Multi-dimensional comprehensive online monitoring intelligent diagnosis system for transformer

Abstract

The invention provides a multi-dimensional comprehensive online monitoring intelligent diagnosis system for a transformer. The system comprises a perception sensing layer, an edge calculation layer, a deep learning layer, a cloud feedback layer and a user control layer. The sensing layer comprises a plurality of intelligent sensors and is used for acquiring a plurality of dimension parameters of the transformer; the edge calculation layer comprises an edge calculation terminal, and the perception sensing layer sends the multiple dimension data to the edge calculation terminal to execute edge calculation; the deep learning layer summarizes and analyzes a plurality of edge calculation results of the edge calculation terminal, and determines whether to provide a feedback signal to the cloud feedback layer based on the summarized and analyzed result; the cloud feedback layer updates an edge computing model of the edge computing terminal based on the feedback signal; and the user control layer is used for controlling the sensing state of the perception sensing layer and identifying the state of the transformer based on the edge calculation result. According to the method, comprehensive intelligent diagnosis can be performed based on multi-dimensional data, and the edge model can be updated in a self-learning manner.

Description

technical field [0001] The invention belongs to the technical field of transformer intelligent monitoring, in particular to a transformer multi-dimensional comprehensive online monitoring intelligent diagnosis system. Background technique [0002] The power transformer is one of the most important equipment in the power grid, and its reliability is directly related to whether the power grid can operate safely, efficiently and economically. Reducing transformer faults means improving the economic benefits of the power grid. Due to the long-term continuous operation of transformers in the power grid, various failures and accidents will inevitably occur. The cause analysis and monitoring of these faults and accidents has been a hot topic for transformer design, operation and maintenance personnel for many years. [0003] Common transformer faults have a variety of test and diagnosis methods, such as: measurement of DC resistance, chromatographic analysis, partial discharge te...

AI Technical Summary

Problems solved by technology

[0007] However, there are certain defects in the various diagnostic schemes mentioned in the prior art

First of all, only a single variable is used for judgment, and the results are biased; in addition, the model used is a static model, which cannot be updated according to the actual situation; finally, the process of testing or collecting signals does not consider the actual sequence and fault dependence, so it needs to be compared. High hardware cost, high energy consumption, reduced economic benefits

Images