Wind turbine blade surface inspection based on deep learning and UAV-taken images

2019 ◽  
Vol 11 (5) ◽  
pp. 053305
Author(s):  
Donghua Xu ◽  
Chuanbo Wen ◽  
Jihui Liu
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Surface Inspection ◽  
Blade Surface

scholarly journals Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification

2021 ◽  
Vol 7 (3) ◽  
pp. 46
Author(s):  
Jiajun Zhang ◽  
Georgina Cosma ◽  
Jason Watkins
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Defect Detection ◽  
Recognition Rate ◽  
Weighted Average ◽  
Wind Turbine Blade ◽  
Evaluation Measures ◽  
Augmentation Techniques ◽  
The Mean

Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification.

Research on Wind Turbine Blade Surface Damage Fault On-Line Monitoring and Diagnosis System

2013 ◽  
Author(s):  
Yongxin Feng ◽  
Tao Yang ◽  
Xiaowen Deng ◽  
Qingshui Gao ◽  
Chu Zhang ◽  
...  
Keyword(s):  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Farm ◽  
Turbine Blades ◽  
Surface Damage ◽  
Wind Turbine Blade ◽  
Offshore Wind ◽  
Blade Surface ◽  
Diagnosis System ◽  
On Line

The basic fault types of wind turbine blades are introduced, a novel blade surface damage detection method based on machine vision is being suggested. The network of wind turbine blade surface damage fault on-line monitoring and fault diagnosis system has already been developed. The system architecture, software modules and functions are described, and given application example illustrates the usefulness and effectiveness of this system. The result shows that this system can monitor the surface damage failure of the blade in real time, and can effectively reduce the blade’s maintenance costs for wind farms, especially offshore wind farm.

Performance Investigation of Non-Linear Insulator against Surface Tracking on Wind Turbine Blade Surface

2014 ◽  
Vol 911 ◽  
pp. 190-194
Author(s):  
Watthanapong Sasimma ◽  
Amnart Suksri
Keyword(s):  
Zinc Oxide ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Saline Solution ◽  
Research Work ◽  
Aluminium Oxide ◽  
Wind Turbine Blade ◽  
Blade Surface ◽  
Surface Tracking ◽  
Modified Epoxy

This research work investigates the surface degradation of wind turbine blade surface insulator which is made from modified epoxy resin mixed with Zinc oxide (ZnO) and Aluminium oxide (Al2O3) in different percentage as a filler elements. Accelerated test with AC voltage of 4.5 kV 50 Hz with NH4Cl saline solution using flow rate of contaminant equals to 0.6 ml/min according to IEC 60587 standard. It was found that, the solid insulators which has 30 % of Zinc oxide (ZnO) and 20% of Aluminium oxide (Al2O3) fillers prolong the process of surface tracking to the order of 5.41 for Zinc oxide (ZnO) filler and also to the order of 30.68 for Aluminium oxide (Al2O3) filler. On the other hand, if the amount of Aluminium oxide (Al2O3) filler is more than 20% by weight, it will lead to a rapid tracking phenomena.

scholarly journals Design and Analysis of Dimple Arrangement on a Small Wind Turbine Blade

2019 ◽  
Vol 9 (2) ◽  
pp. 3552-3557
Keyword(s):  
Wind Turbine ◽  
Turbine Blade ◽  
Aerodynamic Performance ◽  
Wind Turbine Blade ◽  
Performance Estimation ◽  
Cfd Analysis ◽  
Blade Surface ◽  
Ansys Fluent ◽  
Small Wind Turbine ◽  
Overall Performance

This article predominantly focuses on the performance estimation of a small wind turbine blade when a dimple arrangement is made along its upper surface. The dimple arrangement is grooved at two locations: 0.25c and 0.5c, where c is the chord length of the turbine blade. A CFD analysis using the k-ε turbulence model is carried out on the selected blade sections NREL S823 and S822. The continuity and momentum equations are solved using ANSYS Fluent Solver to assess the aerodynamic performance of the proposed design. The effect of introducing a dimple on the blade surface has shown to delay the flow separation, with the formation of vortices. Further, the overall performance of the blade is simulated using GH BLADED and the results acquired are discussed.

scholarly journals An Imbalance Fault Detection Algorithm for Variable-Speed Wind Turbines: A Deep Learning Approach

Energies ◽  
2019 ◽  
Vol 12 (14) ◽  
pp. 2764 ◽  
Author(s):  
Jianjun Chen ◽  
Weihao Hu ◽  
Di Cao ◽  
Bin Zhang ◽  
Qi Huang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fault Detection ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Short Term Memory ◽  
Wind Farms ◽  
Detection Algorithm ◽  
Wind Turbine Blade ◽  
Mathematical Methods ◽  
Time Series Simulation

Wind power penetration has increased rapidly in recent years. In winter, the wind turbine blade imbalance fault caused by ice accretion increase the maintenance costs of wind farms. It is necessary to detect the fault before blade breakage occurs. Preliminary analysis of time series simulation data shows that it is difficult to detect the imbalance faults by traditional mathematical methods, as there is little difference between normal and fault conditions. A deep learning method for wind turbine blade imbalance fault detection and classification is proposed in this paper. A long short-term memory (LSTM) neural network model is built to extract the characteristics of the fault signal. The attention mechanism is built into the LSTM to increase its performance. The simulation results show that the proposed approach can detect the imbalance fault with an accuracy of over 98%, which proves the effectiveness of the proposed approach on wind turbine blade imbalance fault detection.

scholarly journals Defect Monitoring of a Wind Turbine Blade Surface by using Surface Wave Damping

2017 ◽  
Vol 23 (1) ◽  
pp. 90-94
Author(s):  
Kyung-Hwan Kim ◽  
Young-Jin Yang ◽  
Hyun-Bum Kim ◽  
Hyung-Chan Yang ◽  
Jong-Hwan Lim ◽  
...  
Keyword(s):  
Surface Wave ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Wind Turbine Blade ◽  
Blade Surface ◽  
Wave Damping
Sign in / Sign up

Export Citation Format

Share Document