Fault Early Warning of Wind Turbine Gearbox Based on Machine Learning

At present, high frequency vibration data of wind turbine gearbox is collected through condition monitoring system and fault diagnosis for gearbox is made by manual analysis. But this method requires vibration analysis engineers with sufficient experience knowledge. And because of the large number o...

Full description

Saved in:
Bibliographic Details
Main Authors: CHEN Yanan, HU Kaikai, CHEN Gang, SHU Hui, LI Ziyuan
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2021-01-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2021.05.018
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:At present, high frequency vibration data of wind turbine gearbox is collected through condition monitoring system and fault diagnosis for gearbox is made by manual analysis. But this method requires vibration analysis engineers with sufficient experience knowledge. And because of the large number of units, manual analysis will be time-consuming and laborious. In this paper, frequency conversion and alignment of the original data collected are carried out to eliminate the influence of changing working conditions. Data samples are amplified by time-long segmentation, and time domain and frequency domain features of a specific frequency doubling section are extracted as the input of machine learning. Through model training, a gearbox fault prediction model is constructed. The accuracy of the model is more than 90%, which effectively realizes the gearbox fault prediction.
ISSN:2096-5427