Python(编程语言)
残余物
计算机科学
源代码
电池(电)
荷电状态
原始数据
绘图(图形)
国家(计算机科学)
实时计算
模拟
编码(集合论)
数据结构
数据挖掘
电气工程
工程类
功能(生物学)
代码生成
人工智能
标识
DOI:10.5281/zenodo.15606246
摘要
Data and code for paper "Mechanistic Leading Residual Learning for Battery State Monitoring Entire Full Life" Please cite our paper (Y. Che, Y. Zheng, J. Rhyu, J. Guo, S. Wang, R. Teodorescu, R.D. Braatz, Mechanistic Leading Residual Learning for Battery State Monitoring Entire Full Life, Nature Communications, 2025) if the data or code is used. Source data: Data for main results generation figure_source_data: Code for generating the main results based on the Source data The raw data for the results are provided below: OCV_data: OCV data for the prismatic cell cell_data: Cycling data for the prismatic cell MGLocv: OCV data for the pouch cell pouch_cells: Cycling data for the pouch cell code: Python codes for the developed residual learning in battery state monitoring, which can be used to generate all the results in this paper. The versions of the packages are listed below: python -- v 3.8.20 numpy -- v 1.22.2 shap -- v 0.44.1 (The new version above 0.50 will return the shap values with different shapes. So please revise the plot function to the correct shape if you use the newest version) scikit-learn -- v 1.0.2 pandas -- v 1.4.1 scipy -- v 1.5.4 seaborn -- v 0.13.2 configargparse -- v 1.7 matplotlib -- v 3.9.2
科研通智能强力驱动
Strongly Powered by AbleSci AI