电池测试循环的代理模型训练
Application ID: 130291
This app demonstrates the usage of a surrogate model function for predicting the cell voltage, cell open circuit voltage and internal resistance of an NMC111/graphite battery cell undergoing a battery test cycle.
The surrogate function, a Deep Neural Network, has been fitted to a subset of the possible input data values. Five input data values can be set: the current in four segments of the cycle and the initial state of charge of the battery cell. The low computational cost of evaluating the surrogate function allows knobs to be used to interactively combine the input values and predict the cell voltage and internal resistance.
Once a combination of values has been selected, the prediction of the surrogate model can be verified by computing the actual physical Li-ion battery model.
案例中展示的此类问题通常可通过以下产品建模:
您可能需要以下相关模块才能创建并运行这个模型，包括：
建模所需的 COMSOL® 产品组合取决于多种因素，包括边界条件、材料属性、物理场接口及零件库，等等。不同模块可能具有相同的特定功能，详情可以查阅技术规格表，推荐您通过免费的试用许可证来确定满足您的建模需求的正确产品组合。如有任何疑问，欢迎咨询 COMSOL 销售和技术支持团队，我们会为您提供满意的答复。