Automatic detection of icing wind turbine using deep learning method

다국어 초록 (Multilingual Abstract)

Detecting the icing on wind turbine blades built-in cold regions with conventional methods is always a very laborious, expensive and very difficult task. Regarding this issue, the use of smart systems has recently come to the agenda. It is quite possible to eliminate this issue by using the deep learning method, which is one of these methods. In this study, an application has been implemented that can detect icing on wind turbine blades images with visualization techniques based on deep learning using images. Pre-trained models of Resnet-50, VGG-16, VGG-19 and Inception-V3, which are well-known deep learning approaches, are used to classify objects automatically. Grad-CAM, Grad-CAM++, and Score-CAM visualization techniques were considered depending on the deep learning methods used to predict the location of icing regions on the wind turbine blades accurately. It was clearly shown that the best visualization technique for localization is Score-CAM. Finally, visualization performance analyses in various cases which are close-up and remote photos of a wind turbine, density of icing and light were carried out using Score-CAM for Resnet-50. As a result, it is understood that these methods can detect icing occurring on the wind turbine with acceptable high accuracy

참고문헌 (Reference)

1 Godreau, C., "Wind turbine rotor icing detectors performance evaluation" 2019

2 Gao, L., "Wind turbine performance in natural icing environments : A field characterization" 181 : 103193-, 2021

3 Poppy, "Wind turbine Reading’s landmark wind turbine was completed Flickr"

4 Piqsels, "Wind Turbine, Wind Energy, Turn, Power Generation, Wind Generator, Renewable, Propeller, Wind Power, |Piqsels"

5 Simonyan, K., "Very deep convolutional networks for large-scale image recognition" 1-14, 2015

6 Shu, L., "Study of ice accretion feature and power characteristics of wind turbines at natural icing environment" 147 : 45-54, 2018

7 Yan, Q., "Sea ice sensing from GNSS-R data using convolutional neural networks" 15 : 1510-1514, 2018

8 Xu, Y., "Sea ice and open water classification of sar imagery using cnnbased transfer learning" 5-8, 2017

9 Wang, H., "Score-CAM: Score-weighted visual explanations for convolutional neural networks" 111-119, 2020

10 Antikainen, P., "Retrofitting Anti-icing Blade Heating on Installed Wind Turbines" 2018

11 Szegedy, C., "Rethinking the Inception Architecture for Computer Vision" IEEE Computer Society 2818-2826, 2016

12 Xu, J., "Predicting fan blade icing by using particle swarm optimization and support vector machine algorithm" 87 : 106751-, 2020

13 Sarlak, H., "Numerical simulation of icethrow from wind turbines in cold climate" 2018

14 Antikainen, "Megaterends in Blade Heating" 2020

15 Kreutz, M., "Machine learning-based icing prediction on wind turbines" 423-428, 2019

16 Chen, L., "Learning deep representation of imbalanced SCADA data for fault detection of wind turbines" 139 : 370-379, 2019

17 Ummers, M., "Is wind industry ready for disruptive slutions?" 2019

18 Kreutz, M., "Investigation of icing causes on wind turbine rotor blades using machine learning models, minimalistic input data and a full-factorial design" 52 : 168-173, 2020

19 Jiang, W., "Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data"

20 Krizhevsky, B. A., "ImageNet classification with deep convolutional neural networks" 60 : 84-90, 2017

21 Kreutz, M., "Ice detection on rotor blades of wind turbines using RGB images and convolutional neural networks" 93 : 1292-1297, 2020

22 Kaikkonen, V., "Ice and snow management innovations for critical infrastructure" 2020

23 Wadham-Gagnon, M, "Ice Protection System Performance Assessment Methodology" 2018

24 Rizk, P., "Hyperspectral imaging applied for the detection of wind turbine blade damage and icing" 18 : 100291-, 2020

25 Hughes, M. J., "High-quality cloud masking of landsat 8 imagery using convolutional neural networks" 11 : 2019

26 Salman, H., "Hierarchical reinforcement learning for sequencing behaviors" 2733 : 2709-2733, 2018

27 Chattopadhay, A., "Grad-CAM++ : Generalized gradient-based visual explanations for deep convolutional networks" 839-847, 2018

28 Selvaraju, R. R., "Grad-CAM : Visual explanations from deep networks via gradient-based localization" 128 : 336-359, 2020

29 Freytag, R., "Early Information of Potential Icing and Measuring of Icing Events" 2020

30 Son, C., "Development of an icing simulation code for rotating wind turbines" 203 : 104239-, 2020

31 He, K., "Deep residual learning for image recognition" 770-778, 2016

32 LeCun, Y., "Deep learning" 51 : 436-444, 2015

33 Karpathy, A., "Convolutional Neural Networks (CNNs /ConvNets). Retrieved CS231n Convolutional Neural Networks for Visual Recognition"

34 Han, H., "Borderline-SMOTE:A new over-sampling method in imbalanced data sets learning" 878-887, 2005

35 Dong, X., "Blades icing identification model of wind turbines based on SCADA data" 162 : 575-586, 2020

36 Froidevaux, P., "Benchmark of four Blade-based Ice Detection Systems" 2019

37 Hacıefendioğlu, K., "Automatic detection of earthquake-induced ground failure effects through Faster R-CNN deep learning-based object detection using satellite images" 105 : 383-403, 2021

38 Parent, O., "Anti-icing and de-icing techniques for wind turbines : Critical review" 65 : 88-96, 2011

39 Stoyanov, D. B., "Alternative operational strategies for wind turbines in cold climates" 145 : 2694-2706, 2020

40 Madi, E., "A review of integrating ice detection and mitigation for wind turbine blades" 103 : 269-281, 2019

41 Ullo, S. L., "A new mask R-CNN based methoqd for improved landslide detection" 2020

42 Yu, H., "A landslide intelligent detection method based on CNN and RSGR" Institute of Electrical and Electronics Engineers Inc 40-44, 2017