Intelligent restoration method for SCADA data loss of wind power plant

Abstract

The invention provides an intelligent restoration method for SCADA data loss of wind power plant, which comprises the following steps of selecting multiple columns of corresponding auxiliary restoration unit data B for to-be-restored unit data a; selecting a plurality of columns of auxiliary restoration unit data C having the maximum correlation with a in the auxiliary restoration unit data B; judging the variance difference between the to-be-repaired unit data a and the multiple columns of auxiliary repair unit data C, and standardizing the a and the C if the variance difference exceeds a setthreshold value; carrying out baseline compensation on the C; selecting a plurality of columns of unit data D with the minimum average absolute error with the unit data a to be restored in C for theauxiliary restoration unit data C obtained in the above steps; performing grouping and screening on the multiple columns of unit data D to obtain multiple columns of unit data D' closest to a mean value; carrying out median filtering on the multi-column unit data D '; and calculating the mean value of the multiple columns of unit data D' at each moment. The missing data can be efficiently, accurately and intelligently repaired, the efficiency is high, and the robustness is high.

Description

technical field [0001] The invention relates to the field of industrial big data, in particular to an intelligent repair method for missing SCADA data of wind farms. Background technique [0002] Wind energy, as a clean and renewable energy, has increasingly attracted the attention of countries all over the world, and wind power generation technology has become mature. There are dozens or even hundreds of wind turbines in a large wind farm. Due to the remote location of wind farms (especially offshore wind farms), manual maintenance is difficult. During the operation of the SCADA database system of wind farms, SCADA can remotely obtain the operating status data of wind turbines, which is the guarantee for the healthy operation of wind farms. However, SCADA systems are often affected by various factors such as sensor failure and network congestion, resulting in data loss. Therefore, in order to recover the loss caused by missing data, a method of estimating the missing part...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art, to provide an intelligent repair method for missing SCADA data in wind farms, capable of repairing missing data in wind turbine SCADA, and to solve the problem of low repair accuracy and large amount of calculation in existing methods question

Images