基于复合衰减模型与 CNN-GRU-AE 融合的锂电池健康状态估算方法

王紫仪; 武家辉; 王维庆; 丁洪帅; 张华; 杨健

引用本文:	王紫仪,武家辉,王维庆,等.基于复合衰减模型与 CNN-GRU-AE 融合的锂电池健康状态估算方法[J].电力系统保护与控制,2026,54(11):93-104.
	WANG Ziyi,WU Jiahui,WANG Weiqing,et al.State-of-health estimation method for lithium-ion battery based on a coupled degradation model and CNN-GRU-AE fusion network[J].Power System Protection and Control,2026,54(11):93-104

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 143次下载 15次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于复合衰减模型与 CNN-GRU-AE 融合的锂电池健康状态估算方法
王紫仪¹，武家辉¹，王维庆¹，丁洪帅¹，张华²，杨健²
1. 可再生能源发电与并网控制教育部工程研究中心 (新疆大学)，新疆乌鲁木齐 830047；2. 中广核新能源投资 (深圳) 有限公司新疆分公司，新疆乌鲁木齐 841100

摘要:

针对现有数据驱动电池健康状态 (state of health, SOH) 估计模型忽略电化学机理约束的问题，提出融合电化学机理约束的深度学习框架。首先，设计基于卷积神经网络 - 门控循环单元 - 自编码器 (convolutional neural network-gated recurrent unit-autoencoder, CNN-GRU-AE) 复合神经网络架构协同提取电池数据的时序特征，通过 CNN 单元提取局部退化特征得到特征向量，GRU-AE 单元捕获时序依赖关系并计算数据重构损失。其次，为了保证模型在 SOH 估计过程中符合电化学机理，将复合衰减模型嵌入整个框架，该模型集成容量线性衰减模型、活性锂非线性衰减模型与固体电解质界面膜 (solid electrolyte interphase, SEI) 生长模型。整个框架通过可微分编程同步优化神经网络权重与机理参数，结合双任务学习架构同步实现数据重构与锂离子电池 SOH 估计。最后，实验结果表明，与其他模型相比，本模型提高了锂离子电池 SOH 估计精度和鲁棒性，实现了电化学机理与数据驱动模型的深度耦合。

关键词: 锂离子电池健康状态估计复合衰减模型复合神经网络架构

DOI：10.19783/j.cnki.pspc.251156

分类号:

基金项目:新疆维吾尔自治区重点研发专项项目资助 (2022B01020-3)；新疆碳中和能源科学与技术研究项目资助 (2022TSYCLJ0001)

State-of-health estimation method for lithium-ion battery based on a coupled degradation model and CNN-GRU-AE fusion network

WANG Ziyi¹, WU Jiahui¹, WANG Weiqing¹, DING Hongshuai¹, ZHANG Hua², YANG Jian²

1. Engineering Research Center of Renewable Energy Power Generation and Grid-connected Control, Ministry of Education, Xinjiang University, Urumqi 830047, China; 2. Xinjiang Branch of CGN New Energy Investment (Shenzhen) Co., Ltd., Urumqi 841100, China

Abstract:

To address the limitation of existing data-driven models for battery state-of-health (SOH) estimation that neglect electrochemical mechanism constraints, a deep learning framework integrated with electrochemical mechanism constraints is proposed. First, a hybrid neural network architecture based on convolutional neural network-gated recurrent unit-autoencoder (CNN-GRU-AE) is designed to collaboratively extract temporal features from battery data. The CNN unit captures local degradation features to obtain feature vectors, while the GRU-AE unit models temporal dependencies and computes data reconstruction loss. To ensure consistency with electrochemical mechanisms during SOH estimation, a coupled degradation model is embedded into the framework. This model integrates a linear capacity degradation component, a nonlinear active lithium decay model, and a solid electrolyte interphase (SEI) growth mechanism. The entire framework is optimized via differentiable programming, enabling simultaneous learning of neural network weights and mechanistic parameters. Coupled with a dual-task learning architecture, it simultaneously realizes data reconstruction and lithium-ion battery SOH estimation. Finally, experimental results demonstrate that, compared to other models, the proposed model enhances both the accuracy and robustness of lithium-ion battery SOH estimation, achieving deep coupling between electrochemical mechanisms and data-driven modelling.

Key words: lithium-ion battery state-of-health estimation coupled degradation model hybrid neural network architecture

X关闭