Lithium ion battery residual capacity estimation method, apparatus and device, and storage medium

Abstract

The invention relates to a lithium ion battery residual capacity estimation method and device, equipment and a storage medium in the technical field of lithium ion batteries. The method comprises the steps of obtaining experimental measurement values of a plurality of lithium ion batteries, extracting a capacity increment wave crest from a result obtained by fitting the measurement values by adopting an SVM mode, performing preliminary capacity prediction by adopting the SVM, an LSTM network and a GRP, and then taking the preliminary capacity prediction as input, and performing fusion by utilizing a random forest algorithm to obtain capacity output. According to the method, the advantages of the SVM in nonlinearity and high-dimensional space fitting, the GRP in uncertainty prediction and the LSTM network in time sequence prediction are combined, the interference of voltage acquisition noise on the capacity increment curve is effectively solved, and the difficulty of effectively extracting the characteristics of the capacity increment curve is solved. Meanwhile, the random forest algorithm is adopted to estimate the battery capacity, and the defect that a single machine learning algorithm is prone to falling into local optimum is overcome.

Description

technical field [0001] The present application relates to the technical field of lithium ion batteries, and in particular, to a method, apparatus, device and storage medium for estimating the remaining capacity of a lithium ion battery. Background technique [0002] Lithium-ion batteries are a clean and efficient energy storage system that has been widely promoted in electric vehicles. However, due to the material properties of Li-ion batteries, their capacity inevitably deteriorates gradually. Therefore, accurate monitoring of the remaining capacity of Li-ion batteries not only contributes to the estimation and improvement of the state of health and state of charge, but also plays a crucial role in ensuring the reliable operation of electric vehicles. [0003] With the development of computer science, machine learning methods are gradually introduced into the problem of capacity estimation. In machine learning methods, capacity is estimated by mapping the underlying nonli...

AI Technical Summary

Problems solved by technology

Although these methods can achieve capacity estimation, they are all based on a single learner, which tends to trap the estimation result into a local optimum, thus limiting the fidelity of capacity estimation.

Images