Development of positioning system for Nuclear-fuel rod automated assembly

Abstract

Abstract A heavy-water nuclear reactor requires five different types of nuclear-fuel rods assemble into bundles. Intelligent identification and positioning of these different types rods for automated bundle assembly remain a challenge owing to their extensive variations and minute distinctions. This paper presents an innovative machine-vision based nuclear-fuel rod positioning system that enables automated rod bundle assembly in a heavy-water nuclear reactor. The system is capable of identifying the type and polarity and adjusting the pose of rods by incorporating the following solutions: 1) a hypercentric imaging solution that is capable of capturing clear and complete images of the rod spacers, even for the rods with large straightness deviations; 2) a robust and noise-resistant multi-scale, multi-directional morphological edge extraction algorithm that features complete and accurate edge image extraction with minimum false edges; and 3) a rod body center at spacers deviation correction algorithm that contributes to a higher level of consistency with the true rod body center. The system is robust, as demonstrated by the following performance indices: a process capability Cpk of 1.14, which is translated into a process yield of 99.95%; 100% correct rod type identification; 100% correct rod polarity identification; and an average time of 8.92 s for positioning a single rod, meeting the required production cycle. The system has been successfully deployed in the North Nuclear Fuel Components Co., Ltd. (a subsidiary of China National Nuclear Corporation).