针对风力发电机叶片损伤人工检测效率低,受作业人员业务水平制约等因素影响大的问题,提出一种基于热红外图像的风力机叶片损伤识别以及损伤位置判定和损伤大小计算的方法,通过数字图像处理技术在Matlab 2019b平台开发实现。对附有人工损伤的风力机叶片热红外图像采用对比度拉伸、Gabor滤波、二值化阈值分割等方法提取损伤特征,叶片的磨损损伤利用质心确定其位置,裂纹损伤通过2个端点来表征损伤位置。最后根据磨损区域图像面积和裂纹长度,通过几何光学透镜成像法计算损伤大小。该方法实现了风力机叶片损伤的自动识别与测量,提高了风力机叶片损伤的检测效率。通过实验验证,该方法在风力机叶片损伤识别中具有较高的精确性。
Abstract
A calculation method to identify the damage, damage position and size of the wind turbine blade based on thermal infrared image is put forward in this paper to tackle the problems of manual detection efficiency low and the large influence caused by operators. It has been developed and achieved on the Matlab 2019b platform through digital image processing technology. It adopts the contrast stretch, Gabor filtering and binarization threshold segmentation to extract the damage features from the thermal infrared image of wind turbine blade with artificial damage, locates the position of abrasive damage through center of mass, and represents the damage position of cracks through two endpoints. The method makes the automatic identification and measurement of the damage for the wind turbine blade, which improves the detection efficiency of such damage. Experimental results show that this method has high accuracy in wind turbine blade damage identification.
关键词
风力机 /
叶片 /
红外热成像 /
图像处理 /
损伤识别
Key words
wind turbines /
blades /
infrared thermal imaging /
image processing /
damage identification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] JIANG Z M.Reflections on energy issues in China[J]. Journal of Shanghai Jiao Tong University(science), 2008, 13: 257-274.
[2] 吴翔. 我国风力发电现状与技术发展趋势[J]. 中国战略新兴产业, 2017(11): 225.
WU X.China's wind power generation status and technology development trend[J]. China strategic emerging industry, 2017(11): 225.
[3] 羊森林, 赵萍, 王峰, 等. 大型风电叶片缺陷及其无损检测技术研究[J]. 东方汽轮机, 2012(1): 26-34.
YANG S L, ZHAO P, WANG F, et al.Study on the defects of large-scale wind power blades and non-destructive testing technology[J]. Dongfang turbine, 2012(1): 26-34.
[4] 仇梓峰. 基于计算机视觉的风机叶片表面损伤检测研究[D]. 北京: 北京交通大学, 2019.
QIU Z F.Research on blade surface damage detection of wind turbine based on computer vision[D]. Beijing: Beijing Jiaotong University, 2019.
[5] 琦格琦. 基于红外热成像技术的风力机叶片涂层损伤监测的研究[D]. 呼和浩特: 内蒙古农业大学, 2019.
QI G Q.The study on damage testing of the damaged paint coat of the blades of wind turbine generates with the employment of infrared thermal imaging technique[D]. Hohhot: Inner Mongolia Agricultural University, 2019.
[6] MÁRQUEZ F P G, TOBIAS A M, PÉREZ J M P, et al.Condition monitoring of wind turbines:Techniques and methods[J]. Renewable energy, 2012, 46(5): 169-178.
[7] 仇梓峰, 王爽心, 李蒙. 基于无人机图像的风力发电机叶片缺陷识别[J]. 发电技术, 2018, 39(3): 277-285.
QIU Z F, WANG S X, LI M.Defect detection of wind turbine blade based on unmanned aerial vehicle-taken images[J]. Power generation technology, 2018, 39(3): 277-285.
[8] 张建斐. 基于机器视觉的风力发电机叶片表面缺陷检测研究[D]. 兰州: 兰州理工大学, 2018.
ZHANG J F.Study on detecting surface defects of wind turbine blade based on machine vision[D]. Lanzhou: Lanzhou University of Technology, 2018.
[9] 徐灵鑫. 风力发电机叶片表面缺陷检测的研究[D] . 杭州: 中国计量学院, 2015.
XU L X.Study on surface defect detection of wind turbine blades[D]. Hangzhou:China Jiliang University, 2015.
[10] 张磊. 基于计算机视觉的风力机叶片缺陷诊断研究[D]. 武汉: 华中科技大学, 2013.
ZHANG L.Research on wind turbine blade defect diagnose based on computer vision[D]. Wuhan: Huazhong University of Science and Technology, 2013.
[11] 翟永杰, 张木柳, 乔弘, 等. 基于显著性检测的风机叶片裂纹提取研究[J]. 南方能源建设, 2016, 3(2): 136-140.
ZHAI Y J, ZHANG M L, QIAO H, et al.Research on extraction of fan blade crack based on salient region detection[J]. Southern energy construction, 2016, 3(2): 136-140.
[12] 郑凯, 江海军, 陈立. 红外热波无损检测技术的研究现状与进展[J]. 红外技术, 2018, 40(5): 401-411.
ZHENG K, JANG H J, CHEN L.Infrared thermography ndt and its development[J]. Infrared technology, 2018, 40(5): 401-411.
[13] 吴国境. 基于红外热像技术的风力机叶片损伤检测研究[D]. 呼和浩特: 内蒙古农业大学, 2020.
WU G G.Research on wind turbine blade damage detection based o n infrared thermal imaging technology[D]. Hohhot: Inner Mongolia Agricultural University, 2020.
[14] 杨茂祥. 低照度环境下彩色图像增强算法研究[D]. 南京: 南京邮电大学, 2019.
YANG M X.Research on color image enhancement algorithms in low light conditions[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2019.
[15] 葛彬, 周宁宁. 基于MMTD的保留灰度值的直方图均衡化[J]. 计算机技术与发展, 2012(12): 63-66.
GE B,ZHOU N N.Gray value retention histogram equalization based on MMTD[J]. Computer technology and development, 2012(12): 63-66.
[16] 李灿林, 刘金华, 宋胜利, 等. 基于粒子群优化的红外图像增强方法[J]. 科学技术与工程, 2019, 19(15): 219-225.
LI C L, LIU J H, SONG S L, et al.Infrared image enhancement method based on particle swarm optimization[J]. Science technology and engineering, 2019, 19(15) : 219-225.
[17] 刘玉婷, 陈峥, 付占方, 等. 基于CLAHE的红外图像增强算法[J]. 激光与红外, 2016(10): 1290-1294.
LIU Y T, CHEN Z, FU Z F, et al.Infrared image enhancement algorithm based on CLAHE[J]. Laser & infrared , 2016(10): 1290-1294.
[18] 汤晓庆, 黄开兴, 秦元庆, 等. 基于Gabor滤波器和HOG特征的织物疵点检测[J]. 计算机测量与控制, 2018, 26(9): 39-42, 47.
TANG X Q, HUANG K X, QIN Y Q, et al.Fabric defect detection based on Gabor filter and HOG feature[J]. Computer measurement & control, 2018, 26(9): 39-42, 47.
[19] PETKOV N, WIELING M B.Gabor filter for image processing and computer vision[D]. Groningen: University of Groningen, 2008.
基金
草原英才“现代农牧业工程新技术研发及应用创新人才团队”（内组通字 [2018] 19号）; 内蒙古科技计划项目“风电机组叶片健康监测与维护关键技术研究” 内蒙古农业大学高层次人才引进科研启动项目（NDGCC2016-03）; 中国博士后科学基金（2018M643777XB）
PDF(2352 KB)
