A method for early warning of wind turbine component status based on historical data

Abstract

The invention discloses a method for early warning of the status of wind power generating set components based on historical data. Firstly, the main operating characteristic data of the wind generating set are collected; Feature operating data with high sensitivity to component operating feature data; data cleaning of the filtered feature data; input of the cleaned data into the training module to establish a prediction model, and test the model, parameter adjustment, and finally obtain through training and learning algorithms Predictive model: deploy the predictive model to the wind turbine, and then run the predictive model to obtain the predicted value of the operating characteristic data of key components. When the deviation between the model predicted value and the actual value is greater than the preset threshold value, an alarm will be output to realize wind power generation The unit is shut down by early warning protection. The invention has the advantages of accurate prediction, high reliability, good economy and the like.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis and early warning of wind power generating sets, in particular to a method for early warning of wind power generating set component states based on historical data. Background technique [0002] Under the background of the "Internet + Smart Energy" era, the deep integration of digitization, intelligence and traditional wind power industry has become a new trend in the development of wind energy technology. It is recognized in the industry as an inevitable choice to improve market competitiveness by improving the operational stability of wind turbines and reducing operation and maintenance costs through the intelligentization of wind farms. Megawatt double-fed wind turbines have been put into operation in the Chinese market for more than 10 years. The operation covers plains, plateaus, mountains, offshore and other complex geographical environments. Most of the units in operation have gradu...

AI Technical Summary

Problems solved by technology

Megawatt double-fed wind turbines have been put into operation in the Chinese market for more than 10 years. The operation covers plains, plateaus, mountains, offshore and other complex geographical environments. Most of the units in operation have gradually entered the wear and aging period, and the project failure rate has increased year by year. Especially for large components such as generators and gearboxes, once a major failure occurs, the replacement and maintenance costs are high

The traditional preventive maintenance method cannot effectively predict the time of failure and effectively curb the frequent occurrence of wind power accidents

Images