Semantic and volumetric 3D plant structures modeling using projected image of 3D point cloud

Imabuchi, Takashi; Kawabata, Kuniaki

Proceedings of 2024 IEEE/SICE International Symposium on System Integration (SII2024) (Internet), p.141 - 146, 2024/01

http://dx.doi.org/10.1109/SII58957.2024.10417376

A Study on generalization capability of trained structure discrimination network based on 3D point cloud

Imabuchi, Takashi; Kawabata, Kuniaki

Proceedings of 20th International Conference on Ubiquitous Robots (UR 2023), p.632 - 633, 2023/06

Discrimination of structures in a plant facility based on projected image created from colored 3D point cloud data

Imabuchi, Takashi; Kawabata, Kuniaki

Proceedings of 2023 IEEE/SICE International Symposium on System Integration (SII 2023) (Internet), p.396 - 400, 2023/01

Discrimination of the structures in nuclear facility by deep learning based on 3D point cloud data

Imabuchi, Takashi; Tanifuji, Yuta; Kawabata, Kuniaki

Proceedings of 2022 IEEE/SICE International Symposium on System Integration (SII 2022) (Internet), p.1036 - 1040, 2022/01

This paper describes a method for discrimination of the structures in nuclear power station by deep learning based on 3D point cloud data. In order to promote safe and steady decommissioning work, it is important to estimate and assume the condition in nuclear power station based on the measured sensor data. Especially, the data of the dose rate in the workspace is useful to plan the decommissioning task and, the shape and the material property of the structures in the workspace are required for the dose rate simulation. Shape data can be obtained by such as 3D Scan, however, it is difficult to acquire the material property data of the objects. Therefore, we consider that it is possible that the major material property can be estimated from the category of the structures in nuclear power station. In this paper, we proposed a structure discrimination method by 3D semantic segmentation with 3D point cloud data that consists of labeled points by referring category labels of CAD data of existing nuclear facility. We reported discrimination performance of the proposed method by hold-out validation.

Study on creep damage assessment method for Mod.9Cr-1Mo steel by sampling creep testing with thin plate specimen

Kanayama, Hideyuki*; Hiyoshi, Noritake*; Ogawa, Fumio*; Kawabata, Mie*; Ito, Takamoto*; Wakai, Takashi

Zairyo, 68(5), p.421 - 428, 2019/05

This study presents creep damage assessment method for Mod. 9Cr-1Mo steel by sampling creep testing with thin plate specimen. Tensile creep rupture tests were performed using three different sizes of specimen under two different test environments to verify the creep testing with the thin plate specimen. Time to rupture of Mod. 9Cr-1Mo steel using three different sizes were almost same. In addition, there was no effect of environment on time to rupture. Pre-damaged thin plate specimens were machined from a bulk specimen's gage section that pre-damage test was performed with. Pre-damage based on life fraction rule were 8%, 16% and 25%. No effect of the process of machining pre-damaged specimen on time to rupture was confirmed by verification tests in same test condition as pre-damage test. Stress acceleration creep rupture tests were performed to estimate creep damage assessment. Creep damage assessment by stress acceleration creep rupture tests was sufficiently accurate estimate. Creep damage assessments by Vickers hardness and lath width were compared with the assessment by stress acceleration creep rupture tests to study applicability of these methods.

R&D project of digital techniques to reduce radiation exposure for Fukushima Daiichi decommissioning; Overview and key results

Suzuki, Masahiro; Machida, Masahiko; Ito, Rintaro; Kawabata, Kuniaki; Yamaguchi, Takashi; Okamoto, Koji

no journal, , 

no abstracts in English

Toward faster 3D environment modeling based on feature extraction results from movies; Research overview and initiatives

Nakamura, Keita*; Hanari, Toshihide; Madokoro, Hirokazu*; Imabuchi, Takashi; Kawabata, Kuniaki; Nix, S.*; Doi, Akio*

no journal, , 

This paper introduces a research effort for faster 3D environment modeling of the workspace for decommissioning activities at the Fukushima Daiichi Nuclear Power Plant, applying as input video images shot during an investigation of the reactor containment vessel and reactor building. Especially, we construct a system that allows the selection of a 3D reconstruction method with as much information as possible within a specified time limit. We challenge this study with three methods: photogrammetry, simulation, and AI technology. Finally, we aim to integrate the results of each research to build a prototype system that automatically generates a more informative 3D reconstruction result within a specified time and according to the extracted feature values.

Discrimination of structures in a plant facility by deep learning; A Study on out of distribution for unknown input pattern of structures

Imabuchi, Takashi; Kawabata, Kuniaki

no journal, , 

no abstracts in English

Present status of a new pulsed neutron imaging instrument at J-PARC

Segawa, Mariko; Shinohara, Takenao; Kai, Tetsuya; Iikura, Hiroshi; Oi, Motoki; Oikawa, Kenichi; Harada, Masahide; Sakai, Kenji; Soyama, Kazuhiko; Aizawa, Kazuya; et al.

no journal, , 

Object oriented data analysis environment for neutron scattering

Suzuki, Jiro*; Kajimoto, Ryoichi; Ohara, Takashi; Yonemura, Masao*; Aoyagi, Tetsuo; Manabe, Atsushi*; Nakatani, Takeshi; Otomo, Toshiya*; Kawabata, Setsuya*

no journal, , 

Manyo-Lib is a framework of software designed for data analysis for neutron scattering experiment. It is one of the fundamental software used in J-PARC/MLF. Manyo-Lib consists of class libraries of C++ and Python interfaces that wrap the class libraries. The purpose of Manyo-lib is to offer operators for analysis, data containers, distributed computing environment, common data formats necessary to analyzing experiment data generated by various scattering equipments and various research regions. We are going to use NeXus as our common file format.