Open AccessSOC Estimation Based on Time Series Neural Network and Its Performance Evaluation
Author(s) -
Jianhua Li,
Mingsheng Liu,
Yanmei Jiang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1650/3/032072
Subject(s) - artificial neural network , series (stratigraphy) , computer science , time series , key (lock) , estimation , time delay neural network , state (computer science) , algorithm , machine learning , engineering , paleontology , computer security , systems engineering , biology
Aimed at the disadvantage of state of charge (SOC) estimation by using traditional feed forward neural network, a new method proposed to soleve the problem. The time series neural network is introduced to estimate the SOC. The experiments results show that the time series neural can estimate the SOC more accurate. In addition, the different structures and the key parameter are discussed to achieve the best performance.