摘要
针对传统方法难以对不间断电源系统、微网储能系统的蓄电池组进行高效准确的状态估计问题,提出了一种全新的基于数据驱动的方法应用于大规模电池的健康状态预测。首先,分析电池的历史数据,从电池健康状态(空间维度)和时间演变放电过程(时间维度)2个层面对电池状态进行有效聚类。其次,将数据分布映射到高维空间,设计相应的基于时空分布映射的电池健康状态预测深度神经网络模型。最后,实验模型验证了所提方法的有效性。
Efficient and accurate state estimation of storage battery is of great significance for the normal operation of UPS system and microgrid energy storage system.A new data-driven method is proposed to predict the health state of large-scale batteries.Firstly,by analyzing the large-scale historical data of battery,the battery state is effectively clustered from the two levels of battery health state(spatial dimension)and time evolution discharge process(time dimension).Then,by mapping data distribution to higher dimensional space,the corresponding deep neural network model for battery health state prediction based on spatial-temporal distribution mapping is designed.Experimental results demonstrate the effectiveness of proposed method.
作者
王波
陈东东
张锦霞
张之琛
马星星
张志宏
WANG Bo;CHEN Dongdong;ZHANG Jinxia;ZHANG Zhichen;MA Xingxing;ZHANG Zhihong(State Grid Shaanxi Information and Telecommunication Company,Xian 710065,China;School of Biomedical Engineering,Shanghai Jiao Tong University,Shanghai 20030,China;School of Information,Xiamen University,Xiamen 361005,China)
出处
《智慧电力》
北大核心
2022年第6期85-91,共7页
Smart Power
基金
国家自然科学基金面上资助项目(62176227)
国家自然科学基金重点支持项目(U2066213)
中央高校基本科研业务费(20720210047)。
