RESEARCH ON REAL-TIME ERROR MEASUREMENT INCURVE GRINDING PROCESS BASED ON MACHINE VISION

摘要

A machine vision image measurement system for onlinernmonitoring of the wheel wear degree during the curverngrinding process is designed and developed. Thernmeasurement apparatus and its principle of operation arernintroduced in detail. Real-time image of work piece andrnwheel in the grinding zone is gathered by CCD camerarninstalled in the grinder. For the purpose of increasing thernmeasurement precision, a new edge detection approachrncombining Zernike moments operator with Prewitt operator isrnproposed. The edge of the finished work piece is located withrnsub-pixel level accuracy, and then the machining error of thernwork piece is calculated on-line by comparing with therntheoretical curve of the work piece. An application of itsrnvalidity and the experimental results are also given.rnExperimental results demonstrate the proposed measurementrnmethod in this paper is effective, and its detection precisionrnand results are reasonable.