Lithium-ion battery remaining life prediction method based on wde optimized lstm network

Abstract

The invention provides a method for predicting the remaining life of a lithium-ion battery based on a WDE-optimized LSTM network, and relates to the technical field of lithium-ion batteries. The method first constructs two sets of lithium-ion battery monitoring indicators; obtains the monitoring data of lithium-ion batteries, and extracts the monitoring indicator data and lithium-ion battery capacity data of lithium-ion batteries; The indirect prediction model for the remaining life of the ion battery; optimize the key parameters in the indirect prediction model for the remaining life of the lithium-ion battery by using the weighted differential evolution algorithm; use the optimized data to determine the optimal indirect prediction model for the remaining life of the lithium-ion battery; finally use the optimal lithium-ion battery The remaining life indirect prediction model predicts the lithium-ion battery capacity data in the later stage; the method for predicting the remaining life of the lithium-ion battery based on the WDE optimized LSTM network provided by the present invention can accurately predict the change law of the capacity data of the lithium-ion battery and effectively evaluate the remaining life of the lithium-ion battery.

Description

technical field [0001] The invention relates to the technical field of lithium-ion batteries, in particular to a method for predicting the remaining life of a lithium-ion battery based on a WDE optimized LSTM network. Background technique [0002] Lithium-ion batteries have the advantages of no memory effect, low self-discharge rate, high working voltage, high energy density and long cycle life, and have been rapidly and widely used in various fields, such as: new energy vehicles, aircraft and aviation detectors, Industrial production and uninterruptible power supply systems, etc. Lithium-ion battery remaining life prediction and health status monitoring play a vital role in the development of new energy technologies. During the use of lithium-ion batteries, with the increase of charge and discharge times, the performance degradation of lithium-ion batteries is inevitable. By effectively predicting the capacity of lithium-ion batteries, the continuous and stable developmen...

AI Technical Summary

Problems solved by technology

Although the fusion model can improve the accuracy of the prediction results to a certain extent, this type of method also has some shortcomings, such as: the fusion model has a large uncertainty and the calculation complexity is too high, so in actual use, it is still There are certain limitations, and the feasibility of this type of method still needs to be improved

Images