Smart substation real-time diagnosis and fault early warning method

Abstract

The invention discloses a smart substation real-time diagnosis and fault early warning method. The method comprises the following steps of: S1: inputting electrical equipment operation data, network traffic data and server log data into a database when a substation failure occurs to form fault data, and establishing a large data set sample training space; S2: capturing a network packet by employing a network packet analysis tool, and uploading the data in the network packet to the database for analysis and display, wherein the data in the network packet is network data; S3: performing machinelearning for the data in the database, and performing classification and comparison of the fault data and the network data through machine learning to obtain a fault model; and S4: based on the faultmodel, forming a fluctuation threshold of the substation equipment operation fault parameter and accessing the substation real-time data, and when the real-time data fluctuation threshold exceeds theearly warning value of the fault model, performing fault early warning display.

Description

technical field [0001] The invention relates to a fault early warning method, in particular to an intelligent substation real-time diagnosis and fault early warning method. Background technique [0002] The IEC61850 protocol realizes the digitization and informatization of the substation, realizes the information interaction between the equipment of the whole station through GOOSE, SV and MMS messages, and completes the functions of equipment control, protection and monitoring. In order to help operation and maintenance personnel and technical personnel to locate the fault point and find the cause of the fault in time after the occurrence of a substation incident, the smart substation is equipped with a network analysis system. Status monitoring and abnormal information alarm functions, but the lack of effective means to classify and filter various alarm information often makes operation and maintenance personnel at a loss and clueless when faced with a large number of alarm...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that the diagnostic results are fuzzy, and only a large amount of abnormal alarm information can be prompted, but the alarm information cannot be classified and the measures for eliminating defects can not be given, and the operation status of the entire substation equipment and network cannot be displayed dynamically. By dismantling and analyzing the data packets layer by layer and tracing the source step by step, not only the technical threshold is high, but the work efficiency is also extremely low. The purpose is to provide real-time diagnosis and fault warning methods for smart substations to solve the above problems

Images