Fault early warning method for double-fed fan main shaft

Abstract

The invention relates to a fault early warning method for a double-fed fan main shaft. The method comprises the following steps: selecting main shaft temperature and temperature related data of main shaft related parts from fan equipment; selecting features with high correlation with the spindle temperature from the original data set by adopting a Pearson correlation coefficient; optimizing parameters in the LightGBM prediction model by using a whale algorithm to obtain an optimized LightGBM normal main shaft temperature prediction model; inputting the test set data into the optimized LightGBM normal main shaft temperature prediction model to obtain a corresponding main shaft temperature prediction value, and performing residual analysis to obtain a main shaft temperature early warning threshold; and selecting characteristic data with relatively high correlation with the spindle temperature from the fan data to be early warned, inputting the characteristic data into the optimized LightGBM normal spindle temperature prediction model to obtain a current fan spindle temperature prediction value to be early warned, and performing residual analysis to judge a spindle temperature state so as to achieve early warning of a fan spindle fault.

Description

technical field [0001] The invention relates to a fault early warning method, in particular to a double-fed fan main shaft fault early warning method, especially a fan main shaft fault early warning method based on an improved whale algorithm to optimize LightGBM. Background technique [0002] As wind energy, as a renewable clean energy, is widely developed and utilized by various countries, the installed capacity of wind turbines continues to increase. Because wind turbines usually work in harsh environments and complex wind changes, resulting in frequent failures of wind turbines, effective early warning of key component failures in wind turbines has gradually attracted attention. As one of the important components of the wind turbine, the main shaft is also a part of the unit that frequently fails. A failure of the main shaft may even cause the entire wind turbine to fail to operate normally. Therefore, effective fault warning before the main shaft fault is of great sign...

AI Technical Summary

Problems solved by technology

[0004] Traditional wind turbine fault early warning is generally realized by setting a single constant early warning threshold. This invention aims at the problem that the constant threshold early warning cannot meet the early warning requirements under complex working conditions, and proposes a wind turbine main shaft fault early warning method based on the improved whale algorithm to optimize LightGBM

Images