Method and system for establishing battery health state prediction model

• Main Authors: DOU HAOWEN, HUANG ZIYUE, XIE YUQING, TAN YEYU, DANG LUJUAN, CHEN BADONG
• Format: Patent
• Language: Chinese; English
• Published: 24.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention belongs to the technical field of battery management, and relates to a method and system for establishing a battery health state prediction model. According to the method, outlier processing is carried out on all battery maximum capacity data once to obtain preprocessed data; processing the preprocessed data by using a hidden layer, and dividing the processed data into training data and verification data; processing the training data through the convolutional network layer to obtain convolutional network layer processing data; processing the convolutional network layer processing data through a gating circulation unit neural network to obtain a preliminary prediction model; and inputting verification data into the preliminary prediction model to obtain an optimal prediction model. According to the method, block detail information in the battery data can be captured, the effect of coexistence of global dependence and detail capture is achieved, and the accuracy of battery health state prediction