Multi-level state evaluation method of power transformer

Abstract

The invention discloses a multi-level state evaluation method of a power transformer. The method is characterized by firstly, constructing a transformer multi-level system capable of reflecting a fault type and a position, and after index selection, reflecting uncertainty of a criterion boundary by obtaining an index deterioration degree and carrying out Gaussian cloud processing; acquiring a comprehensive weight through an association rule and variable weight processing to reflect the uncertainty of the weight; using DSmT to carry out multiple evidence fusion to solve problems of a high conflict and the uncertainty of an evaluation layer; and finally, acquiring the fault type and the fault position of a device, and a whole state of the transformer. The uncertainty problem of the transformer in an evaluation process is solved, and fault diagnosis and health assessment are combined so that an overall health condition of the transformer can be seen at a macro level, and the fault of thetransformer can be discovered from details.

Description

technical field [0001] The invention relates to a state evaluation method of a power transformer, in particular to a multi-level state evaluation method of a power transformer, which belongs to the technical field of power supply. Background technique [0002] Power transformer is an important equipment in power transmission and transformation and power supply and distribution system, and its operation status has a great influence on the safe and stable operation of the power grid. In the long-term operation of the transformer, it is inevitable that there will be abnormal operation status. Accurate evaluation of the operation status of the power transformer is conducive to the smooth progress of the transformer condition maintenance work and the formulation of a reasonable maintenance strategy. [0003] With the continuous deepening of the current condition-based maintenance and the investment of a large number of online testing equipment, real-time and dynamic analysis of e...

AI Technical Summary

Problems solved by technology

[0003] With the continuous deepening of the current condition-based maintenance and the investment of a large number of online testing equipment, real-time and dynamic analysis of equipment in the state grid and provincial equipment status assessment has become a normal work, and the maintenance status of power system equipment has been certain. Improvement, but also exposed problems such as long equipment status evaluation cycle, insufficient information analysis, and poor real-time performance

At present, with the rapid development of the electric power industry, the data in the electric power industry database is growing explosively, such as ledger information, inspection information, live detection and online monitoring data, offline test data, etc., and has the ability to carry out data analysis and data mining. The data foundation, conventional data processing and statistical analysis methods have been stretched and cannot meet the requirements of power grid development

At present, most of the transformer status evaluation systems focus on the warning of a certain index exceeding the standard, which can only reflect part of the transformer situation, and fail to combine and utilize multi-source information to realize the dynamic comprehensive evaluation of the transformer, resulting in the dispersion of transformer operation and status information in multiple information platforms Moreover, these platforms are relatively independent, which is not conducive to the multi-dimensional and multi-data analysis and display of information, and is not conducive to the in-depth understanding and evaluation of transformer status by operation and maintenance evaluators.

Images