Physics-Informed Machine Learning for Degradation Diagnostics of Lithium-Ion Batteries
Physics-Informed Machine Learning for Degradation Diagnostics of Lithium-Ion Batteries
复制标题
DOI：
10.1115/detc2021-71407
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Adam Thelen;Y. Lui;Sheng Shen;S. Laflamme;Shan Hu;Chao Hu
中科院分区：
文献类型：
--
作者：
Adam Thelen;Y. Lui;Sheng Shen;S. Laflamme;Shan Hu;Chao Hu
锂离子电池的健康状态(SOH)估计通常集中在估计相对于初始电池容量的当前电池容量。虽然在这一领域已经取得了许多成功，但通常更有利的是不仅估计小区容量，而且估计导致容量衰落的潜在退化模式，因为这些模式为最大化小区利用率提供了进一步的洞察。在估计细胞降解模式方面已经取得了一些成功，然而，这些方法要么需要长期的降解数据，要么仅在人工构建的细胞上得到证实，要么在估计生命后期的降解时表现出很高的误差。为了解决这些不足并缓解对长期循环数据的需求，我们提出了一种方法，用于估计电池单元的容量并使用有限的早期寿命退化数据诊断其主要退化机制。该方法使用基于物理的半电池模型的模拟数据和16个电池在两种温度和C速率下循环的早期寿命退化数据来训练机器学习模型。四次交叉验证研究的结果表明，仅用60个早期生命数据(12个训练单元每个训练单元5个数据)和30个高退化模拟数据训练的物理信息型机器学习方法，与仅基于早期实验数据训练的模型相比，估计误差可降低高达9.77均方根误差%。
State of health (SOH) estimation of lithium-ion batteries has typically been focused on estimating present cell capacity relative to initial cell capacity. While many successes have been achieved in this area, it is generally more advantageous to not only estimate cell capacity, but also the underlying degradation modes which cause capacity fade because these modes give further insight into maximizing cell usage. There have been some successes in estimating cell degradation modes, however, these methods either require long-term degradation data, are demonstrated solely on artificially constructed cells, or exhibit high error in estimating late-life degradation. To address these shortfalls and alleviate the need for long-term cycling data, we propose a method for estimating the capacity of a battery cell and diagnosing its primary degradation mechanisms using limited early-life degradation data. The proposed method uses simulation data from a physics-based half-cell model and early-life degradation data from 16 cells cycled under two temperatures and C rates to train a machine learning model. Results obtained from a four-fold cross validation study indicate that the proposed physics-informed machine learning method trained with only 60 early life data (five data from each of the 12 training cells) and 30 high-degradation simulated data can decrease estimation error by up to a total of 9.77 root mean square error % when compared to models which were trained only on the early-life experimental data.