基于机器视觉与UMAC的自动铺丝成型构件缺陷检测闭环控制系统

为保证自动铺丝成型构件的性能,实现对成型构件表面质量的高效检测,本文基于机器视觉检测技术,自行研发自动铺丝成型构件表面缺陷检测闭环控制系统,使自动铺丝过程中预浸纱之间的间隙或重叠在允许范围内,从而保证铺丝精度。研究主要分为三个部分:铺丝成型构件表面图像提取与缺陷检测,检测数据传输,运动轴反馈控制,实现在自动铺丝过程中对成型构件表面缺陷检测实时闭环控制。针对电荷耦合相机采集到的预浸纱图像存在运动模糊和信噪比低等问题,将图像预处理划分为图像复原和降噪两大功能,根据不同类型的噪声采用对应滤波法进行降噪处理,提高了图像的信噪比,为后续检测提供高质量图像;预浸纱缺陷主要由其边缘直线这一几何特征进行表征,因此通过对预浸纱边缘检测实现缺陷识别;利用工控机向图像采集控制器发送命令实现图像采集,同时通过工控机与运动控制器之间信息流和数据流的交换实现检测数据的传输。探讨模糊控制理论用于闭环控制的研究,在反模糊化环节后面,加入自适应参数调节,以适应加工过程的突变,并成功地应用到自动铺丝缺陷检测闭环控制系统中,提高了伺服跟踪精度和跟踪实时性,从而提高铺丝精度。

Defect detection and closed-loop control system for automated fiber placement forming components based on machine vision and UMAC

In order to ensure the performance and accuracy of the automated fiber placement (AFP) forming components, detect the quality of the forming components effectively and control the spacing between the fibers, this paper designs a forming components defect detection and real-time closed-loop control system based on the machine vision technology. The control program is divided into three main parts:image acquisition and defect detection, data transmission and the motion-axis feedback control. Considering the problem that the images captured by the camera have motion blur and low signal-to-noise ratio (SNR), the image preprocessing module has been divided into image restoration function and noise reduction function. According to different types of noises, a variety of filtering methods have been used to reduce the noise and improve the SNR of images, providing good quality of the prepreg image for edge extraction. The prepreg defect can be mainly described by the edge line, so we further study the prepreg edge location to realize defect detection. It is necessary to solve the function of sending command to image acquistion controller communication by industrial computer, and exchanging of information between industrial computer and UMAC to realize the data transmission. In addition, this paper discusses the fuzzy control theory. The adaptive parameter is introduced after the defuzzification to adapt to the velocity jump. The fuzzy control theory is successfully applied to the forming components defect detection and real-time closed-loop control system, and it has a high tracing accuracy.