Prediction of battery capacity based on improved model of support vector regression

Abstract

The state of Health (SOH) of new energy lithium batteries is an important indicator to describe the energy decline of new energy, especially the battery decline. It is very important for the service life of new energy equipment, especially equipment based on a lithium battery. Its internal is a high-dimensional nonlinear complex chemical reaction. In this paper, the state of Health (SOH) of a lithium battery is defined according to the capacity to turn the problem of new energy battery capacity into a new problem. At the same time, the multi-dimensional complex nonlinear regression problem is mapped into the physical space, which is described by the phenomenon of the combined action of the quantum radiation field and the quantum gravitational repulsion force in the physical space, and the corresponding quantum radiation equation and abstract equation are used. Finally, the NASA Ames Research Center battery data set is used to verify the results. The verification shows that the algorithm can accurately predict the capacity of the battery to know the SOH of the battery. The model has good learning accuracy, operation speed, and generalization ability.