Online fan blade damaging real-time diagnosis system and method

Abstract

The invention provides an online fan blade damaging real-time diagnosis system and method, and belongs to the technical field of damage diagnosis of fan blades. The system comprises a quad-rotor unmanned plane, a cloud database and a computer system; the quad-rotor unmanned plane captures the images of the fan blades in real time and transmits the images to the computer system in real time; the cloud database stores an image library used for a VGG-19 net image classification method, and images in the image library stored in the cloud database are dynamically captured from a network; the computer system is used for obtaining an improved VGG-19 net image classification method through training of the image library, and the received fan blade images from the quad-rotor unmanned aerial vehicle are classified by using the improved VGG-19 net image classification method to obtain fan blade damage diagnosis classification and damage grade classification results.

Description

technical field [0001] The invention relates to the field of fan blade damage diagnosis, in particular to an online fan blade damage real-time diagnosis system and method. Background technique [0002] There are many fan blade fault diagnosis schemes in the prior art, but each existing scheme has certain shortcomings. Invention patent application CN107144569A proposes a fan blade fault diagnosis method based on SVM classification algorithm of selective search segmentation and deep convolutional neural network as feature extractor. First, it performs selective search and segmentation on the image to be detected to obtain candidate regions; then, it trains a deep convolutional neural network through the ImageNet image set, and extracts the network structure except the output layer as a feature extractor; finally, the extracted fan The features of the blade image are used to train the SVM classifier to complete the fault diagnosis task. It has the following defects: For the f...

AI Technical Summary

Problems solved by technology

It has the following defects: For the fault diagnosis algorithm of fan blade images, this method proposes to use Imagenet images as training data to determine the structural parameters of the deep convolutional network.

It has the following defects: This method proposes to use unmanned helicopters to carry light, heat, and acoustic signal acquisition devices to collect data on fan blades. Unmanned helicopters are not very stable in performing data acquisition tasks in windy environments, and their structures are complex. , high vibration and noise during operation, large maintenance workload, high cost of use, and poor battery life, it can be seen that it is not completely suitable for this task

It has the following defects: In the fault detection method of wind power blades, Alexnet is used to classify the damage of wind turbine blades based on images, and the Alexnet classification method is a classification method with a relatively simple structure, and this method only detects blade coating peeling, cracks, trachoma, etc. Three types of damage are detected, and the accuracy of damage grade results is not high

Images