| 42 | 0 | 43 |
| 下载次数 | 被引频次 | 阅读次数 |
锂电池在新能源汽车、电网储能电站等领域已实现规模化应用，但是锂电体系的热稳定性脆弱仍是制约其安全应用的瓶颈问题。锂电池安全阀爆开时产生的音频，可对热失控过程实现提前预警。提出了一种基于音频特征识别的锂电池热失控监测方法，首先使用变分模态分解与小波阈值协同去噪；然后融合传统梅尔频率倒谱系数与时域统计特征进行提取；最后采用贝叶斯优化支持向量机模型进行模式识别。实验结果表明，所提出的方法对三元锂电池和磷酸铁锂电池的安全阀音频信号的识别效果较好，识别准确率可达94.32%，可为锂电池热失控预警提供参考。
Abstract：Lithium-ion batteries have been widely used in new energy vehicles and grid energy storage stations.However,the poor thermal stability of lithium battery systems remains a major challenge limiting their safe application.The acoustic signal generated when the safety valve of a lithium-ion battery bursts can provide an early warning of the thermal runaway process.In this study, a monitoring method for lithium-ion battery thermal runaway audio feature recognition is proposed.First, variational mode decomposition(VMD)combined with wavelet thresholding is employed for collaborative denoising.Then,traditional Mel-frequency cepstral coefficients(MFCCs) are fused with time-domain statistical features for feature extraction.Finally,a Bayesian-optimized support vector machine(SVM)model is adopted for pattern recognition.Experimental results demonstrate that the proposed method achieves effective recognition of safety valve acoustic signals from ternary lithium batteries and lithium iron phosphate batteries,with a recognition accuracy of up to 94.32%.The proposed method provides a promising approach for the early warning and monitoring of lithium-ion battery thermal runaway.
[1]杨坤，雷洪钧，肖博文，等.锂离子电池热失控机理分析与解决策略[J].江汉大学学报（自然科学版），2020,48(5):14-20.
[2]曹洪祥，邱子健.锂离子电池热失控安全预警方法研究进展[J].广东化工，2025,52(9):77-79.
[3]Azuaje-Berbec B J,Ertan H B. A model for the prediction of thermal runaway in lithium-ion batteries[J].Journal of Energy Storage,2024,90:111831.
[4]吕娜伟.基于动态阻抗的锂离子电池安全预警方法研究[D].郑州：郑州大学，2021.
[5]郭童吉.基于电-热-老化耦合模型的锂电池热失控预警方法研究[D].兰州：兰州理工大学，2023.
[6]皇甫趁心.动力锂电池火灾热失控早期探测技术及装置开发[D].泉州：华侨大学，2018.
[7]He X,Du J,Yang S,et al. Research on overcharge thermal runaway behavior analysis and early warning algorithm of ternary lithium battery pack[J]. Journal of Applied Electrochemistry,2025,55(2):273-288.
[8]郑志坤.磷酸铁锂储能电池过充热失控及气体探测安全预警研究[D].郑州：郑州大学，2020.
[9]刘宝泉，曹小雨.锂电池热失控早期典型气体精准检测方法[J].储能科学与技术，2024,13(6):1995-2009.
[10]迟诚，贾璐阳.多参数耦合的锂离子电池热失控监测预警技术[J].自动化应用，2024,65(17):91-94,100.
[11]戴明威，张春富，杨佳武.基于多特征融合的锂电池热失控预警方法[J].南方能源建设，2025,12(2):128-133.
[12]叶祥虎.储能磷酸铁锂电池组热失控早期探测方法及灭火装置研究[D].泉州：华侨大学，2023.
[13]蒋建杰，楼平，徐国华，等.基于预测误差的锂离子电池热失控预警方法研究[J].储能科学与技术，2024,13(11):4187-4197.
[14]刘瑶秋，赵苗苗.基于融合算法的电池热失控预警方法研究[J].汽车电器，2024,65(5):14-17.
[15]Wei Y,Wang Z,Ouyang D,et al. Analysis and prediction of thermal runaway propagation interval in confined space based on response surface methodology and artificial neural network[J]. Journal of Energy Storage,2022,55:105822.
[16]Yan P,Li S,Wang X,et al. Research on thermal runaway early warning algorithm of lithium battery based on improved particle swarm algorithm optimized BP neural network[C]∥Journal of Physics:Conference Series.IOP Publishing,2024,2816(1):012032.
[17]Su T,Lyu N,Zhao Z,et al. Safety warning of lithium-ion battery energy storage station via venting acoustic signal detection for grid application[J]. Journal of energy storage,2021,38:102498.
[18]Teng J,Zhang Y,Ma C,et al. The early warning for overcharge thermal runaway of lithium-ion batteries based on a composite parameter[J]. Journal of Power Sources,2023,555:232393.
[19]肖剑，张现国，宋烨，等.基于参数优化VMD的心率检测去噪算法[J].现代雷达，2025,47(6):46-55.
[20]万桂军，黎剑安，冯东明.基于变分模态分解和分段多项式截断奇异值分解的桥梁影响线识别[J].浙江大学学报（工学版），2025,59(3):460-468.
[21]Ge L,Yuan X F,Xiao X T,et al. Acoustic location echo signal extraction of buried non-metallic pipelines based on EMD and wavelet threshold joint denoising[J]. Journal of Measurement Science and Instrumentation,2024,15(4):417-431.
[22]张云龙，夏云霞，闰金明，等.基于小波阈值算法的桥梁结构健康监测信号去噪研究[J].青岛理工大学学报，2025,46(3):9-16,71.
[23]朱宇坤，黎恒，吴文俊，等.基于BO-WT-VMD组合模型的钢丝绳的损伤信号降噪方法[J].江汉大学学报（自然科学版），2024,52(1):43-54.
[24]宋恩哲，朱仁杰，靖海国，等.噪声背景下梅尔频率倒谱系数与多注意力网络在电机故障诊断中的应用[J].哈尔滨工程大学学报，2025,46(3):475-485.
[25]刘旭东，王坤侠.融合MFCC和Wav2vec特征的对话情感识别方法[J].湖南工业大学学报，2025,39(6):29-36.
[26]陈剑，姜涛，陈品.基于声信号的离心泵故障诊断研究[J].电子测量与仪器学报，2024,38(5):169-177.
[27]田野，张晓灿，汤跃忠.基于多分类器融合决策的车辆鸣笛声识别方法[J].电声技术，2022,46(7):85-87,96.
[28]朱鑫宇，徐思远，肖红亮，等.基于贝叶斯优化的自适应循环发动机性能寻优控制[J].航空动力学报，2025,40(7):497-507.
[29]朱鸿章，吴传平，周天念，等.磷酸铁锂和三元锂电池外部过热条件下的热失控特性[J].储能科学与技术，2022,11(1):201-210.
[30]徐远健，李英东，陈轲鼎，等.高镍三元锂离子电池热失控实验及动力学参数分析[J].江汉大学学报（自然科学版），2025,53(1):5-13.
基本信息:
DOI：10.16389/j.cnki.cn42-1737/n.2026.04.003
中图分类号:TN912.3;TM912
引用信息:
[1]闫浩杰,谢家乐,史庆武.基于音频特征识别的锂电池热失控监测方法[J].江汉大学学报(自然科学版),2026,54(04):26-36.DOI:10.16389/j.cnki.cn42-1737/n.2026.04.003.
基金信息:
国家自然科学基金项目（52207235）
2026-07-02
2026-07-02
2026-07-02