基于IC曲线的锂离子电池内短路早期诊断

Early diagnosis of internal short circuit in lithium-ion batteries based on incremental capacity curves

摘要

为提升锂离子电池内短路故障的早期检测能力,提出一种基于卷积神经网络(convolutional neural network,CNN)与长短期记忆网络(long short-term memory,LSTM)融合的内短路诊断方法。首先将电池充电过程中的电压曲线转换为容量增量(incremental capacity,IC)曲线,并利用快速傅里叶变换(fast fourier transform,FFT)对IC曲线进行平滑处理,从中提取电池内部状态变化特征,进而采用CNN提取IC曲线中的局部特征,再通过LSTM捕获长期依赖信息,最终实现内短路故障的分类检测。通过并联电阻模拟不同程度的早期内短路故障,构建包含5 000组样本的数据集。结果表明,以IC曲线为特征时,CNN-LSTM融合模型对故障等级的分类准确率达88.62%,显著优于单一模型,并能有效区分故障严重程度。该方法为电池管理系统智能故障诊断提供了有效方案。

Abstract

To address the challenges of detecting the concealed early-stage characteristics of internal short circuits (ISC) in lithium-ion batteries, and the inability of existing methods to simultaneously capture local features and model temporal evolution, this study proposes a diagnostic method based on a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) architecture. This approach aims to enhance the battery management system′s (BMS) capability to perceive and classify micro-short circuit faults of varying severities. First, leveraging the high sensitivity of incremental capacity (IC) curves to internal electrochemical phase transitions, charging voltage data is converted into IC curves to amplify subtle fault signals. A fast fourier transform (FFT) is then introduced to filter high-frequency noise generated during the differentiation process, effectively preserving key peak and valley features of the curves. Subsequently, a series CNN-LSTM network is designed, a one-dimensional CNN extracts local spatial morphological features from the IC curves, while the LSTM captures the long-term dependency rules of fault evolution over time, establishing an end-to-end fault diagnosis model. In the experiments, four fault states ranging from early-stage micro-short circuits to severe short circuits were simulated by connecting resistors of different resistance values in parallel to 18650 batteries, constructing a balanced dataset containing 5 000 samples. The results demonstrate that the proposed method achieves a test accuracy of 88.62% in the five-category classification task, with the recognition rate for severe short circuits reaching 93.5%. Comparative analysis confirms that the performance of this hybrid model is significantly superior to that of standalone CNN or LSTM networks. It effectively distinguishes the severity of internal short circuits, providing a high-precision technical solution for intelligent battery safety early warning systems.

关键词

锂离子电池 / 内短路检测 / 卷积神经网络 / 长短期记忆网络 / 容量增量曲线

Key words

lithium-ion battery / internal short-circuit detection / convolutional neural network / long short-term memory network / incremental capacity curve

[1] 黎钦懿, 杨林, 羌嘉曦. 融合内部温度估计的锂电池内短路建模与诊断[J]. 机电一体化, 2021, 27(4):31-40.
[2] 崔志仙, 王青松, 孙金华. 锂枝晶导致的锂离子电池内短路模拟研究[J]. 火灾科学, 2019, 28(2):101-112.
[3] 耿莉敏, 赵扬, 高楠, 等. 锂离子电池内短路形成机理及检测方法综述[J]. 汽车工程学报, 2023, 13(4):481-495.
[4] Xin L, Changyong J, Wei Y, et al. Mechanism, modeling, detection, and prevention of the internal short circuit in lithium-ion batteries: recent advances and perspectives[J]. Energy Storage Materials, 2021 (35):470-499.
[5] Qi X, Liu B, Pang J, et al. Unveiling micro internal short circuit mechanism in a 60 Ah high-energy-density Li-ion pouch cell[J]. Nano Energy, 2021(84):105908.
[6] Kong X, Zheng Y, Ouyang M, et al. Fault diagnosis and quantitative analysis of micro-short circuits for lithium-ion batteries in battery packs[J]. Journal of Power Sources, 2018(395):358-368.
[7] Yao Y, Du X, Jiang S, et al. Prognostics of internal short circuit in lithium-ion batteries—Literature survey and performance evaluation[J]. Journal of Power Sources, 2025(648): 237203.
[8] 耿莉敏, 赵扬, 高楠, 等. 锂离子电池内短路形成机理及检测方法综述[J]. 汽车工程学报, 2023, 13(4):481-495.
[9] Tao J, Wang S, Cao W, et al. An innovative multitask learning—Long short-term memory neural network for the online anti-aging state of charge estimation of lithium-ion batteries adaptive to varying temperature and current conditions[J]. Energy, 2025(314): 134272.
[10] 丘恒越, 田凌, 旷永红. 基于弛豫电压的锂离子电池内短路分级检测方法[J]. 广东电力, 2024, 37(7):32-41.
[11] 李志强, 刘杰, 陈慧, 等. 基于神经网络的电池故障诊断与预测[J]. 电池工业, 2018, 23 (4):78-82.
[12] Pan T, Yu Z, Ma S, et al. Detection of internal short circuit in lithium-ion batteries based on electrothermal coupling model[J]. Journal of Energy Storage, 2025(106):114685.
[13] Lai X, Ke Y, Tang X, et al. Balanced capacity-based quantitative method for detecting internal short circuits in lithium-ion battery modules[J]. Journal of Energy Storage, 2025(123):116622.
[14] 昝楠楠. 基于全局CNN与局部LSTM的国画图像分类算法[J]. 自动化技术与应用, 2024, 43(4):115-117.
[15] 王冰梅, 张冶, 李书斌, 等. 基于CNN-LSTM混合网络的新型配电网异常数据检测模型[J]. 太阳能学报, 2025, 46(5):243-250.
[16] 王飞. 基于改进CNN卷积神经网络的音乐识别模型构建[J]. 自动化技术与应用, 2024, 43(2):127-131.
[17] 高振华, 秦奋起, 王琳琳, 等. 基于改进CNN-LSTM的开关闩故障诊断方法[J]. 兵工学报, 2025, 46(9):51-60.
[18] 张莉, 李承桓, 秦美翠, 等. 基于LSTM网络优化的电力客服语音情感识别系统[J]. 自动化技术与应用, 2025, 44(10):66-69.
[19] 边楠, 耿兆杰, 张永跃, 等. 基于CNN探测电动汽车电池内部缺陷分析[J]. 北京汽车, 2022(3):39-42.
[20] 吴诗淼, 王文波, 朱婷, 等. 基于跳跃连接多尺度CNN的锂离子电池剩余寿命预测[J]. 太阳能学报, 2024, 45(7):199-208.
[21] 李轩谊, 赵慧勇. 基于LSTM的电池组工作状态预测[J]. 湖北汽车工业学院学报, 2023, 37(4):22-26, 31.
[22] 黄志礼, 蔺红. 基于LSTM与KPCA的退役动力电池分选方法[J]. 国外电子测量技术, 2023, 42(12):152-159.
[23] Gao W, Zheng Y, Ouyang M, et al. Micro-short-circuit diagnosis for series-connected lithium-ion battery packs using mean-difference model[J]. IEEE Transaction on Industrial Electronics, 2019, 66(3):2132-2142.
[24] Zhao X, Wang J, Zhao M, et al. Micro-short circuit fault diagnosis of the parallel battery module based on increment capacity curve[J]. Journal of Energy Storage, 2024(86): 111201.
[25] Xu Z, Chen Z, Yang L, et al. State of health estimation for lithium-ion batteries based on incremental capacity analysis and Transformer modeling[J]. Applied Soft Computing, 2024(165):112072.
[26] Zhang Y, Liu Y, Wang J, et al. State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression[J]. Energy, 2022(239):121986.
[27] Chen H, Yue W, Bin G, et al. Filter methods comparation for incremental capacity analysis in lithium-ion batteries health prediction[J]. Journal of Energy Storage, 2024 (101):113878.
[28] Cheng F, Liu H, Lyu X. Lithium-ion batteries remaining useful life prediction via Fourier-mixed window attention enhanced Informer with decomposition and adaptive error correction strategy[J]. Advanced Engineering Informatics, 2025(65):103292.
[29] Liu Z, Ruan G, Tian Y, et al. Application of a transformer network based on multi-scale branches and fast Fourier gating mechanism in the state of charge prediction for sodium-ion batteries[J]. Expert Systems with Applications, 2025(285):127931.
[30] Bao G, Liu X, Zou B, et al. Collaborative framework of transformer and LSTM for enhanced state-of-charge estimation in lithium-ion batteries[J]. Energy, 2025(322):135548.

基金资助

广东省基础与应用基础研究项目(2023A1515140004)