Battery state of health estimation method and system driven by data fusion quantum optimization
By combining convolutional neural networks with gated recurrent units and using an improved quantum particle swarm optimization algorithm to optimize the battery health state estimation model, the efficiency and accuracy problems of battery health state estimation and prediction in existing technologies are solved, and intelligent management of the battery management system is realized.
CN120142942BActive Publication Date: 2026-07-10SHANDONG UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2025-02-27
- Publication Date
- 2026-07-10
Smart Images
Figure CN120142942B_ABST
Abstract
The application provides a battery state of health estimation method and system driven by data fusion quantum optimization, and the application constructs a battery state of health estimation and prediction model, introduces a dynamic decreasing strategy of a contraction-expansion factor into a quantum particle swarm optimization algorithm, trains the model by using a training set, and optimizes the battery state of health estimation and prediction model by using an improved quantum particle swarm optimization algorithm in the training process; the model is verified by using a test set; a target battery data set is acquired, constant-current charging time, constant-voltage charging time and internal resistance in a battery charging process are selected as input features, and are preprocessed, then the battery state of health estimation and prediction model that passes the verification is used to estimate and predict the target battery state of health, and estimation and prediction results are obtained. The application can realize efficient and accurate current SOH estimation and future SOH prediction of a battery simultaneously.
Need to check novelty before this filing date? Find Prior Art