The invention relates to the technical field of
transformer excitation
inrush current suppression, in particular to a high-
impedance transformer excitation
inrush current suppression method and
system, and the
system comprises a data collection module, a data preprocessing module, a calculation module, a main control module, an output module and an execution module. The method comprises the following steps: firstly, establishing a finite
element model based on
hysteresis characteristics, and collecting real operation data of a
transformer and taking the real operation data as input to
train the finite
element model; continuously optimizing the model, and performing a
simulation experiment by using the optimized finite
element model to obtain
simulation experiment data so as to construct a
data set R, thereby greatly reducing the labor capacity of a manual experiment and quickly obtaining a large amount of
simulation data;
feature extraction and
deep learning are carried out based on a neural
network model, so that a prediction model about the excitation surge current is trained; then actual operation data of the
transformer are collected, and the magnetizing
inrush current is predicted by using the prediction model; and a proper closing angle or opening angle is selected to control the operation of the transformer, so that the purpose of reducing excitation inrush current is achieved.