A fault diagnosis and early warning method for a power battery intelligent thermal management system

By constructing a dynamic spatiotemporal neural field model and a dual-channel verification mechanism, the micro-short circuit faults inside the power battery are identified, solving the problems of early warning lag and false alarms/missed alarms in the existing technology. This enables early fault identification and high-accuracy early warning of the power battery, improving the safety and reliability of the battery system.

CN120816907BActive Publication Date: 2026-05-01JIANGSU JIAHE THERMAL SYST RADIATOR
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JIANGSU JIAHE THERMAL SYST RADIATOR
Filing Date
2025-08-13
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

Existing power battery thermal management systems are inadequate in identifying early and weak fault signals of thermal runaway caused by hidden defects such as micro-short circuits inside the power battery. They are unable to distinguish between true internal fault precursors and normal system dynamics or noise interference, resulting in delayed warnings and false alarms or missed alarms.

Method used

An adaptive graph neural network is used to construct a dynamic spatiotemporal neural field model. Combined with electrothermal delay analysis and a dual-channel verification mechanism, micro-short circuit signals are identified through cross-correlation delay detection and generative adversarial networks. Background noise signals are synthesized using generative adversarial networks for signal verification. Accurate early warning is achieved by combining a hierarchical response strategy.

Benefits of technology

It enables early identification and high-accuracy warning of micro-short circuit faults inside the power battery, eliminates the risk of misjudgment caused by cooling system fluctuations and sensor noise, and builds a rapid isolation closed-loop safety protection system from the risk initiation stage to the thermal runaway critical point, thereby improving the safety margin of the battery system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120816907B_ABST
    Figure CN120816907B_ABST
Patent Text Reader

Abstract

The application discloses a kind of fault diagnosis and early warning method of power battery intelligent thermal management system, and the application relates to the field of new energy automobile power battery safety technology, comprising the following sequentially executed steps: S1) based on the real-time monitoring data of distributed temperature sensor in battery module, dynamic space-time neural field model is constructed by adaptive graph neural network, and the thermal field fingerprint representing heat propagation topological pattern is generated.The fault diagnosis and early warning method of the power battery intelligent thermal management system, by constructing dynamic space-time neural field model, accurately capture sub-weak thermal anomaly signal, combined with electric heating delay analysis realizes the early identification of micro short circuit fault, solves the problem that fault precursor signal is submerged by complex working condition;Dual-channel verification mechanism relies on the dual mutual certification of physical law rigid constraint and intelligent residual feature identification, eliminates the misjudgment risk caused by cooling system fluctuation and sensor noise, improves the early warning accuracy.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Thermal runaway protection system and method for power battery

    CN117962696A

  • Multi-dimensional battery thermal runaway judgment and early warning method, device, equipment and medium

    CN119627276A