Polishing Process Automation by Industrial Robot with Polished Surface Quality Judgment Based on Image Processing - Visual Inspection Based on Pattern Matching
This study deals with automation of polishing process by using an industrial robot. In polishingprocess, full automation of polishing operation has not been achieved due to the difficulty invisual inspection. Judgment of whether polishing is sufficient or not has been performed by skilledworkers. In this study, the polishing after milling process is targeted. In the previous report, the generationof robot program for polishing operation based on CAD data was already proposed. Focusingon the periodicity of cutter mark patterns on milling surface, we proposed an automatic judgment ofpolished surface quality based on the image processing which uses Discrete Fourier Transformation.In order to capture images of polished surface, a CCD camera was mounted at 6-axis controlled robothand. However, the image processing method proposed in previous report could not judge the curvedcutter mark patterns because the periodicity of those patterns is not uniform. The objective of thisreport is the development of automatic judgment method for non-periodic cutter mark patterns. Wedeveloped judgment method which uses pattern recognition as a mean to judge existence or not of cuttermarks. As a result, the developed system allows the automatic polishing that includes the surfacequality judgment.