Wind generating set paddle monitoring flaw detection method

Abstract

The invention discloses a wind generating set blade monitoring flaw detection method. Specific to the characteristics of fan blade acquisition images of an unmanned aerial vehicle, an unmanned aerial vehicle camera calibration method, a fast adaptive weighted median filtering algorithm, an image enhancement algorithm, blade surface fault feature extraction and selection, and blade surface fault classification monitoring and identification are used, and embedded into a man-machine interaction platform. Through online and offline tests, the platform can realize automatic identification and monitoring of sand holes, cracks, peeling and other defects, and the accuracy can reach 90% or above; compared with traditional monitoring means and other monitoring algorithms, the platform has higher accuracy and higher algorithm stability; and a new way is provided for nondestructive monitoring of wind driven generator blades.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for monitoring and detecting flaws of a blade of a wind power generating set. Background technique [0002] The blades in wind turbines are the key components for wind turbines to capture wind energy, and the troubleshooting time of blades accounts for the highest proportion of the entire wind turbine troubleshooting time. Since the wind farms are mainly distributed in the outer suburbs of the city, offshore and Gobi and other wind energy reserves with complex geographical and climatic environments, the blades of wind turbines are also inevitably impacted by various disasters such as hurricanes and salt spray; The surface is inevitably damaged by various media to form various defects and damages. If these small defect damages are not paid attention to and dealt with in time, they will form large faults after continuous accumulation, and eventually turn into ser...

AI Technical Summary

Problems solved by technology

Both cases will cause serious damage to the blades, and even the fan will be shut down for maintenance

[0004] Using a fan blade surface monitoring and defect identification system based on vibration sensors, acoustic emission sensors, strain sensors, and ultrasonic sensors, the piezoceramic sensor sheet coupled to the blade is used to excite the vibration response of the blade, and through the transmission function, resonance Comparing, operating distorted shape and wave propagation and other methods to monitor the damage of the blade, the accuracy, speed and safety of the above-mentioned monitoring and detection are limited, and the monitoring and detection has low efficiency, unreliable results and high risk technical issues such as high cost

Images