摘要
阀芯是控制燃油在汽车喷油器中流动的核心部件,针对目前人工目检阀芯球窝瑕疵所存在的效率低、准确性不高等问题,提出一种基于MFF-SVM的阀芯球窝瑕疵检测方法。首先,根据不同阀芯球窝缺陷类型之间的差异,以颜色均值、方差及HOG的特征提取方式提取融合特征;其次,以SVM作为瑕疵识别器,判断阀芯球窝的缺陷类型,最后通过对比实验,验证了该检测方法的有效性。
Valve core is the core component that controls the flow of fuel in the automobile fuel injector.Aiming at the problems of low efficiency and low accuracy in the current manual visual inspection of valve core ball and socket defects,this paper proposes a valve core ball socket defect detection method based on MFF-SVM.Firstly,the proposed MFF-SVM detection method extracts fusion features by means of color mean,variance and HOG feature extraction according to the differences between different valve core ball and socket defect types,and then uses SVM as a defect identifier to judge the valve core ball socket defects;Finally,through comparative experiments,the effectiveness of the proposed detection method is verified.
作者
熊鑫州
肖子遥
XIONG Xinzhou;XIAO Ziyao(School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)
出处
《农业装备与车辆工程》
2023年第5期129-133,共5页
Agricultural Equipment & Vehicle Engineering
关键词
阀芯
汽车喷油器
多特征融合
机器学习
瑕疵检测
valve core
automotive fuel injector
multi-feature fusion
machine learning
defect detection