Three-phase grid-connected converters are widely used in renewable and electric power system applications. Due to system nonlinearity and time-variant characteristic, there are limitations in standard decoupled d-q ve...
详细信息
ISBN:
(纸本)9789881563958
Three-phase grid-connected converters are widely used in renewable and electric power system applications. Due to system nonlinearity and time-variant characteristic, there are limitations in standard decoupled d-q vector control mechanism. To mitigate these limitations, a RNN vector controller trained with Levenberg-Marquardt and fatt(Forward accumulation through time) algorithm is designed. The simulation is researched by using MATLAB software, and the results show that training neural-network algorithm is effective and the system using RNN vector control method outperforms the system using conventional PI control method under low sampling rate conditions.
Three-phase grid-connected converters are widely used in renewable and electric power system applications. Due to system nonlinearity and time-variant characteristic, there are limitations in standard decoupled d-q ve...
详细信息
Three-phase grid-connected converters are widely used in renewable and electric power system applications. Due to system nonlinearity and time-variant characteristic, there are limitations in standard decoupled d-q vector control mechanism. To mitigate these limitations, a RNN vector controller trained with Levenberg-Marquardt and fatt(Forward accumulation through time) algorithm is designed. The simulation is researched by using MATLAB software, and the results show that training neuralnetwork algorithm is effective and the system using RNN vector control method outperforms the system using conventional PI control method under low sampling rate conditions.
暂无评论