A single-phase grounding fault line selection method based on the steady-state variation before and after the fault

Abstract

The invention proposes a data-driven single-phase grounding fault line selection method based on the steady-state variation information before and after the fault. The invention is divided into two parts: offline training and online application. First, the topology information and network parameters of the target distribution network are obtained, and a corresponding model is established in the simulation software; feature, the fault line number is the label, the simulation obtains a sufficient sample data set, the machine learning method is used to train the line selection model, and the network error-prone line selection area is obtained by testing; finally, the sample features obtained from the actual distribution network are input for offline training. model, output the line selection result and confidence level, and compare it with the error-prone line selection area. If the line selection result belongs to the error-prone line area, a prompt will be given. The invention can achieve accurate line selection for the single-phase grounding fault of the neutral point ungrounded distribution network, and still has a high line selection accuracy under the condition that the fault is grounded through high resistance.

Description

technical field [0001] The invention belongs to the field of electric power systems, in particular to a data-driven single-phase grounding fault line selection method based on steady-state variation information before and after a fault, which is suitable for a neutral point ungrounded distribution network. Background technique [0002] In order to ensure the reliability of power supply in the distribution network, when the capacitance current of the whole system does not exceed a certain value, the neutral point is mostly ungrounded. When a single-phase grounding fault occurs in the neutral point ungrounded distribution network, the fault current is small, and the current protection will not operate, which provides time for troubleshooting, but also causes difficulty in fault line selection, especially when the fault point touches the branches. , sand, asphalt, cement and other non-ideal media, high-resistance grounding faults are formed, which further increases the difficul...

AI Technical Summary

Problems solved by technology

The third type of method can perform better than the first two types due to the combination of the advantages of the method and the number of samples, but the complexity of the process and the demand for high-precision measurement equipment such as PMU greatly increase the application requirements. threshold

Images