the a ging test, limiting the scope of quantifiable degradation to the test conditions and duration.” Our news journalists obtained a quote from the research from the University of C onnecticut, “Fortunately, recent advances in physics-informed machine learning ( PIML) for modeling and predicting the battery state of health demonstrate the fe asibility of building models to predict the long-term degradation of a lithium-i on battery cell’s major components using only shortterm aging test data by lever aging physics. In this paper, we present four approaches for building physicsinf ormed machine learning models and comprehensively compare them, considering accu racy, complexity, ease-of-implementation, and their ability to extrapolate to un tested conditions. We delve into the details of each physics-informed machine le arning method, providing insights specific to implementing them on small battery aging datasets. Our study utilizes long-term cycle aging data from 24 implantab le-grade lithium-ion cells subjected to varying temperatures and C-rates over fo ur years.”
NETL
NSTL