Research On In Situ Detection System Of Composite Drilling Defects Based On Machine Vision And Ultrasonic Imaging

Compared with other materials,fiber reinforced composite has the advantages of high strength,lightweight,high temperature resistance and so on,and is widely used in the connection of aerospace equipment.However,due to the anisotropy of mechanics and the low strength of interlayer connection,it is easy to produce defects such as burr,tear and delamination in and around the connection hole after drilling.If the defect investigation is not carried out,it will cause unnecessary economic losses and safety risks.Therefore,it is very important to study the efficient,accurate and comprehensive hole defect detection method for the fiber reinforced composite workpiece after drilling.For the surface burr defects,the use of microscopic vision detection.The ORB algorithm based image Mosaic technology is used to improve the accuracy of image acquisition and the field of vision.Aiming at the problem of poor stability of traditional image segmentation algorithm in processing the object in this paper,an image segmentation algorithm based on improved region growth is proposed.According to the characteristics of fiber reinforced composite hole image,the initial pixel points and growth conditions are constrained,so as to achieve accurate segmentation of defect and background.For the internal delamination defects,ultrasonic imaging is used to detect.Machine vision is used to plan the path before scanning,and the scanning efficiency is improved by setting the slow scanning area and the fast scanning area.Virtual sampling method is introduced to interpolate the signal collected in the fast scanning area to improve the imaging accuracy.Based on the attenuation law of sound intensity in the medium,the corresponding relationship between the amplitude of return wave and the gray value of image is established,and the real-time fast imaging of ultrasonic signal is realized.In this paper,based on the theoretical basis of the two detection algorithms,an in-situ detection system for composite drilling defects is developed,which includes an integrated multi-sensor detection end-effector and a defect vision and ultrasonic detection software system.The accuracy of the system was tested by using fiber-reinforced composite plates of different materials,pore sizes and sizes of embedded defects.The experimental results show that the detection system designed in this paper can realize the rapid and high-precision detection of defects in situ,and the average error is within 10mm~2.