A Discrete Bayesian Network-based Fault Location Method for Hybrid Line Distribution Networks

Abstract

The invention provides a method for locating a fault section of a hybrid line distribution network based on a discrete Bayesian network, which relates to the technical field and includes simplifying a physical model of the distribution network; Influence, establish a discrete Bayesian network model for fault location; determine the structure of the discrete Bayesian network according to the topology of the simplified model of the distribution network; use the expectation-maximization algorithm to train the parameters of the discrete Bayesian network based on historical fault information; use The confidence propagation algorithm infers the discrete Bayesian network, and obtains the probability distribution of the fault state of each line segment under the current observation information; according to the probability distribution of the fault state of the line segment, the faulty line segment is determined as the result of the fault segment location. The present invention can provide all possible situations and their probabilities when a fault occurs, has high data fault tolerance, and can effectively solve the problem of inaccurate fault section location caused by fault information distortion or lack.

Description

technical field [0001] The invention relates to the field of distribution network fault diagnosis and recovery control, in particular to a fault section location method for a hybrid line distribution network with fault tolerance capability. Background technique [0002] With the increasing number of overhead-cable hybrid lines in the distribution network, it is of great significance to study the fault handling technology for improving the power supply reliability of the distribution network. As one of the commonly used technologies in fault handling, protection reclosing should not only restore the power supply in healthy areas as much as possible, reduce power outage losses, but also avoid reclosing during faults, which will cause the distribution system to be impacted by secondary short-circuit currents. loss. Because the fault nature (transient fault / permanent fault) of overhead lines and cable lines is generally different, the protection reclosing on hybrid lines lacks ...

AI Technical Summary

Problems solved by technology

Judging from the current research status of distribution network fault section location, the current algorithms are all based on the assumption that the fault information collected by the distribution automation system is accurate.

However, most of the measurement devices for distribution lines are installed outdoors, which will inevitably be disturbed by various environmental factors.

These influencing factors will lead to the problem of signal distortion in the collected fault information

Images