基于机器视觉的水表小流量检定方法研究

Research on Small Flow Verification Method of Water Meter Based on Machine Vision

针对目前水表小流量检定时间长,人工读数不准确等原因,提出了一种基于机器视觉的水表小流量检定方法。通过工业相机以自适应的采样频率采集水表梅花转子图像,利用图像叠加原理,以检定开始时转子图像为背景,相机后续获取每一帧图像在此背景上作叠加处理。根据转子转动过程中图像叠加后的明暗占比大小的变化规律对其转动齿数进行计数,用双计时法通过脉冲当量得到水表指示体积。利用液体流量标准装置,对水表进行检定,采用静态质量法,通过称重箱获取标准体积,计算水表误差。根据实验结果,在小流量检定时,该方法在缩短检定时间、减少用水量后可得到与人工读数法一致的结果,可解决气泡带来的读数干扰,并能有效提高检定效率。

In the view of the current water meter small flow verification time is long,the manual reading is not accurate and other reasons,a verification method of water meter in small flow based on machine vision is proposed. The plum blossom rotor image of water meter is acquired by industrial camera with adaptive sampling frequency. According to the theory of image overlap,the image of the rotor at the beginning of the verification is used as the background,and the subsequent images overlap on this background. During the rotation of the rotor,the number of rotating teeth is counted from the periodic changing of the percent of white and black areas in the overlap image. The indicated volume of the water meter is obtained by the pulse equivalent with the double-time method. Liquid flow standard device is used to calibrate water meter with the actual volume got by the weighing tank through static mass method. The error of water meter can be calculated. The experimental results manifest that the result obtained by this verification method is consistent to the manual reading with shorten verification time and less water in small flow. The method can solve the reading interference from bubbles,and the verification efficiency can be improved.