Open AccessHealth Evaluation Method of Supercapacitor Based on Data Mining
Author(s) -
Zhengjun Fang,
Shuli Liu,
Yanming Zhao
Publication year - 2021
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 - 10.1088/1742-6596/1861/1/012006
Subject(s) - supercapacitor , energy storage , reliability (semiconductor) , train , computer science , euclidean distance , capacitor , energy (signal processing) , voltage , reliability engineering , electrical engineering , power (physics) , engineering , capacitance , mathematics , artificial intelligence , statistics , chemistry , physics , cartography , electrode , quantum mechanics , geography
With the wide application of super capacitor energy storage system as energy storage device on urban rail trains, the problem of its safe operation has attracted great attention. In order to ensure the reliability of the supercapacitor energy storage system, it is necessary to evaluate its health effectively. In view of the fact that the existing model-based supercapacitor evaluation methods are difficult to establish a reasonable and accurate model and the parameter estimation is complex, a data-driven supercapacitor health evaluation method is proposed. In this method, based on the data of voltage, current, temperature and external characteristic parameters of charge and discharge of supercapacitor, the weighted Euclidean distance formula is introduced, the mixed weighted Euclidean distance is calculated, and the comprehensive evaluation index of supercapacitor health state is obtained. It can quickly and effectively evaluate the health status of supercapacitors.