Multi-information fusion segment location method based on extreme learning machine

Abstract

Disclosed is a multi-message fusion section locating method based on an extreme learning machine. After a fault happens, terminals extract feature vectors from zero-sequence transient current measured in real time according to a transient energy method, a wavelet method and a first half-wave method, upload the feature vectors to a master station and input the feature vectors into the extreme learning machine network where weight parameters are obtained after being trained, and the main station starts the multi-message fusion locating algorithm and outputs a section locating result. As the terminals installed at the multiple positions of a circuit can detect the transient zero-sequence current signals in real time, so that the section locating method based on the transient messages can be applied to the actual engineering. The influence on the method by factors like the grounding position, the grounding time and the grounding transition resistance is small, the extreme learning machine is intelligently fused and comprehensively analyzes the zero-sequence current transient information after the fault, and various algorithms are fused to achieve the complementary effect. The inherent defects of a single locating method are overcome, the transient zero-sequence current characteristic can be fully utilized, the fault section can be determined accurately, and the smaller the space between the terminals is, the more accurate the locating is.

Description

technical field [0001] This application belongs to the technical field of power system automation, and is a section positioning method for a single-phase ground fault in a distribution network, which is suitable for a 3-60kV neutral point non-effectively grounded power grid, and can accurately locate the fault when a single-phase ground fault occurs segment. Background technique [0002] After a single-phase ground fault occurs in a small current grounding system, the fault line needs to be selected as soon as possible. After decades of development, the line selection problem has been well solved, the technology is mature, and the reliability of the existing devices is high. After the fault line is selected, it is necessary to further find out the section where the fault point is located, that is, the section location problem. [0003] Compared with the traditional steady-state component, the fault characteristics are obvious by using the transient quantity location, and it...

AI Technical Summary

Problems solved by technology

[0005] Existing positioning methods usually use a single fault information for positioning, the accuracy is low in actual operation, and it is difficult to meet the needs of the site

At present, there are three methods for automatic positioning on site. The first method is to inject a high-frequency signal from the PT and detect the signal along the line to determine the fault location. However, because the distributed capacitance of the line forms a path for the high-frequency signal, the positioning is not correct when it is grounded through a resistor. precise

The second method is to use the fault indicator. Since the fault indicator can only measure the phase current and cannot measure the zero-sequence current, it is better for short-circuit faults, but the accuracy of single-phase ground fault location is very low.

The third method is to install a smart switch with a built-in CT. Although this method can measure the zero-sequence current, the terminals and master stations operating on the market have simple algorithms that only judge whether the steady-state zero-sequence current exceeds a fixed value. The positioning accuracy of the arc suppression coil grounding system is very low

Images