Self-encoding neural network-based wind turbine visual detection system

Abstract

The present invention discloses a self-encoding neural network-based wind turbine visual detection system. According to the system, a part of frames of wind turbine images in an unmanned aerial vehicle aerial video are pre-processed, and the pre-processed images constitute a training sample set and a test sample set for wind turbine visual detection; a self-encoding neural network is built; positive and negative samples in the training sample set are arranged in a self-encoder so as to be pre-trained; an activation quantity which is obtained through calculation is adopted to replace original input, so that a new sample feature set is formed; new feature vectors are inputted to an established BP neural network, so that the two-pass classifier of a wind turbine can be obtained; the sample images in the test set are arranged in the classifier so as to be tested; areas containing the wind turbine are searched through using a random sliding window method; and screening is performed throughnon-maximum suppression, so that a final wind turbine detection area can be obtained. The system of the invention can be widely applied to fields such as pattern recognition and intelligent inspectionof wind power generation.

Description

technical field [0001] The invention relates to a fan visual detection system. Background technique [0002] The area where wind turbines are usually located is tidal flats or offshore, with wide distribution, complex working conditions, and harsh working environment. It is difficult to ensure the efficiency and safety of staff only by means of manual inspection. In addition, the installed capacity of wind turbines is expanding year by year. , which will undoubtedly increase the difficulty of condition monitoring and optimal maintenance of wind turbines. Therefore, it is necessary to use drone technology to monitor the operating status of wind turbines by aerial photography, and use computer technology to realize visual inspection of wind turbines and improve the reliability of wind turbine detection. In recent years, scholars at home and abroad have carried out a lot of research work on wind turbine identification, mainly using acoustic emission technology and infrared the...

AI Technical Summary

Problems solved by technology

In recent years, scholars at home and abroad have carried out a lot of research work on wind turbine identification, mainly using acoustic emission technology and infrared thermal imaging technology to complete the health monitoring of wind turbines. There are still few researches based on artificial neural networks.

Images