使用晶格标度的电池材料数据扩充
Data augmentation for battery materials using lattice scaling
摘要：
锂离子电池（LIB）开发的重要一步只能通过提出基于选择电池组件的最佳材料，优化电池制造，预测LIB的降解机制以及巩固受损电池的再生过程的破模研究来实现。LIB具有更长的回收寿命，更好的安全性和可重复使用的能力，将在循环经济中建立可持续的最先进的电池，具有最高的能源效率，低成本和最小的二氧化碳排放，促进电动汽车和便携式电子产品等相关领域的可持续发展。最近，人们越来越关注应用人工智能（AI）技术及其子类来更好地预测具有设计性能的新型材料。这一系列方法已经取得了相当大的成功，已被用于预测材料的许多物理性质。然而，与其他领域相比，材料数据通常要小得多，有时甚至更多样化，这无疑会影响人工智能模型的构建和有效性。目前，在材料科学中已经提出了几种基于翻转、旋转和扭曲材料单胞的数据增强（Data Augmentation，DA）方法，这些方法在增加数据量和数据质量方面非常有效。在这里，我们提出了一个更有效的新方法的数据增强的基础上晶格缩放的晶体结构。在晶格标度DA方法中，单位晶胞被扰动，以各向同性或各向异性的方式经历单位晶胞体积的增加和减少。这种转变对于电池组件特别相关，因为已经报道了基于插入的LIB在循环期间高达5%的体积变化。
英文摘要：
A significant step forward in Lithium-ion batteries (LIBs) developments can only be achieved by proposing mold-breaking research based on selecting the best materials for the cell components, optimizing cell manufacture, anticipating the degradation mechanisms of the LIBs, and consolidating the regeneration processes of damaged batteries. LIBs with longer recycling life, better safety, and the ability to be reused will establish sustainable state-of-the-art batteries with maximum energy efficiency, low costs, and minimal CO2 emissions within a circular economy, promoting sustainability in areas as relevant as electromobility and portable electronics. Recently, there has been increasing interest in applying Artificial Intelligence (AI) techniques and their subclasses to better predict novel materials with designed properties. This collection of methods has already obtained considerable success, having been used to predict numerous physical properties of materials. However, compared to other fields, the materials data are typically much smaller and sometimes more diverse, which undoubtedly affects the construction and effectiveness of AI models. At present, several Data Augmentation (DA) methods have been proposed in materials science based on flipping, rotating, and distorting the unit cells of materials, which have been demonstrated to be very efficient in increasing the size and quality of data. Here we present an even more effective new method of Data Augmentation based on the lattice scaling of crystal structures. In the lattice scaling DA method, the unit cell is perturbed, undergoing an increase and decrease of the unit cell volume in an isotropic or anisotropic way. This transformation is particularly pertinent for battery components since volume changes of up to 5% have been reported for the insertion-based LIBs during cycling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
