Lithium battery life prediction method based on combination of multilevel feature fusion and time sequence modeling

Through the method of combining multi-level feature fusion and timing modeling, one-dimensional convolutional neural network, Transformer and bidirectional long-term short-term memory network are used to solve the long-range dependence and data robustness problems in lithium-ion battery life prediction, and high-precision battery degradation process modeling and prediction are achieved, suitable for electric vehicles and power energy storage systems.

CN120562284APending Publication Date: 2025-08-29SOUTHEAST UNIV
0 Cites 12 Cited by

Patent Information

Application Number
CN202510670207.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-23
Publication Date
2025-08-29

AI Technical Summary

Technical Problem

Existing lithium-ion battery life prediction methods have challenges in long-range dependency modeling and data quality and robustness, making it difficult to effectively capture the complex degradation process of the battery, especially inadequate prediction stability under context dependence and noise interference over a long span.

Method used

Using a method of combining multi-level feature fusion and timing modeling, local features are extracted through a one-dimensional convolutional neural network, Transformer's multi-headed self-attention structure is used to perform global feature fusion, and a bidirectional long and short-term memory network is designed to capture the dynamic evolutionary characteristics of the battery state. Finally, the remaining service life of the battery is output through a fully connected mapping, and the mean square error is used as a loss function for training.

Benefits of technology

It improves the modeling accuracy and prediction robustness of the complex degradation process of the battery, enhances the memory ability of the long-term evolution mode of the time series, reduces the sensitivity to a single prediction starting point, and is suitable for battery health monitoring and intelligent prediction in electric vehicles and power energy storage systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a multi-level feature fusion and time sequence modeling combined lithium battery life prediction method, and relates to the technical field of lithium ion battery health management and life prediction. The method comprises the steps of receiving time sequence observation data in a battery operation process, inputting the time sequence observation data into a pre-constructed local feature extraction model, and introducing a one-dimensional convolutional neural network into the local feature extraction model to perform feature extraction on the time sequence observation data to obtain local feature representation. According to the method, three structures of local feature extraction, global context modeling and bidirectional time sequence modeling are fused, and the battery degradation modeling capability and prediction precision are effectively improved. The TFN adopts an end-to-end architecture design, has good feature perception capability and time-dependent modeling capability, and can adapt to various degradation modes and complex time sequence environments. The method is suitable for life evaluation and health state monitoring in an intelligent battery management system, and has relatively high practical value and popularization prospect.
Need to check novelty before this filing date? Find Prior Art