Power transformer fault early warning system based on data mining

Abstract

The invention relates to a power transformer fault early warning system based on data mining, and the system comprises a power transformer full-dimension original data set module, a seamless embedded data application interface module, a power transformer full-dimension original data set cleaning module, a power transformer high-quality sample data set module, and a power transformer core algorithm module. a power transformer fault early warning model analysis module, and a human-computer interface display module. Compared with the prior art, the system has the advantages that massive electric power big data generated in intelligent power grid construction is fully utilized, implicit and potential value information is extracted by adopting a data mining method, the modeling speed is high, the learning process is simple, and a complete fault knowledge base is not needed; the defects of low modeling speeds, low accuracy and the like of traditional modeling methods are overcome, the problems of low maintenance pertinence, incapability of distinguishing primary and secondary maintenance, rigid maintenance mode and the like in planned maintenance of the power transformer are solved, and the requirement of fault early warning of the power transformer is met.

Description

technical field [0001] The invention belongs to the application technology of electric power big data analysis, and in particular relates to a power transformer fault early warning system based on data mining. Background technique [0002] With the rapid development of smart grid construction, intelligent online monitoring equipment has been greatly developed, and the data monitored by the power grid shows a geometric growth trend, especially the status monitoring data (DGA) and operation scheduling data related to the operating status of power transformers. (SCADA), production management data (PMS), meteorological information data, and geographic information data (GIS) and other data are showing blowout growth, and new data is generated every moment, showing low data value density and various data types. As well as the typical characteristics of big data such as huge data volume, a rich historical database and real-time database have been formed. Faced with these high-para...

AI Technical Summary

Problems solved by technology

For example, the traditional characteristic gas method is limited to the diagnosis of the threshold value, and it is difficult to identify potential faults; the three-ratio method is limited by the coding type and range, and the fault diagnosis accuracy is poor; the neural network diagnosis will appear oscillations and fall into a local optimal solution The diagnosis of the expert system depends on the fault knowledge base, and the accuracy of the imperfect power transformer fault knowledge base is poor; the coding and decoding of genetic algorithm diagnosis are too complicated; the diagnosis of support vector machine is suitable for binary classification problems, suitable for small sample classification , but for the multi-classification of power transformer faults, the accuracy is poor; the diagnosis of fuzzy theory has no self-learning ability, and the rules require long-term accumulation of experience and knowledge

Most of the above fault diagnosis methods for power transformers require a known and complete fault diagnosis knowledge base, and can only identify existing faults in the knowledge base.

And the power transformer is a complex structure, multi-variable and non-linear complex equipment, there is no clear correspondence between faults and symptoms, a fault may have multiple symptoms, and a symptom may have multiple faults

In addition, traditional fault diagnosis methods can only diagnose after the event, which cannot meet the needs of power transformer fault early warning

Images