System and method for simulating and predicting state of energy storage battery based on digital twinning

By constructing a multi-level, multi-dimensional virtual mapping body based on digital twins and integrating physical mechanism models with data-driven methods, the problems of inaccurate state modeling and uninterpretable predictions of energy storage battery systems are solved. This achieves high-precision real-time state perception and dynamic simulation, supports unified virtual mapping of multi-granularity states, and improves the intelligence and safety of the system.

CN121615530AActive Publication Date: 2026-03-06SHANDONG ELECTRIC TIMES ENERGY TECH CO LTD +1
8 Cites 10 Cited by

Patent Information

Application Number
CN202610148550.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-03
Publication Date
2026-03-06
Estimated Expiration
2046-02-03

AI Technical Summary

Technical Problem

Existing energy storage battery systems suffer from inaccurate state modeling, insufficient sensing granularity, uninterpretable predictions, and delayed responses, making it difficult to achieve high precision and real-time response under complex operating conditions.

Method used

By employing a multi-level, multi-dimensional virtual mapping based on digital twins, and integrating physical mechanism models with data-driven methods, a multi-scale digital twin model is constructed. Combining electrical, thermal, and aging sub-models, a dual-frequency strategy and extended Kalman filtering are used to update model parameters. Adaptive gating parameters and residual compensation mechanisms are introduced to achieve high-precision state estimation and trend prediction.

Benefits of technology

It achieves high-precision real-time state perception and dynamic simulation under complex operating conditions, supports unified virtual mapping of multi-granularity states, has long-term evolution capabilities, provides interpretable prediction results and intelligent early warning, and improves the intelligence and safety of energy storage battery systems.

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

Abstract

The invention provides an energy storage battery state simulation and prediction system and method based on digital twinning, and aims to solve the problems that an existing energy storage system is inaccurate in state modeling, insufficient in sensing granularity, unexplained in prediction, lagged in response and the like. According to the method, an equivalent thermal model, an electrochemical model and an aging mechanism model are adopted for modeling a battery, and a self-adaptive gating parameter fusion mechanism and data characteristics are introduced, so that cross-scale state mapping and characteristic reconstruction from a battery cell to a system level are realized; generating a baseline trajectory by using an electric-thermal-aging coupling relationship, realizing multi-time-domain closed-loop prediction by combining a data-driven residual correction mechanism, and identifying potential faults and risks in advance through a multi-time-domain anomaly judgment system; and constructing a three-dimensional topology model to dynamically display the state parameters, generating a graded alarm signal and providing operation suggestions. The system constructed by the invention has high precision, interpretability and prediction and visualization capabilities, and can significantly improve the intelligent operation and maintenance level of the energy storage battery system.
Need to check novelty before this filing date? Find Prior Art