In the background of“double carbon,”vigorously developing new energy is particularly important.Wind power is an important clean energy source.In the field of new energy,wind power scale is also expanding.With the wi...In the background of“double carbon,”vigorously developing new energy is particularly important.Wind power is an important clean energy source.In the field of new energy,wind power scale is also expanding.With the wind turbine,the probability of large-scale blade damage is also increasing.Because the large wind turbine blade crack detection cost is high and because of the poor working environment,this paper proposes a wind turbine blade surface defect detection method based on UAV acquisition images and digital image pro-cessing.The application of weighted averages to achieve grayscale processing,followed by median filtering to achieve image noise reduction,and an improved histogram equalization algorithm is proposed and used for the characteristics of the UAV acquisition images,which enhances the image by limiting the contrast adaptive his-togram equalization algorithm to make the details at the target area and defects more clear and complete,and improves the detection efficiency.The detection of the blade surface is achieved by separating and extracting the feature information from the defects through image foreground segmentation,threshold processing,and framing by the connected domain.The validity and accuracy of the proposed method in leaf detection were verified by experiments.展开更多
It is crucial to maintain wind turbine blades regularly, due to the high stress leading to defects or damage. Conventional methods require shipping the blades to a workshop for off-site inspection, which is extremely ...It is crucial to maintain wind turbine blades regularly, due to the high stress leading to defects or damage. Conventional methods require shipping the blades to a workshop for off-site inspection, which is extremely time-consuming and very costly. This work investigates the use of pulse-echo ultrasound to detect internal damages in wind turbine blades without the necessity to ship the blades off-site. A prototype 2D ultrasonic NDT （non-destructive testing） system has been developed and optimised for in-situ wind turbine blade inspection. The system is designed to be light weight so it can be easily carried by an inspector onto the wind turbine blade for in-situ inspection. It can be operated in 1D A-scan, 2D C-scan or 3D volume scan. A software system has been developed to control the automated scanning and show the damage areas in a 2D/3D map with different colours so that the inspector can easily identify the defective areas. Experiments on GFRP （glass fibre reinforced plastics） and wind turbine blades （made of GFRP） samples showed that internal defects can be detected. The main advantages of this system are fully automated 2D spatial scanning and the ability to alert the user to the damage of the inspected sample. It is intended to be used for in-situ inspection to save maintenance time and hence considered to be economically beneficial for the wind energy industry.展开更多
随着海上风电的蓬勃发展,运维工作越来越成为突出问题。风电叶片作为风电大尺寸关键构件,其运维对机组至关重要。本文针对海上风机叶片人工运维检测存在的高风险、低效率和低精度等问题,提出了一种基于改进YOLOv5x(You Only Look Once v...随着海上风电的蓬勃发展,运维工作越来越成为突出问题。风电叶片作为风电大尺寸关键构件,其运维对机组至关重要。本文针对海上风机叶片人工运维检测存在的高风险、低效率和低精度等问题,提出了一种基于改进YOLOv5x(You Only Look Once version 5x)算法的海上风机叶片缺陷机器视觉检测系统。该方法引入了卷积块注意力机制(Convolutional Block Attention Module,CBAM),以增强神经网络对输入特征的感知能力,使用智慧交并比(Wise Intersection over Union,WIoU)作为损失函数,减少人工标注数据的误差,提高目标检测的准确性。基于海上风机叶片缺陷数据对模型进行训练,将训练好的模型封装成海上风机叶片机器视觉识别系统。试验结果显示,改进后的YOLOv5x算法,相比于原有的YOLOv5x,平均精度均值(mean Average Precision,mAP)提高了4.71%,准确率(Precision)提高了7.48%,且能满足实时性需求。展开更多
文摘In the background of“double carbon,”vigorously developing new energy is particularly important.Wind power is an important clean energy source.In the field of new energy,wind power scale is also expanding.With the wind turbine,the probability of large-scale blade damage is also increasing.Because the large wind turbine blade crack detection cost is high and because of the poor working environment,this paper proposes a wind turbine blade surface defect detection method based on UAV acquisition images and digital image pro-cessing.The application of weighted averages to achieve grayscale processing,followed by median filtering to achieve image noise reduction,and an improved histogram equalization algorithm is proposed and used for the characteristics of the UAV acquisition images,which enhances the image by limiting the contrast adaptive his-togram equalization algorithm to make the details at the target area and defects more clear and complete,and improves the detection efficiency.The detection of the blade surface is achieved by separating and extracting the feature information from the defects through image foreground segmentation,threshold processing,and framing by the connected domain.The validity and accuracy of the proposed method in leaf detection were verified by experiments.
文摘It is crucial to maintain wind turbine blades regularly, due to the high stress leading to defects or damage. Conventional methods require shipping the blades to a workshop for off-site inspection, which is extremely time-consuming and very costly. This work investigates the use of pulse-echo ultrasound to detect internal damages in wind turbine blades without the necessity to ship the blades off-site. A prototype 2D ultrasonic NDT （non-destructive testing） system has been developed and optimised for in-situ wind turbine blade inspection. The system is designed to be light weight so it can be easily carried by an inspector onto the wind turbine blade for in-situ inspection. It can be operated in 1D A-scan, 2D C-scan or 3D volume scan. A software system has been developed to control the automated scanning and show the damage areas in a 2D/3D map with different colours so that the inspector can easily identify the defective areas. Experiments on GFRP （glass fibre reinforced plastics） and wind turbine blades （made of GFRP） samples showed that internal defects can be detected. The main advantages of this system are fully automated 2D spatial scanning and the ability to alert the user to the damage of the inspected sample. It is intended to be used for in-situ inspection to save maintenance time and hence considered to be economically beneficial for the wind energy industry.
文摘随着海上风电的蓬勃发展,运维工作越来越成为突出问题。风电叶片作为风电大尺寸关键构件,其运维对机组至关重要。本文针对海上风机叶片人工运维检测存在的高风险、低效率和低精度等问题,提出了一种基于改进YOLOv5x(You Only Look Once version 5x)算法的海上风机叶片缺陷机器视觉检测系统。该方法引入了卷积块注意力机制(Convolutional Block Attention Module,CBAM),以增强神经网络对输入特征的感知能力,使用智慧交并比(Wise Intersection over Union,WIoU)作为损失函数,减少人工标注数据的误差,提高目标检测的准确性。基于海上风机叶片缺陷数据对模型进行训练,将训练好的模型封装成海上风机叶片机器视觉识别系统。试验结果显示,改进后的YOLOv5x算法,相比于原有的YOLOv5x,平均精度均值(mean Average Precision,mAP)提高了4.71%,准确率(Precision)提高了7.48%,且能满足实时性需求。
