Deep learning wind power alarm information analysis method based on small sample data

Abstract

The invention discloses a deep learning wind power alarm information analysis method based on small sample data. The method includes extracting characteristic parameters, wind speed and output powerof all components of a fan as the training samples, adopting a contrast divergence algorithm to train a restricted Boltzmann machine model, carrying out characteristic quantity extraction on data, carrying out statistical classification on the extracted characteristic quantity by using a probabilistic neural network algorithm, dividing a corresponding fault risk probability, and carrying out earlywarning according to a fault risk level, thereby realizing fault warning of the wind turbine generator set. According to the method, characteristic quantity extraction is carried out on the data sample through the restricted Boltzmann machine, the effect of dimension reduction is achieved, a good foundation is provided for subsequent data analysis, and the complexity of data analysis is reduced;and the problem of local minimum is solved, and the accuracy of the fault probability risk level is improved.

Description

technical field [0001] The invention relates to a method for analyzing fault alarm information of a wind farm, which is based on a deep Boltzmann machine and a probabilistic neural network algorithm to divide the fault probability risk, thereby improving the accuracy of fault risk early warning, and specifically relates to a method based on a small sample Data deep learning analysis method for wind power warning information. Background technique [0002] With the rapid development of wind energy and the putting into operation of large-scale wind turbines, and because most of the turbines are installed in remote areas and the load is unstable, many wind turbines in my country have experienced operational failures, which directly affect the safety of wind power generation. and economy. In order to maintain the long-term stable development of wind power and enhance its competitiveness with traditional energy sources, the cost of wind power must be continuously reduced. [0003...

AI Technical Summary

Problems solved by technology

[0003] Due to the late start of my country's wind power generation business, the research on early warning of wind turbine failure risk is still in its infancy, and the effective early warning of wind turbine failure is the main problem now. The risk of wind turbine failure is mainly related to electrical systems and control systems. Related to the external environment such as wind speed, the above data types are different and the interrelationships are complex

At present, the commonly used fault warning methods include artificial neural network, fuzzy set theory and evidence theory. Although the methods listed above can use different algorithms to calculate the fault information of diagnostic uncertainty, their conclusions are far from the actual situation.

Images