Abstract

The fault diagnosis modes and fault reasons of grid-connected photovoltaic power system were described, and as to the possible faults of solar grid-connected power system, a method of fault diagnosis based on BP neural network was proposed. The fault information was used as samples to train the BP neural network, and the relations between the network fault information and fault patterns output were established utilizing its strong self-adaptation and nonlinear mapping ability. The test results demonstrate the effectiveness and feasibility of this method. It not only has the characteristics of high diagnostic accuracy, but also is easy to implement, so it can be applied into fault iagnosis of grid-connected photovoltaic power system.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call