Battery health state prediction method based on PSO-ELM algorithm

Abstract

The invention discloses a battery health state prediction method based on a PSO-ELM algorithm. The method comprises steps of 1, establishing a neural network model based on an extreme learning machineELM; 2, initializing parameters of the neural network model, wherein a PSO algorithm is adopted to determine a connection weight w from an input layer to a hidden layer and a threshold b of the hidden layer in the neural network model; 3, training the neural network of which the parameters are determined in the step 2 by adopting a pre-obtained training sample through the ELM algorithm till a training ending condition is met; and 4, predicting a health state of a battery by adopting the trained neural network model. The method is advantaged in that a health state of the battery can be accurately and quickly predicted, and safety monitoring of the battery can be realized; input layer parameters of the model are more accurate and reliable; the neural network model is realized by adopting the extreme learning machine (ELM) algorithm so that the repeated iteration process of a traditional training method is avoided, and the training time is reduced.

Description

technical field [0001] The invention relates to the field of battery detection, in particular to a battery health state prediction method based on the PSO-ELM algorithm. Background technique [0002] The decrease of the battery state of health (State of Health, SOH) is reflected in the increase of the internal resistance of the battery. With the increase of the internal resistance of the battery, the battery will generate more heat during actual use, resulting in a decrease in the useful power of the battery. High battery temperatures also threaten the safety of battery-operated devices. The decline in battery health is also reflected in the decline in battery capacity. With the decrease in the available capacity of lithium batteries, the storage capacity of batteries may not meet the requirements of actual use scenarios. Unnecessary property loss and safety threats to equipment users. Battery health status prediction is an important task in battery management system (Batt...

AI Technical Summary

Problems solved by technology

[0002] The decrease of the battery state of health (State of Health, SOH) is reflected in the increase of the internal resistance of the battery. With the increase of the internal resistance of the battery, the battery will generate more heat during actual use, resulting in a decrease in the useful power of the battery. High battery temperature also threatens the safety of battery-operated devices

The decline in battery health is also reflected in the decline in battery capacity. With the decrease in the available capacity of lithium batteries, the storage capacity of batteries may not meet the requirements of actual use scenarios. Unnecessary property loss and security threats to equipment users

Images