Method for predicting state of charge of vehicle-mounted lithium ion battery based on random forest model

The invention discloses a method for predicting the state of charge (SOC) of a vehicle-mounted lithium ion battery based on a random forest model. The method comprises the steps of: collecting external characteristic parameters, used for predicting the SOC, of the lithium ion battery in the discharging process of the lithium ion battery of an electric vehicle; establishing a random forest system model of different input characteristic parameters according to the collected data sets of different characteristic parameters; establishing a training set and a test set of random forest models of different input parameters by using the random forest system model; utilizing the training set and the test set of the random forest model to establish prediction models of different input parameters for estimating the state of charge of the lithium ion battery; and according to the random forest prediction models of different parameters, carrying out precision analysis on prediction values, and determining an optimal solut