摘要
针对储能系统电池容量实时预测中存在的电池新旧程度不一,放电倍率、采样间隔多样等多元化问题,提出了一种全新的基于安时残差连接的长短时记忆网络。通过进行多通道传感信号的特征变换,使其更适用于多元化电池放电的实时剩余容量预测。所提方法相比于常见基线方法误差降低了11.8%,并且在多倍率测试下方差较小,具有更高的鲁棒性。
In the light of multiple problems in real-time battery capacity prediction of energy storage system,such as the different utilization degree of batteries and the various sampling intervals of discharge rate,a new short and long time memory network based on ampere-hour residual connection is proposed.The characteristic transformation of multi-channel sensor signal makes it more suitable for real-time residual capacity prediction of diversified battery discharge.Compared with common baseline methods,the error of proposed method is reduced by 11.8%.The proposed method has smaller variance and higher robustness under multiple rate test.
作者
陈果
黄祺尧
张志宏
CHEN Guo;HUANG Qiyao;ZHANG Zhihong(State Grid Shaanxi Electric Power Information and Telecommunication Company,Xian 710065,China;School of Informatics,Xiamen University,Xiamen 361005,China)
出处
《智慧电力》
北大核心
2022年第7期29-36,共8页
Smart Power
基金
国家自然科学基金资助项目(62176227,U2066213)。
关键词
储能系统
电池剩余容量预测
安时积分估计法
信号特征处理
Res-LSTM神经网络
多倍率放电
energy storage system
battery remaining capacity prediction
ampere-hour integral estimation method
signal feature processing
Res-LSTM neural network
multi-rate discharge