Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
三上 奈生; 相澤 康介; 栗原 成計; 植木 祥高*
AI Thermal Fluids (Internet), 5, p.100029_1 - 100029_15, 2026/03
Early detection of water/steam leakage is important in the prevention of failure propagation of heat transfer tubes in a steam generator of a sodium-cooled fast reactor. This study proposes an unsupervised learning-based acoustic method to detect gas leakage in liquid and evaluates its noise resistance based on parametric receiver operating characteristic (ROC) analysis. An autoencoder is trained, validated, and tested on time-frequency representations of simulated noise and leak signals for various signal-to-noise ratios (SNRs). To calculate a false positive rate and a true positive rate, the probability density function is assumed to be either as a normal distribution, a power transformed normal distribution, or a power normal distribution. As a result, the power normal distribution that shows the best goodness-of-fit was used as the probability density function to draw an ROC curve. The predictive ability of the autoencoder is evaluated as excellent for 
, 
, 
, and 
dB, good for 
dB, and poor for 
dB. The autoencoder can detect leakage at relatively low-noise levels and has the potential to detect leakage at relatively high-noise levels equivalent to actual noise levels. Segmentation of the noise and leak signals can also be achieved from input, reconstructed, and residual images. These results suggest that the proposed method contributes to laying the foundation for detection and accident analysis of water/steam leakage in a steam generator of a sodium-cooled fast reactor.
植木 祥高*; 平子 樹*; 手塚 晃輔*; 相澤 康介; 荒 邦章*
AI Thermal Fluids (Internet), 4, p.100021_1 - 100021_12, 2025/12
With a final goal of early detection and understanding of the transition of coolant boiling events in the core of sodium-cooled fast reactors, our present aim is to obtain and maintain the basic knowledge necessary for developing anomaly detection technology associated with local anomalies in the core and to demonstrate basic feasibility. We constructed a deep learning method and evaluated its performance to detect the occurrence and understand the transition of subcooled boiling using acoustic identification. In this research, we aim to acquire acoustic data during subcooled boiling of ultrapure water and learn feature quantities of the boiling in time-frequency expression. A deep learning model of a convolutional neural network for label classification was constructed. In addition to being able to identify the occurrence of boiling with high accuracy, the visualization of the identification basis using the gradient-weighted class activation mapping (Grad-CAM) method revealed the acoustic frequency bands that the deep learning model determined to be of high importance. We also constructed a regression analysis-type deep learning model and demonstrated that boiling heat flux values can be predicted with high accuracy.
三上 奈生; 相澤 康介; 植木 祥高*; Michel, F.*; Fache, J.*
Proceedings of 2025 International Congress on Advances in Nuclear Power Plants (ICAPP 2025) (Internet), 10 Pages, 2025/09
The present study evaluates the basic feasibility of an ensemble deep learning model to detect leakage from multi-channel acoustic signals in a steam generator (SG) of a sodium-cooled fast reactor (SFR). The acoustic signals from the bubbling and the gas blowout are measured by an array sensor in a basic experimental apparatus for SG to simulate noise and leak signals. Time-frequency representations (TFRs) are produced from these acoustic signals as the inputs of convolutional neural networks (CNNs). Three typical CNNs are introduced as candidates for the base model of ensemble deep learning. The proposed ensemble deep learning model reaches an accuracy of 95.43%, improved by 4.90% from the solo deep learning model. This result indicates that the proposed ensemble deep learning model has the potential to detect leakage more precisely in an actual SG of SFR.
植木 祥高*; 平子 樹*; 手塚 晃輔*; 相澤 康介; 荒 邦章*
Proceedings of 12th International Conference on Multiphase flow (ICMF2025) (Internet), 2 Pages, 2025/05
With a final goal of early detection and understanding of the transition of coolant boiling events in the core of sodium-cooled fast reactors, our present aim is to obtain and maintain the basic knowledge necessary for developing anomaly detection technology associated with local anomalies in the core, and to demonstrate basic feasibility. We constructed a deep learning method of convolutional neural network and evaluated its performance to detect the occurrence and understand the transition of subcooled boiling using acoustic identification. In addition to being able to identify the occurrence of boiling with high accuracy, the visualization of the identification basis based on Grad-CAM revealed the acoustic frequency bands that the deep learning model determined to be of high importance. We also constructed a regression analysis-type deep learning model and demonstrated that it is possible to predict boiling heat flux values with high accuracy.
相澤 康介; 植木 祥高*
Proceedings of Specialist Workshop on Advanced Instrumentation and Measurement Techniques for Nuclear Reactor Thermal-Hydraulics and Severe Accidents (SWINTH-2024) (USB Flash Drive), 7 Pages, 2024/06
ナトリウム冷却高速炉において異常事象を早期に検知することは安全性向上に寄与するものである。音響計測は応答性が良く、かつ異常発生箇所の物理量を計測点で取得できる特性を有しており、音響計測による異常検知技術の開発を進めている。本論文では、ナトリウム冷却高速炉に音響計測を適用する上での課題を整理するとともに、その課題への対策方針を検討し、かつ研究開発の状況を示す。
三上 奈生*; 植木 祥高*; 芝原 正彦*; 相澤 康介; 荒 邦章*
International Journal of Multiphase Flow, 171, p.104688_1 - 104688_13, 2024/01
被引用回数：6 パーセンタイル：37.41(Mechanics)For the analysis of anomalies in a steam generator (SG) of a sodium-cooled fast reactor (SFR), we evaluate the noise resistance of CNN-based acoustic identification methods of gas-liquid two-phase jets and produce visual explanations for their decisions. First, we introduce the water flow sound and the three types of gas-liquid jet sounds, which simulate the background noise and the anomaly sounds, respectively. Second, we produce time-frequency representations for various signal-to-noise ratios (SNRs) and employ AlexNet, VGG16, and ResNet18 to the identification of the gas-liquid two-phase jets. As a result, the best CNN of ResNet18 achieves more than 0.92 for SNR = 0, -4, -8, and -12 dB and 0.69 for SNR = -16 and -20 dB. This result indicates that our proposed methods can identify the flow states of gas-liquid two-phase jets in low-level noise environments and detect the gas-liquid two-phase jets even in high-level noise environments. Also, Grad-CAM suggests that ResNet18 focuses on one of the spectrum peaks of the water flow sound and all or part of the signal intensity pattern of the gas-liquid jet sounds. Our proposed methods lead to the safe operation and fast, accurate, and accountable analysis of anomalies in SFR.
三上 奈生*; 植木 祥高*; 芝原 正彦*; 相澤 康介; 荒 邦章
Proceedings of 17th International Heat Transfer Conference (IHTC-17) (Internet), 9 Pages, 2023/08
To increase the safety of sodium-cooled fast reactors, it is necessary to develop a method to identify the states of bubble jet flow caused when a heat transfer tube is damaged in steam generators (SGs). For this issue, we propose a novel state sensing method with time-frequency representations (TFRs) and convolutional neural networks (CNNs). This study consists of three phases. First, using water and air as simulant fluids to perform the proof of concept, pipe flow sound and bubble jet flow sound are acquired, each of which simulates normal and anomaly sound. Second, three TFRs are extracted from raw signals based on short-time Fourier transform (STFT), continuous wavelet transform (CWT), and synchrosqueezed wavelet transform (SWT). Third, typical CNNs including AlexNet, VGG16, and ResNet18 are introduced for the identification of pipe flow sound and three types of bubble jet flow sound. As a result, the model combining ResNet18 and STFT reaches the highest accuracy and correctly identifies 1984 out of 200 test data. These results demonstrate that our proposed method based on the acoustic identification of deep learning has great potential to sense the states of bubble jet flow in actual SFRs.
三上 奈生*; 植木 祥高*; 芝原 正彦*; 相澤 康介; 荒 邦章
Journal of Sound and Vibration, 561, p.117797_1 - 117797_14, 2023/05
被引用回数：7 パーセンタイル：32.95(Acoustics)In the present study, we focus on coupled waves of cylinder walls and an internal liquid, one of the important issues in various fluid machinery including nuclear reactors. The main objective of this study is to propose a novel method to predict coupled wave frequencies based on the cylindrical shell theory and wave equation with the consideration of the fluid added mass. First, we introduce the fluid added mass to consider the effects of the liquid mass. Second, we discuss the vibration behavior of cylinder walls and sound propagation of an internal liquid separately to describe the coupled wave theoretically. In this discussion, we derive dispersion relations of the cylinder walls and internal liquid based on the shell theory and wave equation in the cylindrical coordinates, respectively. To validate our proposed theory, we conduct an experiment on the coupled waves using a SUS304 pipe as a cylinder and water as an internal liquid. As a result of frequency analysis based on the power spectral density (PSD), we confirm that the coupled waves occur without any external vibration sources, and the vibration modes and the most prominent vibration mode vary with the flow rate of the internal water.
植木 祥高*; 橋本 俊作*; 芝原 正彦*; 相澤 康介; 荒 邦章
Proceedings of 30th International Conference on Nuclear Engineering (ICONE30) (Internet), 5 Pages, 2023/05
In sodium-cooled fast reactors, coolant boiling in reactor cores is one of the important phenomena in the safety assessment. Our final target of the present study is to realize the acoustic anomaly detection of the boiling inception in actual reactors. In the actual environment, various sorts of noises are expectedly superposed on accidental boiling sounds. It is inevitable to distinguish the boiling sounds from the superimposing hostile disturbance with high accuracy. To achieve this, we utilize machine learning techniques and assess the feasibility of boiling sensing based on acoustic recognition and deep learning. In the present study, we employ an autoencoder to denoise boiling sounds, and a convolutional neural network to detect the boiling inception. The boiling acoustics have not been fully understood yet. In the present study, we find that some characteristics of the boiling acoustics are consistent with the resonance vibration of the heating body. This finding contributes to elucidating the physics of boiling acoustics.
三上 奈生*; 植木 祥高*; 芝原 正彦*; 相澤 康介; 荒 邦章
International Journal of Multiphase Flow, 159, p.104340_1 - 104340_8, 2023/02
被引用回数：13 パーセンタイル：59.56(Mechanics)この研究では、ナトリウム冷却高速炉(SFR)の蒸気発生器(SG)管の損傷によって引き起こされる液中への気泡噴流の検知に関するものである。本研究の主な目的は、気泡噴流に対して音響認識と深層学習に基づく新しい状態検知手法を開発することである。新しい手法の適用性を評価するために、模擬流体として水と空気を用いた概念検討を実施した。まず、SFRのSG管からの正常音と異常音をシミュレートする配管内流動音と気泡噴流音の取得と分析を行い、音響信号と特徴周波数の整理を行った。得られた試験結果を基に、ディープラーニングモデルを構築し、性能評価を実施した。その結果、提案したすべてのモデルは、ほぼ100.00%の精度で配管内流動音と気泡噴流音を識別できた。最も良いモデルでは、配管内流動音と3種類の気泡噴流音を99.76%の精度で識別できた。この結果は、深層学習による音響認識が実際のSFRにおけるバブルジェットの流れの状態を感知する大きな可能性を秘めていることを示唆している。
Xu, X.*; 大平 拓実*; Xu, S.*; 平田 研二*; 大森 俊洋*; 植木 洸輔*; 上田 恭介*; 成島 尚之*; 長迫 実*; 貝沼 亮介*; et al.
Advanced Materials & Processes, 180(7), p.35 - 37, 2022/10
Metallic biomaterials are widely used to replace or support failing hard tissues due to excellent mechanical properties and high wear resistance, with demand increasing as the global population continues to age. It is widely accepted that successful metallic biomaterials should have good biocompatibility, high corrosion resistance, and strong wear resistance. In addition, a low Young's modulus similar to human bone is now recognized as another important factor, in order to avoid bone atrophy due to the stress shielding effect. While the Young's modulus of stainless steels and conventional fcc CoCr alloys is as high as 190-240 GPa, for 
-type Ti-base alloys it is generally in the range of 50-80 GPa. Young's modulus values are as low as 35 GPa for Ti-Nb-Ta-Zr, close to that of human bone at approximately 10-30 GPa. However, Ti-base alloys come with the compromise of low wear resistance. In fact, alloys that feature a low Young's modulus along with high wear resistance have been difficult to realize. This article explores the recently developed bcc CoCr-base alloy Co-Cr-Al-Si as a potential solution to these issues, i.e., the difficulty in combining a low Young's modulus with high wear resistance, and the challenge of realizing large superelastic strains.
大平 拓実*; Xu, S.*; 平田 研二*; Xu, X.*; 大森 俊洋*; 植木 洸輔*; 上田 恭介*; 成島 尚之*; 長迫 実*; Harjo, S.; et al.
Advanced Materials, 34(27), p.2202305_1 - 2202305_11, 2022/07
被引用回数：45 パーセンタイル：92.94(Chemistry, Multidisciplinary)The demand for biomaterials has been increasing along with the increase in the population of elderly people worldwide. The mechanical properties and high wear resistance of metallic biomaterials makes them well-suited for use as substitutes or as support for damaged hard tissues. However, unless these biomaterials also have a low Young's modulus similar to that of human bones, bone atrophy inevitably occurs. Because a low Young's modulus is typically associated with poor wear resistance, it is difficult to realize a low Young's modulus and high wear resistance simultaneously. Also, the superelastic property of shape memory alloys makes them suitable for biomedical applications, like vascular stents and guide wires. However, due to the low recoverable strain of conventional biocompatible shape memory alloys, the demand for a new alloy system is high. The novel body-center-cubic cobalt-chromium-based alloys in this paper provide a solution to both of these problems. We believe our novel alloys are promising candidates for biomedical applications.
113 of the 113th element森田 浩介*; 森本 幸司*; 加治 大哉*; 羽場 宏光*; 大関 和貴*; 工藤 祐生*; 住田 貴之*; 若林 泰生*; 米田 晃*; 田中 謙伍*; et al.
Journal of the Physical Society of Japan, 81(10), p.103201_1 - 103201_4, 2012/10
被引用回数：184 パーセンタイル：97.12(Physics, Multidisciplinary)113番元素である113を
Bi標的に
Znビームを照射する実験により合成した。観測したのは6連鎖の
崩壊で、そのうち連鎖の5番目と6番目は既知である
Db及び
Lrの崩壊エネルギーと崩壊時間と非常によく一致した。この意味するところは、その連鎖を構成する核種が113, 
Rg (Z=111), 
Mt (Z=109), 
Bh (Z=107), Db (Z=105)及びLr (Z=103)であることを示している。本結果と2004年, 2007年に報告した結果と併せて、113番元素である113を曖昧さなく生成・同定したことを強く結論付ける結果となった。
113森田 浩介*; 森本 幸司*; 加治 大哉*; 秋山 隆宏*; 後藤 真一*; 羽場 宏光*; 井手口 栄治*; 鹿取 謙二*; 小浦 寛之; 菊永 英寿*; et al.
Journal of the Physical Society of Japan, 76(4), p.045001_1 - 045001_2, 2007/04
被引用回数：213 パーセンタイル：97.34(Physics, Multidisciplinary)同位体113の合成と崩壊についての研究を行った。実験は353MeVのZnビームを標的Biに当て、気体充填型反跳イオン分離装置を用いて行った。この実験により1つの崩壊連鎖を観測し、これが
Pb(Zn,n)反応によって同位体113が合成された後に続く崩壊連鎖であると同定した。Dbの自発核分裂にて連鎖は止まった。こうして得られた結果は、2004年に最初に報告した113合成及びその崩壊の結果を支持するものである。
112 by Pb + Zn reaction森田 浩介*; 森本 幸司*; 加治 大哉*; 秋山 隆宏*; 後藤 真一*; 羽場 宏光*; 井手口 栄治*; 鹿取 謙二*; 小浦 寛之; 工藤 久昭*; et al.
Journal of the Physical Society of Japan, 76(4), p.043201_1 - 043201_5, 2007/04
被引用回数：157 パーセンタイル：95.79(Physics, Multidisciplinary)同位体112の合成と崩壊についての研究を行った。実験は349.5MeVのZnビームを標的Pbに当て、気体充填型反跳イオン分離装置を用いて行った。この実験により2つの崩壊連鎖を観測し、これがPb(Zn,n)反応によって同位体112が合成された後に続く崩壊連鎖であると同定した。2つの連鎖崩壊はともに粒子を4回放出した後、
Rfの自発核分裂にて連鎖は止まった。こうして得られた崩壊エネルギーと崩壊時間は、ドイツの重イオン研究所(GSI)により報告された結果と一致している。今回の結果はGSIにより報告された112同位体及びその崩壊娘核
Dsの発見実験の報告に対し、明確な形で確認した最初の実験であり、彼らの結果を支持するものである。
森田 浩介*; 森本 幸司*; 加治 大哉*; 秋山 隆宏*; 後藤 真一*; 羽場 宏光*; 井手口 栄治*; Kanungo, R.*; 鹿取 謙二*; 菊永 英寿*; et al.
AIP Conference Proceedings 891, p.3 - 9, 2007/03
理化学研究所の気体充填型反跳分離装置(GARIS)を用いて、最重原子核の生成及びその崩壊の一連の実験が実施された。本実験において得られた112番元素の同位体112及び113番元素の同位体113の実験結果について報告する。Pb(Zn, n)反応により同位体112からの崩壊連鎖が2例確認され、これは以前ドイツのGSIのグループにより報告された112の生成と崩壊を再現、確認する結果となった。また、Bi(Zn, n)反応を実施し、自発核分裂で終わる崩壊連鎖を2例観測した。これは113番元素113及びその娘核であるRg, Mt, BhそしてDbであると同定した。
Bi(Zn,n)113森田 浩介*; 森本 幸司*; 加治 大哉*; 秋山 隆宏*; 後藤 真一*; 羽場 宏光*; 井手口 栄治*; Kanungo, R.*; 鹿取 謙二*; 小浦 寛之; et al.
Journal of the Physical Society of Japan, 73(10), p.2593 - 2596, 2004/10
被引用回数：531 パーセンタイル：99.24(Physics, Multidisciplinary)113番元素の同位体である113及びその娘核111及びMtをBi+Zn反応で初めて観測した。ビームエネルギーは349.1MeVでビーム総粒子数は1.6
10
であった。生成断面積は
fb(
cm
)と見積もられる。
三上 奈生*; 植木 祥高*; 芝原 正彦*; 相澤 康介; 荒 邦章
no journal, ,
本研究では、SFRの蒸気発生器内水リークによる気液二相噴流の発生を対象とし、音響識別と深層学習に基づく新たな状態把握手法の概念実証を行った。その過程で、先ず作動流体として空気と水を用いて、通常音を模擬した配管内水流動音、異常音を模擬した気泡噴流音を測定し、周波数解析と理論的考察を行った。次に、RMSやFFTにより音響特徴量の抽出を行い、FCNNとCNNを用いて各深層学習モデルの性能評価を行った。
柴崎 陸*; 植木 祥高*; 相澤 康介
no journal, ,
データ駆動型音響診断手法の液体金属冷却高速炉への適用を目指した基礎研究を進めている。本技術で着眼している炉内異常の沸騰音による早期検知について、沸騰現象の発現を検知するアルゴリズムを構築することを目標に、音響識別によるサブクール沸騰の発生検知に適合する深層学習活用手法の構築及び検知精度向上手法の検証を行った。また、アンサンブル学習による検知精度向上手法の検証を行なった。沸騰検知のアルゴリズム構築を試行した結果、識別の有効性を確認するとともに、アンサンブル学習の活用により外乱との識別能の改善が期待されることを示した。
植木 祥高*; 相澤 康介; 荒 邦章*
no journal, ,
Na高速炉の炉心における冷却材沸騰事象の早期検知と推移把握を目的とし、当該炉心局所異常に伴う異常検知技術開発に必要な基礎知見の取得整備並びに基本的成立性を示すことを目標に、音響識別によるサブクール沸騰の発生検知及び推移把握に適合する深層学習の手法構築および性能評価を行った。評価の結果、短時間フーリエ変換に基づく時間-周波数表現の音響特徴量データをResNet-50に用いた場合が最良の正答率(99
0.4%)を示した。沸騰発生を高精度で識別することができる他、Grad-CAMに基づく識別根拠の可視化により重要度が高いと深層学習モデルが判定した音響周波数帯域が明らかとなった。また、回帰分析型の深層学習モデルを構築し、沸騰熱流束の数値を高精度(決定係数0.990.00)に予測可能であることを実証した。
