Method and system for key predictors and machine learning for configuring cell performance
Methods and systems are provided for key predictors and machine learning for configuring cell performance. One or more parameters relating to the cell may be measured, via a measurement apparatus, with the cell including a cathode, a separator, and a silicon-dominant anode, and the cell may be managed, based on the one or more parameters, with the managing including predetermining cycle life of the cell based on the one or more parameters using a machine learning model. The cell may be within a battery pack that includes a plurality of cells. The battery pack may be in an electric vehicle. At least one parameter may be measured before a formation process of the cell. At least one parameter may be measured during the formation process. At least one parameter may be measured during cycling of the cell.
1. A method of managing battery performance, the method comprising:
providing a cell comprising a cathode, a separator, and a silicon-dominant anode;
obtaining, via a measurement apparatus, measurements of one or more parameters relating to the cell, wherein at least a portion of the measurements of at least one parameter is obtained before formation or cycling of the cell; and
managing the cell based on the one or more parameters, wherein the managing comprises determining cycle life of the cell based on the one or more parameters using a machine learning model;
wherein the measurements of the one or more parameters correspond to a plurality of different types of data, and
wherein amounts of measured data are different for at least two different types of data.
2. The method of claim 1 , wherein the one or more parameters comprise initial coulombic efficiency.
3. The method of claim 1 , wherein the one or more parameters comprise second cycle coulombic efficiency.
4. The method of claim 1 , wherein the one or more parameters comprise at least one parameter related to one or more characteristics of cell components or raw materials prior to assembly.
5. The method of claim 1 , wherein the one or more parameters comprise cell impedance values.
6. The method of claim 1 , wherein the one or more parameters comprise open-circuit voltage.
7. The method of claim 1 , wherein the one or more parameters comprise cell thickness.
8. The method of claim 1 , wherein the one or more parameters comprise impedance after degassing.
9. The method of claim 1 , further comprising measuring at least one parameter of the one or more parameters before a formation process.
10. The method of claim 1 , further comprising measuring at least one parameter of the one or more parameters during a formation process.
11. The method of claim 10 , wherein the at least one parameter comprises a voltage reached during a first 10% of a first formation cycle.
12. The method of claim 1 , further comprising measuring at least one parameter of the one or more parameters during cycling of the cell.
13. The method of claim 1 , wherein the cycle life is defined as a number of cycles to reach 60-80% of initial capacity.
14. The method of claim 1 , wherein the machine learning model utilizes one or more of the following: logistic regression, lasso regression, AdaBoost regression, AdaBoost classification, XGBoost regression, XGBoost classification, random forest regression, random forest classification, multi-layer perception, long-short-term-memory neural networks, and Bayesian networks.