Abstract As an attempt to apply AI in the field of maintenance, we have been studying "forward analysis", "inverse analysis" and "future prediction". As for the “forward analysis”, as a theoretical verification of the digital hammering inspection results using the AE sensor, the natural frequency obtained in the hammering inspection is confirmed by “time history response analysis”. Because there is a combination of the shape, material properties to be inspected, measuring position of natural frequency, etc....
英字タイトル:
Attempts of forward analysis, reverse analysis and future prediction using AI in the field of maintenance

According to experimental observations, as the failure modes of piping in nuclear power plants caused by large seismic motion, ratchet collapse was observed. Ratchet collapse is the collapse which is followed by ratchet deformation. However, the mechanism of ratchet collapse under the large seismic load is not so clear. In order to clarify ratchet collapse, it is important to examine ratchet deformation and collapse at first. Ratchet deformation occurrence condition and mechanism have already been clear. In...
英字タイトル:
Fundamental study on collapse of piping under dynamic load

In order to quantitatively evaluate the ability of a nuclear plant to recover its safety functions, we are developing a method to simulate accident management in chronological order according to an accident scenario, rather than simply evaluating the probability, and to evaluate whether or not a major accident will eventually occur, i.e., whether or not the minimum necessary safety functions can be recovered within a time limit. In this presentation, we will discuss the development of a method to evaluate w...
英字タイトル:
Visualizing method for resilience of nuclear power plant

In order to decommission TEPCO Fukushima Daiichi nuclear power plant, the removal of fuel nuclear debris is planned from 2021. It is demanded to grasp nuclear material element contents of the debris remaining inside the accident reactors for the effective and safe removal. Our research team aims to do the on-site analysis of the extracted debris by the Spectral X-ray CT method with the portable X-band (9.3 GHz) 950 keV/3.95 MeV electron linac X-ray sources and GAGG X-ray detector. It is expected to realize ...
英字タイトル:
Fukushima Nuclear Fuel Debris Component Analysis by Spectral CT with Portable High Energy X-ray Source

Tracking human motion from video sequences is a notable technique that is used to detect anomalies in individual human behavior. Several commercially available motion capture devices are based on the use of depth cameras. However, there are a couple of problems with the use of a depth camera. Firstly, a complicated camera system is required, and secondly, the optical field of view is limited. To overcome these problems, we need a technique that can recognize human motion from wide-angle images. In this stud...
英字タイトル:
Development of Robust Keypoint Detector for Distorted Wide-Angle Images and Application to Human Motion Analysis

In order to retrieve fuel debris on a large scale, it is effective to use Geopolymer to stabilize the fuel debris. In this study, we proposed a new disposal concept for various radioactive wastes and evaluated the barrier material performance and heat generation as wastes when using Geopolymer. As a result, it was shown that the method using Geopolymer was effective in the process from fuel debris retrieval to waste disposal....
英字タイトル:
Proposal on large- scale fuel debris retrieval considering waste management

In this research, a new method was developed to identify the “hand behavior” of malicious sabotage behaviors. The Convolutional Neural Network (CNN) and the Long Short Term Memory (LSTM) were applied for analysis of the time-series data of hand behavior images and identification of hand behavior....
英字タイトル:
Development of Sabotage Behavior Detection by Hand Image Analysis and Machine Learning

Condition-based maintenance (CBM) technology is required to perform maintenance on rotating machinery at the optimal time before deterioration and failure occurs. In this study, we describe a deep neural network (DNN) model and corresponding training method for analyzing vibration data to realize CBM for rotating machinery. To apply DNN models in order to analyze time-series data such as vibration data, we first need to optimize the parameters of the models by training them on a dataset consisting of data a...
英字タイトル:
Deep Neural Networks for Vibration Signal Analysis and Its Application for Bearing Fault Classification

According to experimental observations, the failure modes of piping in nuclear power plants caused by large seismic motion are fatigue or ratchet deformation. However, the mechanism of ratchet deformation under the large seismic load is not so clear. In this study, authors conducted experiments and analysis of beams which simulates piping due to cyclic sinusoidal or more complicated waves (composite sinusoidal wave). As the results, authors confirmed that ratchet deformation occurrence conditions are strong...
英字タイトル:
Study on ratchet deformation occurrence conditions of beams due to vibration load

According to the IAEA's Incident and Trafficking Database (ITDB) [1], nuclear security-related incidents occur approximately every three days in the world, with the majority being nuclear and radioactive material theft. Generally, material accountancy is applied as a countermeasure against theft. In this study, a deep learning-based approach was proposed to identify theft of nuclear and radioactive material. As various acts can be performed at the site where nuclear material is handled, the recognition of o...
英字タイトル:
Identification of theft from normal operations in nuclear facilities