CN-117647526-B - Wind driven generator blade surface defect detection method and device

CN117647526BCN 117647526 BCN117647526 BCN 117647526BCN-117647526-B

Abstract

The present invention relates to the field of defect detection technology and discloses a method and device for detecting surface defects on wind turbine blades. The method for detecting surface defects on wind turbine blades provided by the present invention integrates multimodal data to improve defect detection accuracy and wind power generation efficiency.

Inventors

WU WENJIE
XU YANLI
YANG LEI
ZHANG XIAOMENG
JIANG PENG
JIN HEPING
Luo Huiheng
ZHANG CHANGAN
LI DELONG
WANG JINGHAN
LIU YUCE
ZHOU CHAOHUI
HU JINYAN

Assignees

中国长江三峡集团有限公司

Dates

Publication Date: 20260512
Application Date: 20231027

Claims (13)

1. A method for detecting surface defects of a wind turbine blade, the method comprising: acquiring an image of the blade surface of the wind driven generator and an ultrasonic reflection signal inside the blade, wherein the image of the blade surface comprises a visible light image and an infrared thermal image; Preprocessing the visible light image and the infrared thermal image respectively, and performing defect detection on the preprocessed visible light image and the preprocessed infrared thermal image respectively by using a preset image analysis model to generate wind driven generator blade surface defect data and thermal anomaly data; Preprocessing the ultrasonic reflection signals, and detecting defects of the preprocessed ultrasonic reflection signals to generate data of defects of the internal structure of the wind driven generator blade; Fusing the surface defect data, the thermal anomaly data and the data of defects of the internal structure of the wind driven generator blade by using a preset algorithm to finish the defect detection of the surface of the wind driven generator blade; fusing the defect data, the thermal anomaly data and the defect data of the internal structure of the wind driven generator blade to finish the defect detection of the surface of the wind driven generator blade, comprising: The K-means clustering algorithm is utilized to fuse the surface defect data, the thermal anomaly data and the defect data of the internal structure of the wind driven generator blade, the type and the depth of the surface defect of the wind driven generator blade are determined, and the defect detection of the surface of the wind driven generator blade is completed; according to the preset early warning level and the preset threshold value, carrying out early warning and alarming on the defect detection result of the surface of the wind driven generator blade, and sending an early warning signal to an operator, wherein the early warning method comprises the following steps: setting m cluster centers, wherein each cluster center represents a defect with preset defect type and depth; assigning a weight wi to each cluster center i, representing the severity of the type and depth of defect; The preset early warning level L is calculated by the following formula: L = ∑wi Ni wherein Ni represents the number of pixels belonging to the ith cluster center; Setting a preset threshold T, and sending an early warning signal to an operator when the preset early warning level L exceeds the preset threshold T.
2. The method of claim 1, wherein the step of performing defect detection of the surface of the wind turbine blade further comprises: and carrying out early warning and alarming on the defect detection result of the surface of the wind driven generator blade according to the preset early warning level and the preset threshold value, and sending an early warning signal to an operator.
3. The method of claim 1, wherein the detection device comprises an unmanned helicopter, a high definition camera, a thermal infrared imager, an ultrasound probe, and a cable, wherein, The high-definition camera, the infrared thermal imaging instrument and the ultrasonic detector are respectively and directly connected with the unmanned helicopter through cables; The high-definition camera is used for collecting visible light images; The thermal imager is used for collecting infrared thermal images; The ultrasonic detector is used for collecting ultrasonic reflection signals of the internal structure of the blade.
4. The method of claim 3, wherein the high definition camera, the infrared thermal imager and the ultrasound probe are all secured to the bottom of the unmanned helicopter.
5. The method of claim 4, wherein the unmanned helicopter is a six-axis stable multi-rotor unmanned helicopter.
6. The method of claim 5, wherein the unmanned helicopter flies around the wind turbine blades according to a predetermined flight path to complete the shooting and scanning of the wind turbine blades.
7. The method of claim 1, wherein the preprocessing the visible light image and the infrared thermal image, respectively, comprises: denoising the visible light image by using a Gaussian filter to enhance the quality of the visible light image; and carrying out contrast enhancement on the infrared thermal image by utilizing histogram equalization, carrying out median filtering treatment on the infrared thermal image with enhanced contrast, and determining a temperature difference region and a thermal anomaly region of the blade.
8. The method of claim 7, wherein the visible light image is denoised using a gaussian filter by: Ienh = G( ,σ) wherein Ienh denotes a denoised visible light image, G denotes a gaussian filter, σ denotes a standard deviation, Representing a visible light image.
9. The method of claim 7, wherein the infrared thermal image is contrast enhanced with histogram equalization by the formula: Wherein, the An infrared heat map after contrast enhancement is shown, An infrared thermal image is represented and is displayed, Representing a histogram equalization algorithm.
10. The method of claim 9, wherein the contrast enhanced infrared heat map is median filtered by the formula: Wherein, the Representing the infrared heat map after the median filtering process, Representing the median filtering algorithm, Representing the window size of the filter.
11. A wind turbine blade surface defect detection device, the device comprising: the acquisition module is used for acquiring images of the blade surface of the wind driven generator and ultrasonic reflection signals inside the blade, wherein the images of the blade surface comprise visible light images and infrared thermal images; The first detection module is used for respectively preprocessing the visible light image and the infrared thermal image, respectively detecting defects of the preprocessed visible light image and the preprocessed infrared thermal image by utilizing a preset image analysis model, and generating wind driven generator blade surface defect data and thermal anomaly data; the second detection module is used for preprocessing the ultrasonic reflection signals, detecting defects of the preprocessed ultrasonic reflection signals and generating data of defects of the internal structure of the wind driven generator blade; And the fusion module is used for fusing the surface defect data, the thermal anomaly data and the data of defects of the internal structure of the wind driven generator blade by using a preset algorithm to finish the defect detection of the surface of the wind driven generator blade.
12. A computer device, comprising: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of detecting a surface defect of a wind turbine blade according to any one of claims 1 to 10.
13. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the wind turbine blade surface defect detection method of any one of claims 1 to 10.

Description

Wind driven generator blade surface defect detection method and device Technical Field The invention relates to the technical field of defect detection, in particular to a method and a device for detecting surface defects of a blade of a wind driven generator. Background The wind driven generator is a power equipment which converts wind energy into mechanical work, the mechanical work drives a rotor to rotate, and finally, alternating current is output. The wind driven generator generally comprises a wind wheel, a generator (comprising a device), a steering gear (tail wing), a tower, a speed limiting safety mechanism, an energy storage device and other components, and in order to drive the wind wheel to rotate, wind is required to be captured through the generator blades so as to drive the wind wheel to rotate, so that the quality of the generator blades influences the working efficiency of the generator, and in order to ensure that the generator can work normally, the generator blades can be detected before the generator is installed, and defects on the surfaces of the wind driven generator blades are avoided. There are two current methods for detecting the blades of a generator: The method I is a manual visual inspection method, the visual inspection method is widely used for detecting large-size structural materials on spaceflight planes or bridges, and the method can also be used for generator blades. Because of the very large size of the construction material, the time required for visual inspection is relatively long, and the accuracy of the inspection is dependent on the experience of the inspection personnel. Because some materials belong to the field of 'high-altitude operation', the danger of the work of the detection personnel is high, the detection personnel is generally provided with a long-lens digital camera in the detection process, but the long-time detection process can cause eyestrain. Visual inspection can visually detect defects on the surface of a material, but defects of the internal structure cannot be detected, so that other effective means are required to evaluate the internal structure of the material. The second method is that the camera visual inspection is carried out by a special image processing system for machine visual products, and the visual inspection is to use a machine to replace human eyes for measurement and judgment. The visual detection means that a machine visual product (image pickup device: CMOS and CCD) is used for converting a picture of a picked-up wind driven generator blade into an image signal, the image signal is transmitted to a special image processing system, the image signal is converted into a digital signal according to information such as pixel distribution, brightness, color and the like, the image system performs various operations on the converted signals to extract target characteristics, and then the on-site equipment action is controlled according to a discrimination result. Compared with the two methods, the first method has the advantages that the technology is simple and practical, the detection time is long, omission is easy to occur, the second method can efficiently detect the generator blades, omission is difficult to occur, but the two methods have a fatal problem that only the generator blades before installation can be detected, when surface defects such as cracks occur when the generator blades are in a state after installation, the method is not applicable, and aiming at the description, the existing defect detection method can only be detected when the wind driven generator has serious problems, and the defect of low wind power generation efficiency exists. Disclosure of Invention In view of the above, the present invention provides a method and a device for detecting surface defects of a wind turbine blade, so as to solve the problem of low wind power generation efficiency. In a first aspect, the present invention provides a method for detecting a surface defect of a blade of a wind turbine, the method comprising: acquiring an image of the blade surface of the wind driven generator and an ultrasonic reflection signal inside the blade, wherein the image of the blade surface comprises a visible light image and an infrared thermal image; Preprocessing the visible light image and the infrared thermal image respectively, and performing defect detection on the preprocessed visible light image and the preprocessed infrared thermal image respectively by using a preset image analysis model to generate wind driven generator blade surface defect data and thermal anomaly data; Preprocessing the ultrasonic reflection signals, and detecting defects of the preprocessed ultrasonic reflection signals to generate data of defects of the internal structure of the wind driven generator blade; and fusing the surface defect data, the thermal anomaly data and the data of defects of the internal structure of the wind driven generator blade by using a pr