Parametric Average-Value Modeling of Diode Rectifier Systems Based on Neural Network

In an ac power system, the diode rectifier is often used as the front-end circuit of many electronic loads. In the research of power electronic systems, averaging modeling (AVM) is essential, in which complex switching subcircuits can be replaced by appropriate non-switching averaging subcircuits and dependent controllable sources and other circuit components. For parametric AVM of diode rectifier, when the operational conditions, the PAVM may need to be re-formulated and many times of detailed simulation is needed, which is time-consuming. The neural network has been widely used in the field of artificial intelligence in recent years. This paper uses the neural network to learn the parametric functions in PAVM and compares the neural network-based PAVM with the detailed model. Test results show the effectiveness and accuracy of the proposed PAVM model.