Defect detection of large wind turbine blades based on image stitching and improved Unet network

Abstract

Aiming at the problem that the existing computer vision detection technology is difficult to comprehensively and carefully detect the damage status of large wind turbine blades due to the limitation of the field of view, this paper proposes a refined and multi-scale detection method for large-scale wind turbine blades by combining an image stitching algorithm and a deep learning network. First of all, combining the image stitching algorithm with image weighted fusion, images of large wind turbine blades shot in close range are stitched together, so as to realize the clear restoration of the full size and defects of the blades. On this basis, an improved Unet network VGG16Unet is proposed. Combined with transfer learning, the classification and detection of various defects on wind turbine blades under the condition of small dataset training are realized. Finally, by the aid of the combination of the image stitching algorithm and the semantic segmentation network, the refined damage detection of the overall structure of large wind turbine blades is implemented. The research shows that the mean pixel accuracy and the mean intersection over union of the VGG16Unet model are 95.33% and 85.20%, respectively, which is better than the classical semantic segmentation models, fully convolutional neural network model and Unet model. The combination of the VGG16Unet model and the image stitching algorithm not only realizes the global detection of the entire structure but also ensures the detailed detection of each local area, which makes the detection of large wind turbine blades more comprehensive and refined.