9. DESIGN AND DEVELOPMENT OF GEAR TESTING & SEGREGATION CONVEYOR BY USING MATLAB

Gears are one of the most common mechanisms for transmitting power and motion. Error in gears causes two main problems, increased acoustic noise in operation and increased wear, both of which are sufficiently troublesome to cause concern. Therefore, precision measurement of gears plays a vital role in gear measurement and inspection. The current m ethods of gear measurement are either time consuming or expensive. In addition, no single measurement method is available and capable of accurately measuring all gear parameters while significantly reducing the measurement time. Computer vision -based methods typically need to determine the coordinate of the centre of the gear as a benchmark, so the accuracy of centre detection directly affects the precision of the measurement of gear parameters. Among the traditional methods of image detection, the centre d etection algorithm generally requires an edge detection method to determine the edge of the gear, and then uses the gravity method, the median method, and the Hough transform method to determine the centre of the gear. The first two algorithms require more evenly distributed images; otherwise, they will lead to considerable errors. The latter algorithm requires voting point -by-point and requires more time to record, yet the accuracy is not high enough for industrial standards The aim of this work is to util ize computer vision technology to develop a non -contact and rapid measurement system capable of measuring and inspecting most of spur gear parameters with appropriate accuracy. The vision system has been established in the metrology lab and it is used to c apture images for gears to be measured or inspected. Software (named Gear Vision) has been especially developed in -house using Microsoft Visual C++ to analyze the captured images and to perform the measurement and inspection processes.