Storage battery performance prediction method and system based on combined model

The invention provides a storage battery performance prediction method and system based on a combined model, and the method comprises the steps: obtaining a change trend representation vector of the internal resistance of a storage battery based on the historical operation data of the internal resis...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LYU XINQUAN, HAN GUANGMING, LI LI, ZHU YOUXIANG, XIE GAOPENG, TIAN ANQI, WANG LIJUN, ZHANG YAN, ZHU GUOPENG, XIAO SHENYANG, JIANG YINGJIE, MA LIANG, SUN CHAO, MA KAI, ZHANG PU, LIU WEI, REN TINGXIN, WANG QI, MI YUANZE, YU QIUSHENG, WEI YONGJING, LU YI, LIU LEI, WANG RUI, WANG SHIHAO
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a storage battery performance prediction method and system based on a combined model, and the method comprises the steps: obtaining a change trend representation vector of the internal resistance of a storage battery based on the historical operation data of the internal resistance of the storage battery; based on storage battery internal resistance historical operation data and storage battery internal resistance related influence factors, extracting correlation among the influence factors, and obtaining a global representation vector of storage battery internal resistance change; based on the change trend representation vector and the global representation vector, performing combined prediction of the internal resistance of the storage battery by adopting meta learning and a gating network to obtain a combined representation vector of the change of the internal resistance of the storage battery; carrying out feature extraction on the storage battery charging and discharging data to ob