Diagnosis of wind turbine faults with transfer learning algorithms

被引：118

作者：

Chen, Wanqiu ^{[1
]}

Qiu, Yingning ^{[1
]}

Feng, Yanhui ^{[1
]}

Li, Ye ^{[2
]}

Kusiak, Andrew ^{[3
]}

机构：

[1] Nanjing Univ Sci & Technol, Sch Energy & Power Engn, 200 Xiao Ling Wei, Nanjing 210094, Peoples R China

[2] Shanghai Jiao Tong Univ, Dept Naval Architecture & Ocean Engn, Shanghai 200240, Peoples R China

[3] Univ Iowa, Dept Ind & Syst Engn, 4627 Seamans Ctr, Iowa City, IA 52242 USA

来源：

RENEWABLE ENERGY | 2021年 / 163卷

基金：

国家重点研发计划; 中国国家自然科学基金;

关键词：

Wind turbine; Transfer learning; Fault diagnosis; SCADA data; SCADA DATA;

D O I：

10.1016/j.renene.2020.10.121

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

A framework of using transfer learning algorithms, Inception V3 and TrAdaBoost, for fault diagnosis of two wind turbine faults is presented and verified. Two failure modes, blade icing accretion and gear cog belt fracture, are analyzed using SCADA data. A new index named 'Comprehensive Index' is defined to evaluate performance of different algorithms. Traditional machine learning algorithms do not perform well for data sets that are unbalanced and follow different distributions. The former causes bias in classification and the latter leads to poor adaptability of algorithms. A novel transfer learning algorithm studied in this paper, TrAdaBoost, has been proved to have superior performance on dealing with data imbalance and different distributions. A new approach to calibrate data labels using transfer learning algorithms is also proposed, which provides important insights into unsupervised learning for wind turbine fault diagnosis. (c) 2020 Elsevier Ltd. All rights reserved.

引用

页码：2053 / 2067

页数：15

共 34 条

[1]

Abadi M., 2015, Large-Scale Machine Learning on Heterogeneous Systems

[2] Random forests [J].