Fault early warning method for transmission system of wind turbine generator

Abstract

A fault early warning method for a transmission system of a wind turbine generator comprises the steps of firstly, acquiring wind turbine generator SCADA operation data, selecting health data of continuous operation, and completing related preprocessing of the data; then, constructing a long-short-term memory self-encoding model, and training the model by using a training set and a test set; and finally, verifying the reconstruction capability of the model by using a verification set, calculating a residual error between reconstructed data and original data, setting a threshold control line by using a kernel density estimation method, performing fault early warning when a reconstruction error is higher than a threshold, and judging a specific component with a fault according to the size of the reconstruction error and the time when the reconstruction error reaches the threshold. According to the method, the gating unit of the long and short-term memory network is combined with the de-noising self-encoding network, so that the internal space-time relevance of the data can be effectively captured, the characteristic information between the data and the characteristic information of the data in the time dimension can be better mined, and the reliability of fault early warning can be effectively improved.

Description

technical field [0001] The invention relates to a fault early warning method for a transmission system of a wind turbine. Background technique [0002] With the rapid development of social civilization, human demand for energy is gradually increasing, and it is imminent to solve the environmental problems caused by the consumption of fossil energy. Actively exploring and fully utilizing renewable energy has become an important issue facing countries all over the world. As a clean and renewable energy, wind energy has been developed and utilized on a large scale worldwide in recent years. According to statistics, my country's cumulative total installed capacity and annual installed capacity account for 35% and 37% of the world's total respectively, occupying a pivotal position in the entire wind power industry. [0003] Wind turbines are usually distributed in areas with abundant wind energy such as coastal areas and mountainous areas but with harsh natural conditions. The w...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of the complex coupling relationship of each component of the current wind turbine transmission system and the time dependence of each dimension of data in the operating data of the data acquisition and monitoring control system, this invention proposes a wind turbine based on long-term short-term memory self-encoding network Transmission system fault early warning method

Images