A method for monitoring and locating early warning of thermal runaway in battery modules

By using an acoustic sensor array and a sparse expert hybrid acoustic recognition model, the problem of inaccurate location of thermal runaway in battery modules was solved, enabling early and accurate location and rapid response, thus improving the safety and reliability of battery energy storage systems.

CN120993216BActive Publication Date: 2026-05-26CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202511192800.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-25
Publication Date
2026-05-26
Estimated Expiration
2045-08-25

AI Technical Summary

Technical Problem

In the existing technology, it is difficult to accurately locate the thermal runaway source after the thermal runaway of the battery module occurs. Traditional temperature sensors and smoke detection systems have insufficient accuracy and response lag, and cannot accurately pinpoint the specific thermal runaway source battery or module.

Method used

By employing an acoustic sensor array and a sparse expert hybrid acoustic recognition model, and by constructing an acoustic feature library and an acoustic region division mechanism, combined with the thermal runaway propagation dynamics equation, the precise location of the thermal runaway module is achieved.

Benefits of technology

It achieves precise monitoring and location of thermal runaway in battery modules, enabling rapid identification of the thermal runaway source in the early stages, improving the targeted nature of emergency response, and maintaining high precision and anti-interference capabilities in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120993216B_ABST
    Figure CN120993216B_ABST
Patent Text Reader

Abstract

This invention provides a method for monitoring, locating, and warning of thermal runaway in battery modules, belonging to the field of battery module thermal runaway monitoring technology. This invention involves setting up multiple acoustic sensor arrays within the battery module's energy storage compartment to collect acoustic signals in real time, constructing a target acoustic event feature library including safety valve opening and battery exhaust characteristics, employing a sparse expert hybrid acoustic recognition model to intelligently identify and classify the acoustic signals, and establishing an acoustic region division mechanism based on the exhaust sound attenuation propagation equation. When a safety valve opening event is detected, the thermal runaway module is quickly located by comparing the peak values ​​of the cross-channel sound pressure level. The method continuously monitors the acoustic characteristics of battery exhaust and calculates the sound pressure level attenuation gradient, matching it with the regional acoustic feature library to achieve precise region location. Simultaneously, it predicts the diffusion path based on the thermal runaway propagation dynamics equation and dynamically adjusts the recognition model parameters, solving the technical problem of accurately locating the thermal runaway source.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Recognition model generation method, recognition method, system, equipment and medium

    CN116304639A

  • Calculation method and device based on hybrid expert model, equipment and storage medium

    CN117972293A

  • Acoustics-based battery thermal runaway early warning and positioning method, system, equipment and medium

    CN119535361A