Author
Alexey V. Beloborodov
Bio: Alexey V. Beloborodov is an academic researcher from Russian Academy of Sciences. The author has contributed to research in topics: Pellets & Digital image processing. The author has an hindex of 2, co-authored 5 publications receiving 9 citations.
Papers
More filters
01 Sep 2018
4 citations
TL;DR: In this article, reflected images of pellet surfaces are taken by digital cameras, which provides high contrast of defective areas against the frame background, and an experimental model of a system with a capacity of up to 10 pellets per second was designed.
Abstract: Optoelectronic methods for controlling the appearance of nuclear reactor fuel pellets are considered. In the proposed methods, reflected images of pellet surfaces are taken by digital cameras, which provides high contrast of defective areas against the frame background. Image processing algorithms for identification of defective products are given. An experimental model of a system with a capacity of up to 10 pellets per second was designed. A database containing surface images of simulators and real pellets was designed to train the system. Results of real time processing of the obtained images show that the probability of detection of defective pellets is not less than 95%.
2 citations
TL;DR: In this paper, the results of development and investigation of computer-vision systems for inspection of the external view of fuel pellets for nuclear fuel elements are presented, which utilize CCD-cameras to record the images of a fuel pellet's external view in reflected beams that ensure high contrast of the defects in the picture area.
Abstract: The results of development and investigation of computer-vision systems for inspection of the external view of fuel pellets for nuclear fuel elements are presented. The systems developed utilize CCD-cameras to record the images of a fuel pellet’s external view in reflected beams that ensures high contrast of the defects in the picture area. One has developed a database containing images of simulators, as well as real pellets. Tests of an experimental set for fuel pellet inspection have demonstrated its inspection productivity to be 1 pellet per second and its detection probability higher than 95%. The research team has also developed an experimental set with higher inspection productivity (at least 7 pellets per second).
2 citations
TL;DR: In this paper, the universal structured light method for 3D inspection of Russian and western grid spacers using diffraction elements is developed and the experimental results of industrial testing are given.
Abstract: Safety increasing of nuclear reactors is urgent problem for atomic industry. It takes 100% noncontact dimensional inspection of nuclear reactor components. Optoelectronic methods and systems for 3D inspection of fuel assembly elements, including spacer grids and fuel elements, are presented. The universal structured light method for 3D inspection of Russian and western grid spacers using diffraction elements is developed. For fuel elements inspection one considers the shadow method which allows one to implement full inspection of articles under transported along the automatic production line. TDI SIE has developed the commercial version of systems for integral inspection of spacer grids and fuel elements. The experimental results of industrial testing are given.
1 citations
Cited by
More filters
TL;DR: A Weighted Object Variance (WOV) threshold crack detection method guided by SE-CrackNet convolutional neural network is proposed, which can accurately identify cracks on the surface of nuclear fuel pellets, greatly reduce the crack false detection rate, meet the real-time quality inspection requirements ofnuclear fuel pellet production lines, and vastly improve the performance of traditional machine vision inspection systems.
Abstract: Crack detection is one of the important contents of the nuclear fuel pellet quality inspection. Aiming at the problem of high crack false detection rate caused by low image contrast of nuclear fuel...
3 citations
TL;DR: In this paper, a dedicated optical system for the quality inspection of cylindrical surfaces is presented and the results of using the system for inspection of quality of fuel pellets are provided.
Abstract: Calculations of a dedicated optical system for the quality inspection of cylindrical surfaces are presented. Peculiarities of imaging a cylindrical surface by means of specially enhanced inherent field curvature are considered. Results of using the system for the inspection of quality of fuel pellets are provided.
3 citations
01 Nov 2019
2 citations
TL;DR: In this paper, the authors report on the generation of simulated defects on sintered uranium dioxide fuel pellets by taking advantage of the underwater laser ablation procedure and their subsequent characterization.
1 citations
TL;DR: Basing on the structural lighting method, a contactless system of the alignment control for weapon barrels is developed and a construction of a compact optical sound using a diffraction optical element to expose the barrel bore is proposed.
Abstract: Basing on the structural lighting method, we develop a contactless system of the alignment control for weapon barrels. We propose and design a construction of a compact optical sound using a diffraction optical element to expose the barrel bore. We provide processing algorithms for images obtained under the scanning of the barrel bore; then, using these algorithms, we restore the 3
$$D$$
-shape of the controlled item and compute the required geometric parameters. We provide test results of the alignment control system on samples of real products.
1 citations