期刊文献+

基于机器学习的铆接质量数字化检测系统 被引量:2

Digital Detection System of Riveting Quality Based on Machine Learning
下载PDF
导出
摘要 为实现铆接质量数字化检测和质量追溯,提出基于机器学习的铆接质量数字化检测方法。使用CCD摄像机对铆接部位进行图像采集,然后进行中值滤波、Canny边缘检测、图像形态学处理等,实现铆接部位裂纹检测和特征信息提取。利用改进的粒子群优化最小二乘支持向量机算法建立铆接质量检测模型,并使用检测样本对模型进行检验。对不合格的铆接进行质量追溯,应用专家系统判断产生缺陷的原因。在某型号飞机装配车间对原型系统进行应用验证。结果表明:所设计的系统检测准确率达96%,可提高铆接质量检测效率、统一检测标准、减少工人劳动。 In order to realize the digital detection and traceability of riveting quality,a digital detection method for riveting quali⁃ty based on machine learning was proposed.Based on the images of riveted part captured by CCD cameras,median filtering,Canny edge detection,image morphology processing were used to detect the cracks and extract the feature information.A riveting quality de⁃tection model was established based on the improved particle swarm optimization least squares support vector machine algorithm,and the model was tested by using the detection samples.The quality tracing of unqualified products was carried out,and the expert system was used to determine the causes of defects.The prototype system was tested through the inspection samples and validated in a certain type of aircraft assembly workshop.The results show that the designed system detection accuracy rate reaches 96%,by which the effi⁃ciency of riveting quality testing can be improved,the testing standards can be unified,and the labor can be reduced.
作者 郝博 闫俊伟 王杰 郭嵩 尹兴超 HAO Bo;YAN Junwei;WANG Jie;GUO Song;YIN Xingchao(School of Mechanical Engineering and Automation,Northeastern University,Shenyang Liaoning 110819,China;Key Laboratory of Vibration and Control of Aero-Propulsion System,Ministry of Education,Northeastern University,Shenyang Liaoning 110819,China)
出处 《机床与液压》 北大核心 2022年第15期65-70,共6页 Machine Tool & Hydraulics
基金 装备预研领域基金重点项目(61409230103) 装备预研领域基金项目(61409230125)。
关键词 机器学习 铆接质量 数字化检测系统 质量追溯 Machine learning Riveting quality Digital detection system Quality traceability
  • 相关文献

参考文献9

二级参考文献64

共引文献107

同被引文献8

引证文献2

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部