One-stop optimization method and device for dual-active bridge converter with operating condition robustness

The invention discloses a dual-active bridge converter one-stop optimization method with operating condition robustness, which comprises the following steps of: initializing a corresponding modulation parameter scheme according to a modulation strategy specified by a user; setting an expert system b...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	LI XINZE, LEI WEIHAO, LIN FANFAN, ZHANG XIN, LIU XUEQI
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	APPARATUS FOR CONVERSION BETWEEN AC AND AC, BETWEEN AC AND DC,OR BETWEEN DC AND DC, AND FOR USE WITH MAINS OR SIMILAR POWERSUPPLY SYSTEMS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONTROL OR REGULATION THEREOF CONVERSION OF DC OR AC INPUT POWER INTO SURGE OUTPUTPOWER CONVERSION OR DISTRIBUTION OF ELECTRIC POWER COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRICITY GENERATION PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The invention discloses a dual-active bridge converter one-stop optimization method with operating condition robustness, which comprises the following steps of: initializing a corresponding modulation parameter scheme according to a modulation strategy specified by a user; setting an expert system based on a specified modulation strategy to generate an oscillogram of the electrical signal; collecting time-varying inductive current, and selecting the inductive current at the same time node and the electric signal in the oscillogram as samples to construct sample data; constructing a physical structure recurrent neural network; training the physical structure recurrent neural network by using the data set to obtain an optimal prediction model; and constructing a performance optimization objective function and solving to obtain an optimal modulation parameter scheme. The invention also provides a dual-active bridge converter modulation device. The method provided by the invention can accurately reveal behavior r