Distribution transformer heavy overload identification early warning method based on neural network and terminal equipment

Abstract

The invention relates to a distribution transformer heavy overload identification early warning method based on a neural network and terminal equipment, and the method is used for identifying and early warning a heavy overload event of a distribution transformer in a certain day, and comprises the following steps: 1) obtaining basic data of the distribution transformer in each transformer area tobe identified, and carrying out the preprocessing of the basic data; 2) based on the preprocessed basic data, carrying out coarse prediction classification on each transformer area distribution transformer, wherein the category of the coarse prediction classification comprises first-level safety, second-level safety and second-level attention; and 3) judging whether a transformer area distributiontransformer belonging to second-level attention exists or not, if so, performing fine prediction on the transformer area distribution transformer belonging to the second-level attention by adopting the trained GRU type neural network, outputting distribution transformer early warning information based on a fine prediction result, and if not, outputting distribution transformer normal information.Compared with the prior art, the method has the advantages that the state of dynamic monitoring at any time can be kept, the computing power can be saved, and the accurate prediction effect is achieved.

Description

technical field [0001] The invention relates to a distribution transformer overload identification and prediction method, in particular to a neural network-based distribution transformer overload identification and early warning method and terminal equipment. Background technique [0002] In the process of power transmission in the distribution network, the distribution transformer (distribution transformer for short) is affected by various complex factors such as the external environment, users, and the attributes of the equipment itself, and the power supply equipment in the station area often appears in a heavy overload operation state. When the equipment is in a heavy overload state for a long time, it will cause hidden troubles or even serious losses to the safe operation of the entire power grid. Traditionally, the control method of the power system for the overload of the distribution transformer usually focuses on the real-time monitoring of the power monitoring syst...

AI Technical Summary

Problems solved by technology

This kind of management method is relatively passive, and cannot completely avoid the loss of power grids and users, and the early warning accuracy is not high and the timeliness is poor, resulting in large personnel costs and long cycles, slow maintenance response, and serious lag

[0003] Therefore, at present, the accuracy of the overload prediction of the distribution variable weight is not good, and it consumes manpower, which is a technical problem that those skilled in the art need to solve.

Images