Comparison between open phase fault of arc suppression coil and single phase to earth fault in coal mine distribution network

When, in a coal mine distribution network whose neutral point is grounded by an arc suppression coil (ASC), a fault occurs in the ASC, compensation cannot be properly realized. Furthermore, it can damage the safe and reliable run of the network. We first introduce a three-phase five-column arc suppression coil (TPFCASC) and discuss its autotracking compensation theory. Then we compare the single phase to ground fault of the coal mine distribution network with an open phase fault at the TPFCASC using the Thévenin theory, the symmetrical-component method and the complex sequence network respectively. The results show that, in both types of faults, zero-sequence voltage of the network will appear and the maximum magnitude of this zero-sequence voltage is different in both faults. Based on this situation, a protection for the open phase fault at the TPFCASC should be estab-lished.

Faulty Feeder Identification in Resonant Grounding Distribution Networks Based on Deep Learning and Transfer Learning

Identification of faulty feeders in resonant grounding distribution networks remains a significant challenge dueto the weak fault current and complicated working conditions.In this paper, we present a deep learning-based multi-labelclassification framework to reliably distinguish the faulty feeder.Three different neural networks (NNs) including the multilayerperceptron, one-dimensional convolutional neural network (1DCNN), and 2D CNN are built. However, the labeled data maybe difficult to obtain in the actual environment. We use thesimplified simulation model based on a full-scale test field (FSTF)to obtain sufficient labeled source data. Being different frommost learning-based methods, assuming that the distribution ofsource domain and target domain is identical, we propose asamples-based transfer learning method to improve the domainadaptation by using samples in the source domain with properweights. The TrAdaBoost algorithm is adopted to update theweights of each sample. The recorded data obtained in the FSTFare utilized to test the domain adaptability. According to ourvalidation and testing, the validation accuracies are high whenthere is sufficient labeled data for training the proposed NNs.The proposed 2D CNN has the best domain adaptability. TheTrAdaBoost algorithm can help the NNs to train an efficientclassifier that has better domain adaptation. It has been thereforeconcluded that the proposed method, especially the 2D CNN, issuitable for actual distribution networks.