| 熊学涛,张艳辉,黄崇亨,冯威,李晓宇.动态信息熵电动卡车锂电池故障检测[J].电子测量与仪器学报,2025,39(12):1-9 |
| 动态信息熵电动卡车锂电池故障检测 |
| Dynamic information entropy for lithium batteryfault detection in electric trucks |
| |
| DOI： |
| 中文关键词: 重型电动商用车 动态自编码器 信息熵 模型可解释性 多模态解耦 |
| 英文关键词:heavy-duty electric commercial vehicles dynamic autoencoder information entropy model interpretability multimodal decoupling |
| 基金项目:国家自然科学基金委面上项目(52177219)、广东省基础与应用基础研究基金（2023A1515240014）、深圳市科技计划重点项目（JCYJ20220818103416035）资助 |
|
|
| Author | Institution |
| Xiong Xuetao | 1.College of Mechanical and Control Engineering, Guilin University of Technology, Guilin 541006，China;
2.Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518067，China |
| Zhang Yanhui | Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518067，China |
| Huang Chongheng | College of Mechanical and Control Engineering, Guilin University of Technology, Guilin 541006，China |
| Feng Wei | Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518067，China |
| Li Xiaoyu | Shenzhen University, Shenzhen 518066，China |
|
| 摘要点击次数: 836 |
| 全文下载次数: 590 |
| 中文摘要: |
| 锂离子电池驱动的卡车作为重型电动商用车辆领域的新兴类别，其深度应用对我国加速交通运输领域“双碳”目标落地具有重要意义。然而，重型电动商用车在大电流充电过程中存在电池状态误报问题，引发不必要的停机，故障诊断准确性和运营效率低的问题。为解决上述问题，提出了一种基于卷积神经网络（CNN）、长短期记忆网络（LSTM）和动态自编码器（DYAD）融合的电池故障检测方法，用于解决电池状态变化与累积故障效应问题。采用编码器-解码器架构，利用CNN提取电池数据的空间特征，通过LSTM网络捕捉时间序列的动态演化规律，并借助DYAD信息熵处理电池系统的非线性特性，从而实现对复杂故障模式的深度学习。模型架构通过CNN与LSTM的融合，有效提取了时空特征，引入多模态解耦技术实时监测关键特征误差，并结合全局可解释性分析与潜在空间可视化，显著提升了模型可信度与透明度。实验结果表明，该方法在真实数据集上达到了88.7%的受试者工作特征曲线下面积（AUROC），相比图动态网络（GDN）提升26.2%；通过重构误差分析，显著减少了因大电流充电事件引发的虚假报警，并实现了故障早期检测。 |
| 英文摘要: |
| Lithium-ion battery-powered trucks, as an emerging category in the field of heavy-duty electric commercial vehicles, their in-depth application is of great significance for China to accelerate the implementation of the “dual carbon” goals in the transportation sector. However, heavy-duty electric commercial vehicles have the problem of false battery status alarms during high-current charging, which leads to unnecessary shutdowns, low accuracy in fault diagnosis and low operational efficiency. To address the above issues, this paper proposes a battery fault detection method based on the fusion of convolutional neural network (CNN), long short-term memory network (LSTM), and dynamic autoencoder (DYAD), which is used to solve the problems of battery state changes and cumulative fault effects. The encoder-decoder architecture is adopted. The spatial features of battery data are extracted by CNN, the dynamic evolution law of time series is captured by LSTM network, and the nonlinear characteristics of the battery system are processed with DYAD information entropy, thereby achieving deep learning of complex fault modes. The model architecture effectively extracts spatio-temporal features through the integration of CNN and LSTM, introduces multimodal decoupling technology to monitor key feature errors in real time, and combines global interpretability analysis and potential spatial visualization, significantly enhancing the credibility and transparency of the model. The experimental results show that this method achieves an area under the receiver operating characteristic curve (AUROC) of 88.7% on the real dataset, which is 26.2% higher than that of the graph dynamic network (GDN). By reconstructing error analysis, false alarms caused by high-current charging events have been significantly reduced, and early fault detection has been achieved. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
