基于微分形态学梯度风力发电机叶片缺陷边缘增强的红外检测研究  

STUDY ON INFRARED DETECTION EDGE ENHANCEMENT OF WIND TURBINE BLADE DEFECTS BASED ON DIFFERENTIAL MORPHOLOGY GRADIENT

作　　者：康爽 陈长征[1,2] 罗园庆 周勃 Kang Shuang;Chen Changzheng;Luo Yuanqing;Zhou Bo(Shool of Mechanical Engineering,Shenyang University of Technology,Shenyang 110870,China;Liaoning Engineering Center for Vibration and Noise Control,Shenyang 110870,China)

机构地区：[1]沈阳工业大学机械工程学院,沈阳110870 [2]辽宁省振动噪声控制技术工程研究中心,沈阳110870

出　　处：《太阳能学报》2021年第6期432-437,共6页Acta Energiae Solaris Sinica

基　　金：国家自然科学基金(51675350,51575361)。

摘　　要：针对风力发电机叶片红外检测探伤中,对缺陷轮廓信息识别难度高的问题,提出一种基于膨胀腐蚀的微分形态学梯度(DMG)边缘增强方法。首先,在风场实验测得缺陷红外热图像;其次,对红外图像进行Sobel算子、Prewitt算子、膨胀腐蚀算子、DMG算子的对比,采用四相邻原则对比度作为衡量标准;最后,将原图与DMG图进行融合,通过对比度受限自适应均衡化的方法对融合图像进行增强,将增强图像显示在检测软件中。实验结果表明,所提出的算法能有效增强缺陷的边缘轮廓信息,可解决叶片红外检测时缺陷轮廓识别难的问题。In order to solve the problem difficultly to identify the defect contour information in the infrared detection of wind turbine blades,a differential morphological gradient(DMG)edge enhancement method based on expansion corrosion is proposed in this paper.Firstly,the infrared thermal image of the defect is measured in the wind field experiments.Then,Sobel operator,Prewitt operator,dilation corrosion operator and DMG operator are employed to process the infrared image.Moreover,the four adjacent principle contrast is selected as the measurement standard.Furthermore,the original image is fused with the DMG image,and the fused image is enhanced by contrast limited adaptive equalization method.Finally,the enhanced image is displayed in the detection software.The experimental results show that the algorithm proposed in this paper can effectively enhance the edge contour information of defects,which solves the difficulty of detecting the contour recognition during blade infrared inspection.

关 键 词：风力发电机叶片 膨胀腐蚀 缺陷识别 红外检测 图像融合 

分 类 号：TK83[动力工程及工程热物理—流体机械及工程]