元の名称記録: SHANDONG UNIVERSITY

The present invention provides a topology, method and system for bi-directional power conversion of excitation power supply for power battery testing, wherein the topology comprises a three-phase PWM (pulse width modulation) converter, a high-frequency isolation three-level LLC (logical link control) resonant converter and a DC-DC (direct current) converter forming a topology structure for a three-stage power conversion; an input end of the three-phase PWM converter is connected to a power grid side; the high-frequency isolation three-level LLC resonant converter is connected between the three-phase PWM converter and the DC-DC converter in series and is configured for realizing bi-directional DC voltage conversion and isolation, and to raise a busbar voltage between the high-frequency isolation three-level LLC resonant converter and the DC-DC converter; and, the DC-DC converter is configured to generate charging and discharging excitation currents for a power battery testing.

Provided is a method for perceiving and eliminating an abnormal state of active distribution network based on data enhancement, including: acquiring, by synchrophasor measurement device, data of each node of active distribution network in target domain in real-time and transmitting to processor; inputting the acquired data into a classification model, and outputting abnormal detection and classification results in real time; and analyzing the abnormal detection and classification results, and transmitting an abnormal state eliminating instruction to a distribution terminal to eliminate the abnormal state. Wherein, hidden distribution features in node data of active distribution network are mined through dynamic clustering, a large amount of unlabeled data are clustered, a data label is generated through self-coding and label correction rule, training samples with balanced category distribution is generated through data enhancement and is used to train the classification model based on dynamic graph attention network by domain adaption method.