Power equipment on-line monitoring error data diagnosis method based on time sequence chaos characteristics

Abstract

The invention discloses a power equipment on-line monitoring error data diagnosis method based on time sequence chaos characteristics. According to the invention, the chaotic characteristic of the on-line monitoring data time sequence based on the state quantity of the power equipment is provided, the state quantity online monitoring data is judged, and error data in the state quantity on-line monitoring data is identified. The method is suitable for the state quantity with strong randomness, and has a very good supplementary effect on identifying error data based on a probability statistical distribution rule and a deterministic change rule of state quantity online monitoring data in the prior art.

Description

technical field [0001] The invention belongs to the field of electric equipment state evaluation, and specifically relates to a correlation-based identification method for error data in online monitoring data of electric equipment, which is used for eliminating error data in online monitoring data of electric equipment state quantities. Background technique [0002] The health status of power transmission and transformation equipment is crucial to the safe operation of the power grid. Power equipment in poor health will seriously threaten the safe operation level of the power grid and even cause grid accidents. How to accurately monitor the status of power equipment, discover potential defects of power equipment in time, and avoid accidents has become an important issue in the power industry. [0003] However, due to damage to the online monitoring device, performance degradation and other reasons, there are often erroneous data in the submitted test results, which seriously...

AI Technical Summary

Problems solved by technology

[0024] From a high-dimensional point of view, the time series of discharge data and other data directly obtained by the observer is the projection of the phase space trajectory in the low-dimensional space, and there is compression in the middle, resulting in information distortion or even error

What is certain is that there must be such phase points, which may be irrelevant in the high-dimensional space but may become two adjacent points in the low-dimensional time series during the extrusion and distortion process, which may lead to inability to Obtain correct and complete regularity information directly from measured time series

Images