Warren-Vega Walter M, Zárate-Guzmán Ana I, Carrasco-Marín Francisco, Ramos-Sánchez Guadalupe, Romero-Cano Luis A
Grupo de Investigación en Materiales y Fenómenos de Superficie, Departamento de Biotecnológicas y Ambientales, Universidad Autónoma de Guadalajara, Av. Patria 1201, C.P., Zapopan 45129, Mexico.
Unidad de Excelencia Química Aplicada a Biomedicina y Medioambiente, Materiales Polifuncionales Basados en Carbono (UGR-Carbon), Departamento de Química Inorgánica, Facultad de Ciencias, Universidad de Granada (UEQ-UGR), 18071 Granada, Spain.
Materials (Basel). 2024 Aug 24;17(17):4193. doi: 10.3390/ma17174193.
Traditionally, the performance of sodium-ion batteries has been predicted based on a single characteristic of the electrodes and its relationship to specific capacity increase. However, recent studies have shown that this hypothesis is incorrect because their performance depends on multiple physical and chemical variables. Due to the above, the present communication shows machine learning as an innovative strategy to predict the performance of functionalized hard carbon anodes prepared from grapefruit peels. In this sense, a three-layer feed-forward Artificial Neural Network (ANN) was designed. The inputs used to feed the ANN were the physicochemical characteristics of the materials, which consisted of mercury intrusion porosimetry data (S and average pore), elemental analysis (C, H, N, S), I/I ratio obtained from RAMAN studies, and X-ray photoemission spectroscopy data of the C, N and O regions. In addition, two more inputs were added: the cycle number and the applied C-rate. The ANN architecture consisted of a first hidden layer with a sigmoid transfer function and a second layer with a log-sigmoid transfer function. Finally, a sigmoid transfer function was used in the output layer. Each layer had 10 neurons. The training algorithm used was Bayesian regularization. The results show that the proposed ANN correctly predicts (R > 0.99) the performance of all materials. The proposed strategy provides critical insights into the variables that must be controlled during material synthesis to optimize the process and accelerate progress in developing tailored materials.
传统上，钠离子电池的性能是基于电极的单一特性及其与比容量增加的关系来预测的。然而，最近的研究表明，这一假设是不正确的，因为它们的性能取决于多个物理和化学变量。基于上述原因，本通讯展示了机器学习作为一种创新策略，用于预测由葡萄柚皮制备的功能化硬碳阳极的性能。从这个意义上说，设计了一个三层前馈人工神经网络（ANN）。用于输入ANN的是材料的物理化学特性，包括压汞孔隙率数据（S和平均孔径）、元素分析（C、H、N、S）、拉曼研究获得的I/I比以及C、N和O区域的X射线光电子能谱数据。此外，还增加了另外两个输入：循环次数和应用的C倍率。ANN架构由具有sigmoid传递函数的第一隐藏层和具有对数sigmoid传递函数的第二层组成。最后，在输出层使用sigmoid传递函数。每层有10个神经元。使用的训练算法是贝叶斯正则化。结果表明，所提出的ANN能够正确预测（R>0.99）所有材料的性能。所提出的策略为材料合成过程中必须控制的变量提供了关键见解，以优化该过程并加速定制材料开发的进展。
