Defect identification of wind turbine blades based on defect semantic features with transfer feature extractor

Abstract The monitoring of the status of the wind turbine blades is significant for the wind generation system and currently mainly dependent on manual visual inspections. The variance of the blade defects and the lack of the blade defect images make the defect identification of the wind turbine blades challenging. This paper proposes a defect identification method of wind turbine blades based on defect semantic features with transfer feature extractor. A deep convolutional neural network (DCNN) is built and is trained on the ImageNet Large Scale Visual Recognition Challenge dataset. The deep hierarchical features of the training blade images are extracted by the trained DCNN and fed into a classifier. By training on the labeled blade images, the first n layers of the trained DCNN is selected as the transfer feature extractor to extract the defect semantic features and the defect classifier is also obtained. The blade images can be diagnosed by the defect classifier based on the defect semantic features. The experiments are conducted on a real dataset of wind turbine blade images. The experimental results demonstrate the high learning ability of the proposed method from the small samples and its effectiveness for the defect identification of wind turbine blades.

[1]  Yingning Qiu,et al.  Wind turbine condition monitoring: technical and commercial challenges , 2014 .

[2]  Michael Unser,et al.  Steerable Wavelet Machines (SWM): Learning Moving Frames for Texture Classification , 2017, IEEE Transactions on Image Processing.

[3]  Yang Zhang,et al.  Multiwavelet Packet Entropy and its Application in Transmission Line Fault Recognition and Classification , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Shibin Wang,et al.  Composite Damage Detection Based on Redundant Second-Generation Wavelet Transform and Fractal Dimension Tomography Algorithm of Lamb Wave , 2013, IEEE Transactions on Instrumentation and Measurement.

[5]  E. Romero,et al.  Rotation invariant texture characterization using a curvelet based descriptor , 2011, Pattern Recognit. Lett..

[6]  James A. Sherwood,et al.  Damage detection and full surface characterization of a wind turbine blade using three-dimensional digital image correlation , 2013 .

[7]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[8]  Yan Liang,et al.  Bias estimation for asynchronous multi-rate multi-sensor fusion with unknown inputs , 2018, Inf. Fusion.

[9]  Yi Qin,et al.  The Optimized Deep Belief Networks With Improved Logistic Sigmoid Units and Their Application in Fault Diagnosis for Planetary Gearboxes of Wind Turbines , 2019, IEEE Transactions on Industrial Electronics.

[10]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Zhengming Ma,et al.  Face recognition based on the fusion of global and local HOG features of face images , 2014, IET Comput. Vis..

[12]  Mehdi Behzad,et al.  Modal-based damage identification for the nonlinear model of modern wind turbine blade , 2016 .

[13]  A. Belousov,et al.  A flexible classification approach with optimal generalisation performance: support vector machines , 2002 .

[14]  Yanwen Chong,et al.  Pedestrian detection based on gradient and texture feature integration , 2017, Neurocomputing.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  A. Rosenfeld,et al.  Texture Primitive Extraction Using an Edge-Based Approach , 1979 .

[17]  Jing Shi,et al.  Fine tuning support vector machines for short-term wind speed forecasting , 2011 .

[18]  Kazuro Kageyama,et al.  Process/health monitoring for wind turbine blade by using FBG sensors with multiplexing techniques , 2008, International Conference on Optical Fibre Sensors.

[19]  Huijun Gao,et al.  A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis , 2019, Neurocomputing.

[20]  Harris Drucker,et al.  Learning algorithms for classification: A comparison on handwritten digit recognition , 1995 .

[21]  Bin Yang,et al.  Testing, inspecting and monitoring technologies for wind turbine blades: A survey , 2013 .

[22]  Monika Sharma,et al.  Automatic texture defect detection using Gaussian mixture entropy modeling , 2017, Neurocomputing.

[23]  Siva Sivoththaman,et al.  MEMS Multisensor Intelligent Damage Detection for Wind Turbines , 2015, IEEE Sensors Journal.

[24]  Giles M. Foody,et al.  Feature Selection for Classification of Hyperspectral Data by SVM , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Zijun Zhang,et al.  Automatic Detection of Wind Turbine Blade Surface Cracks Based on UAV-Taken Images , 2017, IEEE Transactions on Industrial Electronics.

[26]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[27]  A. Majumdar,et al.  Opportunities and challenges for a sustainable energy future , 2012, Nature.

[28]  Yiding Wang,et al.  Local feature approach to dorsal hand vein recognition by Centroid-based Circular Key-point Grid and fine-grained matching , 2017, Image Vis. Comput..

[29]  Quan Pan,et al.  The joint optimal filtering and fault detection for multi-rate sensor fusion under unknown inputs , 2016, Inf. Fusion.

[30]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[31]  Gert Frolund Pedersen,et al.  Investigation of a UWB Wind Turbine Blade Deflection Sensing System With a Tip Antenna Inside a Blade , 2016, IEEE Sensors Journal.

[32]  Bruno Rocha,et al.  Load monitoring of aerospace structures utilizing micro-electro-mechanical systems for static and quasi-static loading conditions , 2012 .

[33]  Feng Jia,et al.  An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data , 2016, IEEE Transactions on Industrial Electronics.

[34]  A. G. Dutton,et al.  Acoustic Emission Monitoring of Small Wind Turbine Blades , 2002 .

[35]  Jung-Ryul Lee,et al.  Structural health monitoring for a wind turbine system: a review of damage detection methods , 2008 .

[36]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[38]  Gunner Chr. Larsen,et al.  Fundamentals for remote structural health monitoring of wind turbine blades - a preproject , 2002 .

[39]  Trygve Randen,et al.  Filtering for Texture Classification: A Comparative Study , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  P. Green,et al.  Measuring perceived differences in surface texture due to changes in higher order statistics. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[41]  Seong-Whan Lee,et al.  Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis , 2014, NeuroImage.

[42]  Fu-Kuo Chang,et al.  Adhesive interface layer effects in PZT-induced Lamb wave propagation , 2010 .

[43]  Yong Luo,et al.  Multiview Vector-Valued Manifold Regularization for Multilabel Image Classification , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[44]  Xiaodong Liu,et al.  Adaptive neuro-fuzzy algorithm to estimate effective wind speed and optimal rotor speed for variable-speed wind turbine , 2018, Neurocomputing.

[45]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[46]  Katerina Krebber,et al.  Fiber Bragg grating sensors for monitoring of wind turbine blades , 2005, International Conference on Optical Fibre Sensors.

[47]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[48]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.