触发式弹簧表面缺陷多角度光源补偿检测系统  被引量:2

Multi-angle light source compensation for detection system onsurface defect of trigger spring

在线阅读下载全文

作  者:樊伟 吴定祥 唐立军[1,2] FAN Wei;WU Ding-xiang;TANG Li-jun(School of Physics and Electronic Sciences,Changsha University of Science and Technology,Changsha 410114,China;Hunan Province Higher Education Key Laboratory of Modeling and Monitoring on the Near-Earth Electromagnetic Environments,Changsha University of Science and Technology,Changsha 410114,China;Changsha Billion Set Intelligent Technology Limited Company,Changsha 410000,China)

机构地区:[1]长沙理工大学物理与电子科学学院,湖南长沙410114 [2]长沙理工大学近地空间电磁环境监测与建模湖南省普通高校重点实验室,湖南长沙410114 [3]长沙亿旭智能科技有限公司,湖南长沙410000

出  处:《计算机工程与设计》2021年第4期1173-1180,共8页Computer Engineering and Design

基  金:国家科技支撑计划课题基金项目(2014BAH28F04);湖南省教育厅科学研究基金项目(15K009、17K004)。

摘  要:为解决触发式弹簧因表面反光特性导致表面缺陷难以检测的问题,提出一种多角度光源补偿的检测方案。设计多光源补偿系统和影像采集处理平台,通过四核ARM实现多核协同控制,研究用于缺陷检测的聚类算法,实现触发式弹簧表面缺陷检测系统。实验结果表明,该系统能有效检测触发式弹簧表面缺陷,缺陷弹簧的识别率在99%以上,单个弹触发式弹簧表面缺陷提取的准确率在85%以上,单个弹簧的处理时间在15 ms内,具有较高的实时性,可实现触发式弹簧的在线检测。To solve the problem that it is difficult to detect the trigger spring surface defects on the reflective surface,a detection method of multi-angle light source compensation was presented.The multi-source compensation system and image acquisition and processing platform were designed,and the collaborative control was performed through quad-core ARM.The clustering algorithm for defect detection was studied and the trigger spring surface defect detection system was built.Experimental results show that the compensation detection system of multi-angle light source can effectively detect the surface defects of trigger spring,the recognition rate of defective springs is more than 99%,and the accuracy rate of single spring surface defects is more than 85%.The processing time of a single spring is within 15 ms,which shows high real-time performances.Thus,it make the online detection of trigger spring possible.

关 键 词:弹簧表面缺陷 聚类算法 多核协同控制 ARM处理器 光源补偿 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象