Achieving robust damage mode identification of adhesive composite joints for wind turbine blade using acoustic emission and machine learning

2020 ◽  
Vol 236 ◽  
pp. 111840 ◽  
Author(s):  
D. Xu ◽  
P.F. Liu ◽  
Z.P. Chen ◽  
J.X. Leng ◽  
L. Jiao
Keyword(s):  
Machine Learning ◽  
Acoustic Emission ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Composite Joints ◽  
Damage Mode ◽  
Mode Identification

Damage mode identification of composite wind turbine blade under accelerated fatigue loads using acoustic emission and machine learning

2019 ◽  
Vol 19 (4) ◽  
pp. 1092-1103 ◽  
Author(s):  
Pengfei Liu ◽  
Dong Xu ◽  
Jingguo Li ◽  
Zhiping Chen ◽  
Shuaibang Wang ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Mode Identification ◽  
Emission Signal ◽  
Composite Blade ◽  
Acoustic Emission Sensors ◽  
Safety Precaution ◽  
Fatigue Loads

This article studies experimentally the damage behaviors of a 59.5-m-long composite wind turbine blade under accelerated fatigue loads using acoustic emission technique. First, the spectral analysis using the fast Fourier transform is used to study the components of acoustic emission signals. Then, three important objectives including the attenuation behaviors of acoustic emission waves, the arrangement of sensors as well as the detection and positioning of defect sources in the composite blade by developing the time-difference method among different acoustic emission sensors are successfully reached. Furthermore, the clustering analysis using the bisecting K-means method is performed to identify different damage modes for acoustic emission signal sources. This work provides a theoretical and technique support for safety precaution and maintaining of in-service blades.

scholarly journals A data enlargement strategy for fault classification through a convolutional auto-encoder

2019 ◽  
Vol 255 ◽  
pp. 05001
Author(s):  
Cui Hao ◽  
Wang Kesheng ◽  
Li Yu ◽  
Yang Binyuan ◽  
miao Qiang
Keyword(s):  
Machine Learning ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Machine Learning Techniques ◽  
Fault Classification ◽  
Energy Harvest ◽  
Operational Conditions ◽  
Learning Techniques ◽  
Enlargement Strategy

The amount of data is of crucial to the accuracy of fault classification through machine learning techniques. In wind energy harvest industry, due to the shortage of faulty data obtained in real practice, together with ever changing operational conditions, fault detection and evaluation of wind turbine blade problems become intractable through conventional machine learning methods. In this paper, a modified unsupervised learning method, namely a convolutional auto-encoder based data enlargement strategy (ABE) is proposed for wind turbine blade fault classification. Limited simulation results for different levels of wind turbine icy blades are used for investigation. First, convolutional auto encoder is used to increase the amount of the data. Then, decision tree based xgboost tool, as an example, is used to demonstrate the effectiveness of data enlargement strategy for fault classification. The study shows that the proposed data enlargement strategy is an effective method to improve the fault classification accuracy through machine learning techniques.

An Identification Method of Appearances and Expansion of Fatigue Crack in the Wind Turbine Blade Based on Fractal Feature

2012 ◽  
Vol 591-593 ◽  
pp. 2123-2126
Author(s):  
Bo Zhou ◽  
Chang Zheng Chen ◽  
Quan Gu ◽  
Huan Liu
Keyword(s):  
Acoustic Emission ◽  
Fractal Dimension ◽  
Fatigue Crack ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Correlation Dimension ◽  
Wind Turbine Blade ◽  
Crack Identification ◽  
Simplified Method ◽  
Fatigue Experiment

In this work an efficient and simplified method for crack identification in wind turbine blade has been developed based on fractal dimension. Firstly, the algorithm is studied on the calculation of the correlation dimension of acoustic emission signals, and an analysis of these equations makes it possible to identify cracks. Then it turns out that the complexity could vary with different crack expansion conditions, i.e. reduction and augmentation of the correlation dimension due to the occurrence of a crack by the fatigue experiment. Finally, the proposed detection methodology is compared to wavelet analysis. It is testified that the method exploits both the typical steady expansion of the crack and the appearance phenomenon due to the presence of crack.

scholarly journals Linear and nonlinear features and machine learning for wind turbine blade ice detection and diagnosis

2019 ◽  
Vol 132 ◽  
pp. 1034-1048 ◽  
Author(s):  
Alfredo Arcos Jiménez ◽  
Fausto Pedro García Márquez ◽  
Victoria Borja Moraleda ◽  
Carlos Quiterio Gómez Muñoz
Keyword(s):  
Machine Learning ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Nonlinear Features ◽  
Linear And Nonlinear ◽  
Detection And Diagnosis ◽  
Ice Detection
Sign in / Sign up

Export Citation Format

Share Document