Lithium ion battery internal short circuit detection method based on impedance spectrum and Elman neural network

• Main Authors: NIE WEI, ZHANG HAILONG, WANG YI, LUO ZHANG, YOO KI-YEOL, CHEN WENLI
• Format: Patent
• Language: Chinese; English
• Published: 03.11.2023
• Subjects: MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a lithium ion battery internal short circuit detection method based on an impedance spectrum and an Elman neural network, and the method comprises the steps: collecting the impedance spectrum data of a lithium ion battery, and extracting eight internal short circuit features based on the impedance spectrum; calculating a Pearson correlation coefficient of the internal short circuit feature, and retaining four features with relatively strong correlation; performing feature fusion on the internal short-circuit features by using canonical correlation analysis to obtain a one-dimensional comprehensive variable, and constructing an internal short-circuit feature data set based on the comprehensive variable; optimizing the Elman neural network through a particle swarm optimization algorithm; training an Elman neural network based on the internal short circuit feature data set; measuring the impedance spectrum of the to-be-detected battery, performing feature extraction and fusion, and inputt