Wind power plant wind turbine generator frequency converter state evaluation method based on temperature prediction

Abstract

The invention discloses a wind power plant wind turbine generator frequency converter state evaluation method based on temperature prediction. The wind power plant wind turbine generator frequency converter state evaluation method comprises the following steps: randomly selecting data of an a wind turbine generator in an SCADA system in N days in a service life, and forming N groups of datasamples; preliminarily screening the types of input variables of the time series nonlinear prediction model; comprehensively screening multiple input variables of the prediction model; re-training and synthesizing a multi-input and multi-output prediction model; evaluating the frequency converter state according to the frequency converter temperature prediction result; and predicting the frequency converter temperatures of all the wind turbine generators in the wind power plant, and further performing self-confirmation and evaluation on the frequency converter states of the wind turbine generators. The wind power plant wind turbine generator frequency converter state evaluation method carries out temperature prediction of a frequency converter of a wind turbine generator of a wind power plant under complex and variable working conditions, masters the state of the wind turbine generator frequency converter in real time, reminds wind power plant technicians to take necessary measures toprevent the frequency converter from being damaged too early and accidents from happening, and can also be popularized and applied to frequency converter temperature prediction and state evaluation of other complex electromechanical systems.

Description

【Technical field】 [0001] The invention relates to the technical field of state monitoring and data mining of a wind turbine in a wind farm, in particular to a method for evaluating the state of a frequency converter of a wind turbine in a wind farm based on temperature prediction. 【Background technique】 [0002] As the problem of environmental pollution becomes more and more prominent, and in order to overcome the energy crisis, wind energy, as a green renewable energy, has been paid more and more attention by countries all over the world. Key equipment has developed rapidly. By the end of 2016, the total installed capacity of wind turbines in the world reached 486GW. Wind turbines are complex mechatronic equipment. Moreover, large wind turbines are usually located in remote areas with harsh environments and coastal or offshore areas. The engine room is generally installed at a height of tens of meters or even hundreds of meters above the ground. Therefore, abnormalities and...

AI Technical Summary

Problems solved by technology

However, due to the large amount of information redundancy in the SCADA data of wind turbines in wind farms, the correlation and correlation of each monitoring signal of wind turbines are not clear, so it is not ideal to use SCADA data to timely grasp the real-time operation status of wind turbine inverters.

Images