PDF
Full
Outline
Aiming at the problem of lack of a large number of actual fault image training samples during the fault diagnosis and modeling of offshore wind turbine blades, an image recognition method for offshore wind turbine blade faults based on small data sets is proposed. In this method, the Kmeans clustering algorithm is improved to identify blade segmentation according to the color and shape characteristics of blades and their faults in wind turbine blade images, an adaptive algorithm is designed to adjust the Canny operator parameters to identify the segmentation of early fault areas on the blade surface, and the Kmeans clustering algorithm is used to extract the color and shape features of faults and design corresponding classifiers to achieve fault classification. Simulation examples show that this method is effective for the identification of early faults on the blade surface, and can provide an accurate diagnostic model for the blade fault identification of offshore wind turbines on the basis of a small number of fault samples, which can improve the operation and maintenance efficiency of offshore wind farms.
PDF
286
147
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
