Parameter identification of DC–DC converter based on dendrite net under fluctuating input voltages

• DOI: 10.1049/pel2.12529
• Publication Date: 2023-05-27T06:40:02Z
• Authors: Yueming Jiang; Yanlong Liu; Zhiming Yang
• Keywords: Identification

Abstract The traditional identification methods of direct current‐to‐direct current (DC–DC) converters usually consider the common situation where training and testing sets have same input voltage. In real‐world applications, actual voltage may fluctuate beyond its original value, thus negatively affecting parameter accuracy. Therefore, this paper presents a method under fluctuating voltages. Firstly, to increase accuracy, proposes coefficient variation extract key features from all time‐ frequency‐domain as data. Then, for voltages, adds voltages into data build network based on Dendrite Net. When using established identify component parameters in practical change an unknown value because irregular fluctuation. Hence, needs be identified before identifying DC–DC converter. Finally, builds network. By combining results voltage, can completed. simulation hardware experiments validate practicability effectiveness proposed method.