KOA-CNN Based Fault Line Selection Method for Hybrid Grounding System in 10kV Distribution Network

Aiming at the requirements of fast and accurate fault line selection in hybrid grounding systems of 10kV distribution network, a kind of grounding fault line selection method based on the convolutional neural network of the Keplerian optimization algorithm is proposed. Firstly, the wavelet transform is used to map the zero sequence current signal into a two-dimensional time-frequency diagram to prepare a small current grounding data set. And then, the Keplerian optimization algorithm is used on the convolutional neural network to optimize its learning rate, convolutional kernel size, and number to construct the KOA-CNN small current grounding fault line selection network. Finally, in order to verify the algorithm, the simulation is carried out by MATLAB software, and the results show that the proposed fault line selection method can achieve accurate identification of faulted lines with high reliability.