Operation state trend prediction method and system for phase modifier

Abstract

The invention discloses a running state trend prediction method and system for a phase modifier. The method comprises the following steps: determining specified monitoring quantity data and state quantity of the phase modifier; performing normalization and smooth denoising on each piece of monitoring quantity data, mining nonlinear correlation between state quantities and the monitoring quantities, selecting a part of monitoring quantities with relatively strong nonlinear correlation for each type of state quantity, adding input characteristics, constructing a training sample data set according to the input characteristics of all the state quantities and the state quantities, and training the machine learning model to obtain a running state trend prediction model of the phase modifier. On the basis of fully considering the problems of large data volume and poor data quality under the monitoring background of the existing sensor, the prediction analysis of the state quantity of the phase modifier system is realized, the prediction precision of the running state trend prediction of the phase modifier is improved, and an important support is provided for the safe and stable running of the synchronous phase modifier.

Description

technical field [0001] The invention belongs to electric power engineering, and in particular relates to a method and system for predicting the running state trend of a condenser. Background technique [0002] With the rapid development of UHV DC transmission projects in China, synchronous condensers, as powerful equipment for "strong reactive power support", can quickly provide large-scale dynamic reactive power for the power grid in a short period of time, so they are gradually widely used in power grids. However, the large-capacity synchronous condenser has a complex structure and a large volume. At this stage, various sensors are installed in each component system of the condenser to monitor its operating status and abnormal feature quantities in real time. There is no effective prediction method for the monitoring quantity of the condenser, and it cannot meet the requirements of large-scale synchronous condensers. The requirement for the safe operation of capacity conde...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a method and system for predicting the running state trend of the camera are provided. The present invention fully considers the large amount of data and the quality of data under the background of existing sensor monitoring On the basis of these problems, the prediction and analysis of the state quantity of the condenser system is realized, the prediction accuracy of the trend prediction of the operating state of the condenser is improved, and an important support is provided for the safe and stable operation of the synchronous condenser

Images