Lithium battery RUL estimation method based on multi-feature fusion LSTM network

• Main Authors: WANG XIAOHUA, YIN LUJUN, NI NANBING, ZHOU ANRU, DAI KE
• Format: Patent
• Language: Chinese; English
• Published: 18.04.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a lithium battery RUL estimation method based on a multi-feature fusion LSTM network. The method comprises the steps that 1, a battery charging and discharging data set in a laboratory environment and a data set in a natural environment are acquired; 2, a multi-feature fusion module is established, and high-dimensional data dimension reduction, feature fusion and multi-feature reweighting are achieved; 3, establishing an LSTM network based on local and global feature combination, and extracting local features between time sequences and global features of a data overall trend; carrying out local and global feature fusion calculation to obtain a predicted value at the next moment; and 4, constructing a mean square loss function, and optimizing model parameters. According to the method, the influence of the capacity characteristic of the battery and auxiliary characteristics such as current, voltage and temperature on battery capacity prediction is fully considered, and the battery RUL pr