検索対象:     
報告書番号:
※ 半角英数字
 年 ~ 
 年
検索結果: 37 件中 1件目~20件目を表示

発表形式

Initialising ...

選択項目を絞り込む

掲載資料名

Initialising ...

発表会議名

Initialising ...

筆頭著者名

Initialising ...

キーワード

Initialising ...

使用言語

Initialising ...

発行年

Initialising ...

開催年

Initialising ...

選択した検索結果をダウンロード

論文

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

今渕 貴志; 谷藤 祐太; 川端 邦明

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

本稿は、3次元点群データに基づいた深層学習による原子力プラント内構造物の識別手法について報告するものである。安全かつ着実な廃炉作業の推進のためには、取得した作業空間情報に基づいて状態の推定や想定を行うことが重要である。特に空間内の放射線量に関わる情報をシミュレーション等の計算で正確に推定することができれば作業計画の立案等が容易になる。正確な放射線量に関する計算を行うためには、作業空間内に存在する物体の空間形状と材質のデータが必要不可欠であるが、その推定は容易ではない。そこで我々は、原子力プラント内の構造物の種別から材質を推定しうることに着目し、深層学習による構造物識別手法の研究開発に取り組んでいる。本稿では、学習データとして既存プラントの3次元点群データに基づき作成されたCADデータの属性ラベルをボクセルグリッドサンプリングによって当該点群データへ付与する手法を提案し、Hold-out学習による学習精度を示すことでその有用性についての考察を述べる。

論文

A Learning data collection using a simulator for point cloud based identification system

谷藤 祐太; 川端 邦明

Proceedings of International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2020) (Internet), p.246 - 249, 2020/02

In this paper, we describe a method of acquiring learning data 3D point cloud data as learning data for deep learning using a simulator. Generally, a lot of data is necessary for building classifiers by deep learning approach. By using a simulator, various measurement conditions can be set thus, it is expected to collect variety of data for building high performance classifier. Data collection was conducted by virtual measurement using a mobile robot model and a sensor model. As a feasibility study of evaluating classification performance, we performed a simple identification experiment to confirm performance and applicability to actual measurement data. As a result, a high identification rate of 89 percent to three categories was obtained.

論文

Development of a GUI-based operation system for building a 3D point cloud classifier

谷藤 祐太; 川端 邦明; 羽成 敏秀

Proceedings of 2019 IEEE Region Ten Conference (TENCON 2019) (Internet), p.36 - 40, 2019/10

This paper describes a Graphical User Interface (GUI) based operation system for building a classifier based on deep learning and verifying its categorization performance. Currently, we build a structure discrimination method based on deep learning with 3D point cloud to support status awareness of the operator of remotely controlled robot. For building a powerful classifier, the operations like "collection of learning data", "construction of architecture" and "creation of learning model "are done by trial and error. Therefore, we consider to develop a system to make such complicated operations easier and more efficiently. In this paper, we describe about required functions for helping such operations and explain developed a prototype system in detail.

論文

A Structure discrimination method by deep learning with point cloud data

谷藤 祐太; 川端 邦明

Proceedings of International Topical Workshop on Fukushima Decommissioning Research (FDR 2019) (Internet), 4 Pages, 2019/05

This paper describes about the development of an environment recognition method with point cloud data collected in a dark place like Fukushima Daiichi Nuclear Power Station (FDNPS). We reported the results of a feasibility study of the structure discriminations from LiDAR 3D point cloud data by a deep learning approach. Proposed method utilizes the image data of projected 3D point cloud as input for the classifier instead of coordinate data of 3D points directly. This idea realized to make shorten the learning time without large capacity of the memory for the computations. We selected five kinds of structures (Stairs, Pipe, Grating, Switchboard and Valve) commonly appeared in the general plant as a discrimination subjects for evaluating proposed method. As a result, the classifier showed an accuracy of 99.6% to five categories and we could confirm the validity of proposed method for the structure discrimination.

論文

Image reconstruction of radioactive contamination due to the Fukushima-Daiichi Nuclear Power Station Accident using a compact Compton camera

佐藤 優樹; 寺阪 祐太; 宮村 浩子; 冠城 雅晃; 谷藤 祐太; 川端 邦明; 鳥居 建男

Reactor Dosimetry; 16th International Symposium on Reactor Dosimetry (ISRD-16) (ASTM STP 1608), p.428 - 436, 2018/11

 被引用回数:0 パーセンタイル:0.05

We developed a lightweight compact Compton camera to measure the distribution of radioactive contamination inside the Fukushima Daiichi Nuclear Power Station. We conducted performance evaluation tests in the coastal area of Fukushima, Japan, using the camera, which employs a cerium (Ce)-doped GAGG (Gd$$_{3}$$Al$$_{2}$$Ga$$_{3}$$O$$_{12}$$) scintillator coupled with a multipixel photon counter. The camera can clearly visualize spreading of radioactivity along the ground surface. In addition, we performed three-dimensional image reconstruction of the distribution of radioactive contamination using the multi-angle data obtained with the Compton camera. We succeeded in obtaining a three-dimensional image of radioactive contamination in the outdoor area.

論文

Radiation imaging using a compact Compton camera inside the Fukushima Daiichi Nuclear Power Station building

佐藤 優樹; 谷藤 祐太; 寺阪 祐太; 宇佐美 博士; 冠城 雅晃; 川端 邦明; 宇津木 弥*; 菊地 弘幸*; 高平 史郎*; 鳥居 建男

Journal of Nuclear Science and Technology, 55(9), p.965 - 970, 2018/09

 被引用回数:30 パーセンタイル:96.56(Nuclear Science & Technology)

The Fukushima Daiichi Nuclear Power Station (FDNPS), operated by Tokyo Electric Power Company Holdings, Inc., went into meltdown after the occurrence of a large tsunami caused by the Great East Japan Earthquake of March 11, 2011. The radiation distribution measurements inside the FDNPS buildings are indispensable to execute decommissioning tasks in the reactor buildings. We conducted the radiation imaging experiment inside the turbine building of Unit 3 of the FDNPS using a compact Compton camera, and succeeded in visualizing the high-dose contamination (up to 3.5 mSv/h). We also drew a three-dimensional radiation distribution map inside the turbine building by integrating the radiation image resulting from the Compton camera into the point cloud data of the experimental environment acquired using the scanning laser range finder. The radiation distribution map shows the position of these contaminations on the real space image of the turbine building. The radiation distribution map helps workers to easily recognize the radioactive contamination and to decrease the radiation exposure; the contamination cannot be observed with the naked eye, naturally.

論文

A 3D radiation image display on a simple virtual reality system created using a game development platform

佐藤 優樹; 寺阪 祐太; 小澤 慎吾*; 谷藤 祐太; 鳥居 建男

Journal of Instrumentation (Internet), 13(8), p.T08011_1 - T08011_10, 2018/08

 被引用回数:6 パーセンタイル:31.36(Instruments & Instrumentation)

The Fukushima Daiichi Nuclear Power Station (FDNPS), operated by Tokyo Electric Power Company Holdings, Inc., suffered a meltdown after a large tsunami caused by the Great East Japan Earthquake on March 11, 2011. The measurement of radiation distribution inside FDNPS buildings is indispensable for executing appropriate decommissioning tasks in the reactor's buildings. In addition, it is extremely important to accurately predict the location of radioactive contamination beforehand because the working time is limited owing to radiation exposure to workers. In this paper, a simple virtual reality (VR) system that can detect radioactive substances in virtual space has been developed to simulate real working environments. A three-dimensional (3D) photo-based model of the real working environment, including an image of the radioactive substance, was imported into the virtual space of the VR system. The developed VR system can be accessed using a smartphone and a cardboard goggle. The VR system is expected to be useful for preliminary training of workers and for recognizing radioactive hotspots during decommissioning of the work environment.

論文

A Three-dimensional radiation image display on a real space image created via photogrammetry

佐藤 優樹; 小澤 慎吾*; 谷藤 祐太; 鳥居 建男

Journal of Instrumentation (Internet), 13(3), p.P03001_1 - P03001_8, 2018/03

 被引用回数:6 パーセンタイル:35.9(Instruments & Instrumentation)

The Fukushima Daiichi Nuclear Power Station (FDNPS), operated by Tokyo Electric Power Company Holdings, Inc., went into meltdown after the large tsunami caused by the Great East Japan Earthquake of March 11, 2011. Radiation distribution measurements inside FDNPS buildings are indispensable to execute decommissioning tasks in the reactor buildings. We have developed a method of three-dimensional (3-D) image reconstruction for radioactive substances using a compact Compton camera. We also succeeded in visually recognize the position of the radioactive substances on the real space by integration of the 3D radiation image and the 3D photo-model created by photogrammetry.

論文

Towards enhancement of test facilities for supporting nuclear decommissioning by remote technology

川端 邦明; 毛利 文昭*; 白崎 令人; 谷藤 祐太; 羽成 敏秀

Proceedings of 2017 IEEE/SICE International Symposium on System Integration (SII 2017), p.450 - 455, 2018/02

本論文は、遠隔技術による廃炉、特に福島第一原子力発電所を支援するための試験施設および設備について報告を行う。原子力機構楢葉遠隔技術開発センターでは、1F廃炉のための遠隔技術開発を支援するためのセンターであり、モックアップ階段、ロボット試験用水槽、モーションキャプチャなどを整備して、2016年4月から運用開始している。これに加えて、廃炉用遠隔操作ロボットの試験環境の設計、開発も行っている。本論文では、楢葉遠隔技術開発センターにおける試験施設や試験環境開発の現状について報告を行う。

論文

Remote radiation imaging system using a compact $$gamma$$-ray imager mounted on a multicopter drone

佐藤 優樹; 小澤 慎吾*; 寺阪 祐太; 冠城 雅晃; 谷藤 祐太; 川端 邦明; 宮村 浩子; 和泉 良*; 鈴木 敏和*; 鳥居 建男

Journal of Nuclear Science and Technology, 55(1), p.90 - 96, 2018/01

 被引用回数:41 パーセンタイル:98.09(Nuclear Science & Technology)

A remote radiation imaging system comprising a lightweight Compton camera and a multicopter drone was developed to remotely and quickly measure radioactive contamination inside the buildings of the Fukushima Daiichi Nuclear Power Station (FDNPS). The drone system is used for measuring detailed radiation distributions in narrow areas, which have been difficult to gauge with conventional aircraft monitoring using helicopters. A measurement of radiation distributions in outdoor environments in the coastal areas of Fukushima, Japan, was performed. The drone system with the Compton camera succeeded in remote observations of dense hotspots from the sky over a contaminated area near the FDNPS. The time required for image reconstruction is approximately 550 s in the case of a 9-m flight altitude for the hotspots with a surface dose rate of several tens of $$mu$$Sv/h. This drone system will be used inside the buildings of the FDNPS for remote measurement of radioactive contamination.

論文

Development of compact Compton camera for 3D image reconstruction of radioactive contamination

佐藤 優樹; 寺阪 祐太; 小澤 慎吾*; 宮村 浩子; 冠城 雅晃; 谷藤 祐太; 川端 邦明; 鳥居 建男

Journal of Instrumentation (Internet), 12(11), p.C11007_1 - C11007_8, 2017/11

 被引用回数:17 パーセンタイル:65.53(Instruments & Instrumentation)

The Fukushima Daiichi Nuclear Power Station (FDNPS), operated by Tokyo Electric Power Company Holdings, Inc., went into meltdown after the large tsunami caused by the Great East Japan Earthquake of March 11, 2011. Very large amounts of radionuclides were released from the damaged plant. Radiation distribution measurements inside the building of FDNPS are indispensable to execute the decommission tasks in the reactor buildings. We have developed a light-weight compact Compton camera to three-dimensionally measure the distribution of radioactive contamination inside FDNPS. The total weight of the Compton camera is lower than 1.0 kg. The $$gamma$$-ray sensor of the Compton camera employs the Ce-doped GAGG scintillators coupled with a multi-pixel photon counter (MPPC: Hamamatsu Photonics K.K.,). We performed the 3D image reconstruction of the $$^{137}$$Cs-radioactive sources as shown in Fig. 1; the 3D radiation image is reconstructed using the multi-angle data measured with the Compton camera. Here, we introduce the development status of the 3D radiation imaging system consisting of the Compton camera. Moreover, we present the results of a performance evaluation test for 3D image reconstruction of radioactive contaminations in details.

論文

福島第一原子力発電所廃止措置における楢葉遠隔技術開発センターの取り組み

谷藤 祐太

原子力年鑑2018, p.96 - 97, 2017/10

福島第一原子力発電所の事故収束に向けて、楢葉遠隔技術開発センターで行っている遠隔技術開発の取り組みについて報告する。

論文

Radiation imaging system using a compact $$gamma$$-ray imager mounted on a remotely operated machine

佐藤 優樹; 川端 邦明; 小澤 慎吾*; 和泉 良*; 冠城 雅晃; 谷藤 祐太; 寺阪 祐太; 宮村 浩子; 河村 拓馬; 鈴木 敏和*; et al.

IFAC-PapersOnLine, 50(1), p.1062 - 1066, 2017/07

 被引用回数:3 パーセンタイル:66.55

The development of remote and quick radiation imaging methods in the high dose-rate environment is requested to accelerate implementation of decommissioning of the Fukushima Dai-ichi Nuclear Power Plant (FDNPP). We developed the remote radiation imaging system consisting of a Compton camera and a multicopter drone to remotely measure the radioactive contamination on the several radioactive fields in the environment and inside the building of nuclear facilities such as the FDNPP. The drone system succeeded in the observation of several hotspots from the sky at the outdoor environments in coastal areas of Fukushima, Japan. In addition, we are now developing the SLAM technology for remotely operated machines such as the drone to complete the remote radiation imaging system, which can autonomous flight.

論文

Design of test methods for remotely operated robots utilized for decommissioning tasks

川端 邦明; 谷藤 祐太; 毛利 文昭; 白崎 令人

Proceedings of 2017 International Congress on Advances in Nuclear Power Plants (ICAPP 2017) (CD-ROM), 4 Pages, 2017/04

本論文では、原子力緊急時対応および廃炉作業にもちられる遠隔操作ロボットの性能評価とオペレータ訓練のための試験法に開発について述べる。代表的なロボットの作業に対して時間解析を行い、作業効率の関連から環境要因について検証を行った。これらの検証事項にもとづいて、試験場モジュールをいくつか試作し、テストを行った。

口頭

Start up of Naraha Remote Technology Development Center and consideration of deployed robot operation for new standard testing method

川端 邦明; 土田 佳裕; 谷藤 祐太; 川妻 伸二; 鳥居 建男

no journal, , 

Development of Standard Test Methods (STM) for nuclear emergency response robot is one of the research themes of Naraha Remote Technology Development Center. For two years after the accident at Fukushima Daiichi, more than thirty robots have been deployed to the Fukushima Daiichi NPS. To clarify the functions and requirements to be evaluated for nuclear emergency response robots, it is important to analyze the objective of robot development. The functions and requirements have become clear, based on the time analysis, and failure analysis of such robots. From the time analysis of operation using Quince, more than 70% are moving in time, but 10% have uncertain stops. From the failure analysis, 4 out 5 failed robots have trouble related to communication with robot control. Some STMs could be used to evaluate the function and requirements. JAEA is planning to develop the additional STM at the Naraha Remote Technology Development Center.

口頭

研究拠点向上のための遠隔技術開発,4; 原子力災害対応ロボットの標準試験法の導入に向けて

谷藤 祐太; 白崎 令人; 毛利 文昭; 山田 大地; 土田 佳裕; 川端 邦明; 鳥居 建男; 川妻 伸二

no journal, , 

日本原子力研究開発機構では、原子力災害対応ロボットの標準試験法(Standard Test Method: STM)の開発を進めている。STMではロボットの性能やオペレータの習熟度を評価する「ものさし」を設計・開発する必要がある。我々が現在取り組んでいる原子力災害対応ロボット用のSTMに関する開発状況について述べる。

口頭

Analysis of emergency response robots deployed for Fukushima Daiichi Nuclear Power Plants' accidents

川妻 伸二; 川端 邦明; 土田 佳裕; 谷藤 祐太

no journal, , 

福島第一原子力発電所の事故発生時に緊急時対応として展開されたロボットについての分析について報告する。また、その結果から原子力事故対応用遠隔操作ロボットの求められる要件についてまとめた。

口頭

遠隔機器のための試験法開発の取り組み

谷藤 祐太; 白崎 令人; 毛利 文昭; 川端 邦明

no journal, , 

原子力機構楢葉遠隔技術開発センターでは、福島第一原子力発電所の廃炉作業に貢献するための遠隔操作機器についての性能評価方法の開発を行っている。本発表では、現在進めているロボット評価のための試験法開発の取り組みについて報告する。

口頭

小型・軽量コンプトンカメラを用いた遠隔放射線イメージング技術の開発,1; コンプトンカメラを搭載した無人飛行体による放射性物質分布の可視化に向けた取り組み

佐藤 優樹; 小澤 慎吾*; 和泉 良*; 寺阪 祐太; 冠城 雅晃; 宮村 浩子; 河村 拓馬; 谷藤 祐太; 川端 邦明; 鈴木 敏和*; et al.

no journal, , 

東京電力ホールディングス福島第一原子力発電所(以下、1F)の事故により1F建屋内外に放出された放射性物質について、詳細な除染計画の立案や作業員の被ばく線量の低減のために、飛散した放射性物質を可視化するための技術開発が求められている。日本原子力研究開発機構は放射性物質を可視化するための装置として、小型・軽量なコンプトンカメラを製作し、千代田テクノルと共同で動作試験を進めている。加えて、広いエリアの屋外環境や1F建屋内部の高線量率環境における遠隔での放射線イメージングを目的とし、コンプトンカメラをドローン等の遠隔機器に搭載することによる遠隔放射線イメージングの技術開発を同時に進めている。本シリーズ発表では、測定システムの概要をはじめに紹介し、福島県浜通り地域屋外におけるコンプトンカメラの性能評価試験の結果と、コンプトンカメラによる3次元線源分布再構成に関する検討について発表する。

口頭

遠隔操作移動ロボットのための試験場の開発

川端 邦明; 毛利 文昭; 谷藤 祐太; 白崎 令人; 羽成 敏秀

no journal, , 

本発表では、遠隔操作移動ロボットの開発支援のためのモジュール型試験場の開発状況について報告を行う。福島第一原子力発電所の廃炉のための遠隔技術開発と操作者習熟度向上のために活用するために、現在いくつかのプロトタイプを開発している。ケーブル巻きつき効果のための柱状障害物モジュールや金属製階段モジュールなどを構築した。

37 件中 1件目~20件目を表示