基于鹈鹕优化和极限学习机的锂离子电池健康状态估计

State of health estimation of lithium-ion battery based on Pelican optimization algorithm and Extreme learning machine

准确估计锂离子电池的健康状态(State of Health,SOH)对储能系统的安全稳定运行至关重要。针对传统估计方法准确度较低的问题,提出一种基于鹈鹕优化算法和极限学习机(POA-ELM)的SOH估计方法。首先,选取充放电过程中的四个健康特征,并采用皮尔逊相关性分析来量化它们与电池SOH的相关性。然后,建立ELM模型来映射健康特征与电池SOH之间的关系。针对ELM模型中超参数寻优问题,采用POA算法进行解决。最后在NASA电池数据集上进行试验分析,并与其他经典超参数寻优算法进行了比较。实验结果表明该方法能够实现SOH的准确估计,具有较高的估计准确度,估计误差稳定在2%以内。

Accurately estimating the state of health(SOH)of lithium-ion batteries is crucial for the safe and stable operation of energy storage systems.A SOH estimation method based on Pelican optimization algorithm and extreme learning machine(POA-ELM)is proposed to address the problem of low accuracy in traditional estimation methods.Firstly,select four health characteristics during the charging and discharging process,and use Pearson correlation analysis to quantify their correlation with battery SOH.Then,establish an ELM model to map the relationship between health features and battery SOH.The POA algorithm is used to solve the hyperparameter optimization problem in the ELM model.Finally,experimental analysis was conducted on the NASA battery dataset and compared with other classic hyperparameter optimization algorithms.The experimental results show that this method can achieve accurate estimation of SOH with high estimation accuracy,and the estimation error is stable within 2%.