A machine-vision system for automated quality control of welded rings

In this paper we describe the development and application of an intelligent measuring control system with integrated robot vision, to enable the solving of complex assembly and quality control tasks with high accuracy and speed. The existing quality-control procedure for welded rings involves a visual observation of the inner surface of the welded ring and the use of calipers. As explained in Section "Determination of the control goals", this leads to limitation of the ring accuracy and the ability to detect faults. To overcome these limitations we have developed a non-contact control method implemented in the machine-vision system. The development and application of machine-vision is a multifold problem. It requires a great amount of expert knowledge, experience and innovation. We present a machine-vision system consisting of a mathematical algorithm developed for accurate measurement of the diameter and roundness of welded rings, to be used along with physical measurements. The principle of the measuring method and the required equipment are given in Section "Main idea of the measurement". Section "Theoretical description of the algorithm" contains the mathematical formulation implemented in a computer algorithm for the measured parameters. Section "Algorithm verification and the necessary corrections" describes analytical experiments conducted to verify the accuracy of the algorithm and derive necessary corrections. Three systems with different range of quality and accuracy are compared and discussed at the end of the paper. The developed machine-vision measuring system was successfully implemented in industrial application, thus eliminating human subjectivity.