基于机器视觉的圆柱直齿轮齿距偏差检测技术研究

Research on Detection Technology of Tooth Pitch Deviation Based on Machine Vision for Spur Gears

摘要:

针对渐开线圆柱直齿轮齿距偏差的自动测量问题,研究了一种基于机器视觉的影像测量方法。该方法利用影像测量系统摄取被测圆柱直齿轮端面图像,根据齿距偏差的定义设计了齿距偏差自动测量程序。该程序能自动采集待测齿轮图像,并通过图像预处理、拟合圆算法、构造分度圆、提取测量点等一系列处理,最终计算出每个齿距偏差,从而计算出齿轮的单个齿距偏差、齿距累积偏差和齿距累积总偏差。搭建了影像测量系统对该方法进行了实验验证,对实验结果进行了比较分析,分析结果表明齿距测量的重复性精度优于6 μm,所述方法和系统能够实现齿距偏差的有效检测。

Abstract:

For involute cylindrical spur gear pitch deviation problem of automatic measurement, A method of image measurement based on machine vision is studied. The method uses the image measurement system to absorb measured cylindrical spur gear face images. According to the definition of tooth pitch deviation, the automatic measurement program of tooth pitch deviation is designed. The program can automatically collect images under test gear. And through the image preprocessing algorithm, fitting circle algorithm, Indexing circle construction, extraction measurement point and a series of processing, the program finally calculated each pitch deviation, Then it calculated a single pitch deviation, gear pitch cumulative deviation and gear pitch cumulative total deviation. An image measurement system was built to verify the method, and the experimental results were compared and analyzed. The analysis results show that the repeatability accuracy of tooth pitch measurement is better than 6 μm, and the method and system can realize the effective detection of tooth pitch deviation.