A lithium battery thermal runaway early warning method based on a thermally induced sound-producing material

By coating the surface of lithium batteries with thermally expanding microcapsules and combining distributed sound acquisition with lightweight convolutional neural networks, the spatial blind spot and time lag problems of lithium battery thermal runaway early warning are solved, realizing very early warning and accurate identification of lithium battery thermal runaway.

CN122246315APending Publication Date: 2026-06-19CHINA UNIV OF MINING & TECH
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA UNIV OF MINING & TECH
Filing Date
2026-05-14
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing lithium battery thermal runaway early warning technologies suffer from spatial coverage blind spots, time response lag, and weak anti-interference capabilities, making it difficult to provide effective early warnings before the thermal runaway critical point.

⚗Method used

A distributed sound acquisition and early warning method based on a thermoacoustic response layer and a lightweight convolutional neural network is adopted. By covering the battery surface with thermal expansion microcapsules, high-frequency pulse sound wave signals are acquired and identified in real time. Combined with the signal processing of the lightweight convolutional neural network, the accurate identification and early warning of early thermal anomalies can be achieved.

🎯Benefits of technology

Breaking through the spatial blind spots and time lag of traditional perception, it achieves extremely early warning of lithium battery thermal runaway, broadens the time window for safe escape and emergency response, and has high anti-interference capability and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

This invention provides an early warning method for thermal runaway in lithium batteries based on thermoacoustic materials, belonging to the field of battery safety monitoring technology. First, a thermoacoustic response layer containing thermally expanding microcapsules is coated on the surface of a single battery cell. When a local abnormal temperature rises to a preset threshold, the microcapsules undergo transient brittle fracture, releasing specific high-frequency pulsed sound waves. Second, the gaps between the cells are used as parallel-plate acoustic waveguides, and mixed sound waves are collected in real time via a MEMS microphone array. The audio is converted into a Log-Mel spectrogram and input into a lightweight convolutional neural network. Depthwise separable convolution is used to extract acoustic features, and an adaptive loss function is combined to accurately extract weak signals from complex background noise. Finally, confirmation is performed based on time-density integral logic, triggering a BMS-based shutdown mechanism. This invention deeply integrates passive physical phase transitions with AI recognition, achieving "very early, highly accurate, and comprehensive" proactive warning before the thermal runaway critical point.
Need to check novelty before this filing date? Find Prior Art