Fault identification method for UHVDC transmission line based on multi-source information fusion

Abstract

The invention relates to a method for identifying the cause of a UHV DC transmission line fault based on multi-source information fusion, which includes: acquiring electrical quantity fault data and non-electrical quantity information of the UHVDC transmission line; extracting the electrical characteristic quantity of the UHVDC transmission line , to construct the electrical characteristic input vector; extract the non-electrical characteristic quantity of the UHV DC transmission line, and construct the non-electrical characteristic input vector; construct the comprehensive neural network identification model for lightning strike, mountain fire, pollution, wind deviation, and bird damage respectively, and the neural network model The number of layers of the hidden layer is selected by the method of minimum error; the method of self-learning is used to identify the specific cause of the fault. The present invention integrates electrical quantity information and non-electrical quantity information, searches for characteristic rules, uses the fusion of neural network itself to fuse multi-source information, uses the idea of ​​big data methods, uses multi-source fault information, and combines neural network algorithms to carry out The identification of the cause fully guarantees the accuracy of the identification of the cause.

Description

technical field [0001] The invention relates to the field of operation and maintenance of high-voltage transmission lines, in particular to a method for identifying fault causes of ultra-high voltage direct current transmission lines based on multi-source information fusion. Background technique [0002] The length of UHV DC transmission lines can reach thousands of kilometers, and most of them are located in mountainous and hilly areas. They are vulnerable to various natural disasters, external force damage, etc., and failures occur. Timely identification and research of the cause of failures can guide line inspections, speed up maintenance and maintenance of lines. Power restored. [0003] Transmission line faults mainly include faults caused by lightning strikes, wildfires, pollution, bird damage, and wind deviation. The identification of the cause of the fault needs to be based on the understanding of various fault principles and processes. On this basis, the characteri...

AI Technical Summary

Problems solved by technology

[0004] Among them, the fault characteristics include the fault characteristics of electrical quantities and the fault characteristics of non-electrical quantities. There are similarities in the characteristics of electrical quantities under different reasons, and there are also unique factors in non-electrical quantities, which cannot be accurately identified only by one factor.

At present, there is no complete set of methods for identifying the cause of UHVDC transmission line faults, and it is impossible to provide operation and maintenance personnel with decision-making assistance after a fault occurs in the transmission line.

Images