Wind turbine generator fault early warning method based on SVR algorithm and kurtosis

Abstract

The invention relates to the field of wind turbine generator fault early warning, and provides a wind turbine generator fault early warning method based on an SVR algorithm and kurtosis. The method comprises: carrying out data collection of historical data of a wind turbine generator; performing data cleaning to remove abnormal data; establishing an early warning model by using a support vector regression algorithm; carrying out residual analysis and early warning; and based on skewness and kurtosis in statistics, calculating the residual error of the output value of the early warning model; and calculating the kurtosis and skewness of the residual error day by day through a sliding window algorithm, taking a mean value of a maximum value of the skewness and a maximum value of the kurtosisas a maximum value of an early warning model threshold, taking a mean value of a minimum value of the skewness and a minimum value of the kurtosis as a minimum value of the early warning model threshold, and carrying out online monitoring and early warning on real-time data of the wind turbine generator. According to the method, pre-fault pre-judgment can be provided in time before the wind turbine generator breaks down, fault analysis and control are achieved in the first time, and huge economic losses and safety accidents are prevented from being brought.

Description

technical field [0001] The invention relates to the field of wind power generator failure early warning, in particular to a wind power generator failure early warning method based on SVR algorithm and kurtosis. Background technique [0002] With the increasing shortage of energy supply in recent years, the problem of environmental pollution has become increasingly prominent, and the country's demand for new energy is increasing day by day. The world is urgently developing renewable energy to solve the plight of increasingly scarce non-renewable energy. As a clean and efficient energy source, wind energy has become the focus of national attention and development. For the entire wind power industry, the road is getting wider and wider. According to the "Wind Power Industry Market Prospect and Investment Strategic Planning Analysis Report", it is estimated that by 2023, the cumulative installed capacity of wind power in the world will reach 969.15GW. For decades, my country's...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a wind turbine generator failure early warning method based on the SVR algorithm and kurtosis, which solves the problems of complex algorithm calculation, strong parameter assumptions, long time-consuming, Insufficient reliability of the prediction model, weak generalization ability and other problems; By detecting the change trend of the actual value and the predicted value of the generator bearing temperature, based on the relatively strong support vector regression algorithm (SVR) in machine learning, the generator bearing The temperature prediction model realizes online monitoring and early warning with fast training speed, strong generalization ability, fast convergence speed and high accuracy

Images