基于机器视觉的模具保护方法研究与实现  

Research and Implementation of Mold Protection Method Based on Machine Vision

作　　者：王平江[1] 徐长杰[1] 唐小琦[1] 吕明明[1] 

机构地区：[1]华中科技大学机械科学与工程学院 国家数控系统工程技术研究中心,武汉430074

出　　处：《计算机测量与控制》2013年第5期1281-1284,共4页Computer Measurement &Control

基　　金：国家自然科学基金(50835004与51075166);科技重大专项:课题(2012ZX04001-022)

摘　　要：传统注塑机模具保护方法不稳定,经常出现误检测使模具损坏现象,为此提出一种基于机器视觉的模具保护方法;此方法是将合模前空模前景图与空模背景图相比较,计算各个ROI(Region of Interesting)检测区域内的像素合格率,以此判断合模前模具中是否有异物;采用了近红外光照明、背景自动更新等技术,以解决周围环境光亮度变化和震动对检测结果的负面影响;同时设定多个ROI检测区域,以提高检测速度和稳定性;根据实验结果可以得出基于视觉的模具保护方法具有处理稳定,速度快的特点,能够有效地保护模具和检测工件的完整性。The traditional mold protection method of injection molding machine often appears error detection which makes mold damage therefore, this paper proposes a mold protection method based on machine vision. This method is to compare the empty foreground image with the empty background image before closing mold, calculate qualified rate of pixel of all ROI （Region of Interesting）, judge whether a foreign body in the mold. This paper use the near infrared illumination, background updating technology and so on, which solve the influence of vibration and brightness changing in surrounding environment on the detecting results. At the same time in order to improve the detecting speed and accuracy, ROI is set.

关 键 词：模具保护 机器视觉 背景更新 差影法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]