US 2020/0402220 A1 · ON-LINE REAL-TIME DIAGNOSIS SYSTEM AND METHOD FOR WIND TURBINE BLADE (WTB) DAMAGE

Abstract

The present invention provides an on-line real-time diagnosis system and method for wind turbine blade (WTB) damage. The system includes a four-rotor unmanned aerial vehicle (UAV), a cloud database, and a computer system. The four-rotor UAV captures images of WTBs in real time, and transmits the images to the computer system. The cloud database stores an image library used for a Visual Geometry Group (VGG)-19 net image classification method, where an image in the image library stored in the cloud database is dynamically captured from a network. The computer system is used to perform training by using the image library to obtain an improved VGG-19 net image classification method, and classify, by using the improved VGG-19 net image classification method, the images of the WTBs received from the four-rotor UAV, to obtain a WTB damage diagnosis and classification result and a damage grading result.

Claims15

Dependent claims

An on-line real-time diagnosis system for wind turbine blade (WTB) damage, the on-line real-time diagnosis system comprising:

a four-rotor unmanned aerial vehicle (UAV);
a cloud database;
and
a computer system;
wherein the four-rotor UAV captures images of WTBs in real time, and transmits the images to the computer system;
wherein the cloud database stores an image library used for a Visual Geometry Group (VGG)-19 net image classification method, wherein an image in the image library stored in the cloud database is dynamically captured from a network;
and
wherein the computer system is used to perform training by using the image library to obtain an improved VGG-19 net image classification method, and classify, by using the improved VGG-19 net image classification method, the images of the WTBs received from the four-rotor UAV, to obtain a WTB damage diagnosis result and a damage grading result.

5 more elements

A on-line real-time diagnosis method for wind turbine blade (WTB) damage, the on-line real-time diagnosis method comprising:

collecting, by a four-rotor unmanned aerial vehicle (UAV), images of WTBs, and transmitting the collected images to a computer system;
training a Visual Geometry Group (VGG)-19 net model in an improved VGG-19 net image classification method by using a dynamically updated training and testing image library provided by a cloud database;
receiving, by the computer system, the collected images, and classifying the images by using the VGG-19 net image classification method;
and
outputting, by the computer system, a blade damage state based on an image classification result.

2 more elements

Dependencies are inferred from the claim text.

On-line real-time diagnosis system and method for wind turbine blade (wtb) damage

Life of this patent

On-line real-time diagnosis system and method for wind turbine blade (wtb) damage

Life of this patent

Abstract

Claims15