Research and Implementation of a Colloid Area Detection and Determination System Based on Machine Vision
In order to solve the problem that the iron core and protective box are not firmly adhered due to the insufficient dispensing quality of nanocrystalline automobile grade common mode inductor,the manual single direct weighing has high labor intensity,low efficiency and is prone to misjudgment,a judgment system based on machine vision is proposed to detect the large and small colloid area,and then judge whether the colloid quality is qualified.The colloidal area image is collected through the machine vision system,and the visionbank software development system is used to complete the automatic detection of colloidal area through image preprocessing,feature positioning,mask processing,plaque area calculation and other algorithms.The data research shows that there is a certain proportional relationship between the area of colloid and the quality of colloid.Through the comparative analysis of the relationship between area and quality,the judgment standard of colloid area is obtained.The detection speed of this judgment system is about 0.8 s/per unit,and the detection accuracy is more than 95%,which greatly improves the product quality of nanocrystalline automobile common mode inductor.
machine visioncolloidal areananocrystalline iron corecommon mode inductance
NETL
NSTL
万方数据
