This study proposes an efficient estimator and uses it to estimate the health of a lithium-ion battery and a supercapacitor in the hybrid energy storage system (HESS). A new type of online health estimator that uses a fuzzy brain emotional learning neural network (FBELNN) is proposed. This neural network is different to a conventional brain emotional learning neural network where the fuzzy inference system and a new reward signal are used. The effect capacity fading on the output of energy storage components is also determined. The proposed method uses a discrete wavelet transform (DWT) and principal component analysis (PCA) to extract features from the response signal for the impulse load. The DWT-PCA can reduce the workload for feature extraction. The parameter adaptation laws and convergence analysis for the FBELNN are derived and the internal parameters for the FBELNN are optimized using a genetic algorithm (GA). A neural network estimates the capacity of a supercapacitor and lithium-ion battery in real-time to better ensure the safety of HESS. The sample set is collected from the voltage response signal in the HESS simulation platform and practical experimental platform. Simulation and experimental results show that the proposed method has a faster learning speed and is more accurate than other methods.

本研究提出了一种有效的估计器，并使用它来估计混合储能系统 (HESS) 中锂离子电池和超级电容器的健康状况。提出了一种使用模糊大脑情绪学习神经网络（FBELNN）的新型在线健康估计器。这种神经网络不同于传统的大脑情感学习神经网络，其中使用了模糊推理系统和新的奖励信号。还确定了容量衰减对储能组件输出的影响。所提出的方法使用离散小波变换 (DWT) 和主成分分析 (PCA) 从脉冲负载的响应信号中提取特征。DWT-PCA 可以减少特征提取的工作量。推导出 FBELNN 的参数适应规律和收敛分析，并使用遗传算法 (GA) 优化 FBELNN 的内部参数。神经网络实时估计超级电容器和锂离子电池的容量，以更好地确保 HESS 的安全。样本集是从HESS仿真平台和实际实验平台中的电压响应信号中采集的。仿真和实验结果表明，与其他方法相比，所提出的方法具有更快的学习速度并且更准确。样本集是从HESS仿真平台和实际实验平台中的电压响应信号中采集的。仿真和实验结果表明，与其他方法相比，所提出的方法具有更快的学习速度并且更准确。样本集是从HESS仿真平台和实际实验平台中的电压响应信号中采集的。仿真和实验结果表明，与其他方法相比，所提出的方法具有更快的学习速度并且更准确。