A Fusion Algorithm Based Lithium-ion Battery Remaining Life Prediction Method

Abstract

The invention relates to a method for predicting the remaining life of a lithium-ion battery based on a fusion algorithm, and belongs to the technical field of battery management. The method includes the following steps: S1: Acquire battery capacity decay data, and determine model parameters based on optimal control algorithm RUL prediction. S2: Fit the training set data, iteratively output the optimal control algorithm model parameter filtering estimated value and the battery capacity attenuation data filtering estimated value, and obtain the initial RUL predicted value through the model parameter filtering estimated value. S3: Based on the difference between the estimated filtering value of the optimal control algorithm and the experimental data, the original error sequence is established and used as the input of the neural network algorithm, the error sequence is continuously iteratively trained, and the prediction result of the error sequence is output. S4: After the training set data is used, the initial prediction value of the optimal control algorithm and the error sequence prediction result of the neural network algorithm are integrated to obtain the final lithium-ion battery RUL prediction result.

Description

technical field [0001] The invention belongs to the technical field of battery management and relates to a method for predicting the remaining life of a lithium-ion battery based on a fusion algorithm. Background technique [0002] In recent years, due to its wide application in new energy vehicles and other technological fields, lithium-ion batteries have gradually become a research hotspot in the field of new energy vehicle power batteries due to their high energy density and long cycle life. However, as the battery capacity gradually decays with the increase of the number of cycles, the performance of the battery will deteriorate, and even cause economic losses and personal injuries. Therefore, battery health monitoring based on the capacity decay of lithium-ion batteries has become an urgent problem to be solved. The remaining battery life can be defined as the number of charge and discharge cycles before the attenuation performance index of the battery reaches the spec...

AI Technical Summary

Problems solved by technology

In the first category, the use of data-driven methods to infer or compensate physical models, the use of data-driven methods to estimate predictive measurements of model-based methods, the use of data-driven methods to estimate or adjust the parameters of physical methods, the use of filtering methods These four methods estimate / adjust the parameters of the data-driven method; but none of them mentions the use of data-driven algorithms to compensate the filtering model for error compensation to achieve lithium-ion battery RUL prediction

Images