Joint estimation method for state of health and state of charge of lithium battery based on machine learning

Abstract

The invention relates to a joint estimation method for the state of health and the state of charge of a lithium battery based on machine learning. The method comprises the steps of determining a battery model, and fitting a V-SOC curve according to the detailed data of a charging and discharging process; establishing a lithium battery equivalent circuit model; performing parameter identification on the curve of the voltage rebound characteristic curve in a charging and discharging period to obtain a machine learning model; carrying out one-time initialization test operation during startup; fitting the voltage rebound curve in the period to obtain the ohmic resistance and polarization resistance of the current battery, measuring the environment temperature, reading the charging and discharging cycle data of the battery in the storage chip, and calculating the state of health (SOH) of the battery; and updating model parameters according to the ohmic resistance, the polarization resistance, the polarization capacitance and the maximum available capacity obtained through identification, estimating the state of charge (SOC) of the battery by using a UKF or EKF algorithm, and recording an SOC value in a storage chip. The method has the characteristics of instant updating of state equation parameters, comprehensive consideration of life influence factors, repeated use of the parameters, saving of computing resources and the like.

Description

technical field [0001] The invention belongs to the technical field of state estimation of a lithium battery management system, and in particular relates to a method for jointly estimating the state of health and the state of charge of a lithium battery based on machine learning. Background technique [0002] With the gradual depletion of non-renewable energy sources and the aggravation of the global greenhouse effect, all countries are seeking new energy technologies that are sustainable, energy-saving and environmentally friendly. As an energy-saving and environment-friendly means of transportation, new energy vehicles have attracted people's attention. The power battery on electric vehicles has the characteristics of high energy density, high safety and fast charging for the battery management system; the wind power photovoltaic industry plays an important role in the power generation market Gradually occupy a higher proportion, and because of its more prominent consumpti...

AI Technical Summary

Problems solved by technology

But in fact, with the different cycle times and environmental factors of the battery, the relationship between the battery capacity and its internal resistance will change, and the maximum available capacity of the battery will also change.

If the parameters are not adjusted in time for these changes, the estimation error of the battery state of charge and state of health will become larger and larger

Images