We propose acceleration schemes for self-evolving atomistic kinetic Monte Carlo (SEAKMC), which is a promising technique for meso-timescale simulations while maintaining atomistic fidelity. The significant acceleration by a factor of up to ~100 is achieved through the acceleration schemes. Further, the accelerated SEAKMC is applied to the meso-timescale evolution of a cluster of irradiation-induced defects, and we observed the transformation process of the cluster into an energetically stable configuration ...
英字タイトル:
Multi-timescale modeling of structural materials while maintaining atomistic fidelity

A deep learning model has been proposed to recognize hand action for nuclear security A system has been developed that can automatically recognize hand action from video data acquired by a single depth camera...
英字タイトル:
Hand Motion Recognition from Movie Data by Deep Learning

A time-series data future prediction algorithm using Long-Short Term Memory (LSTM), which is a kind of Regression Neural Network (RNN), has been proposed for the purpose of detecting early abnormality of monitoring signals of dynamic devices. An improvement for applying this algorithm to actual dynamic equipment monitoring signals was proposed, and an anomaly judgment method was also proposed....
英字タイトル:
Predictive Maintenance of Dynamic Equipment Monitoring Signal using Deep Learning

A deep learning model has been proposed to estimate flaw depth from ECT signals. The applicability of deep learning to data mixed with unknown parameters for defects was verified. The applicability of deep learning to data assuming lift-off fluctuation during measurement was verified....
英字タイトル:
Flaw Depth Identification from ECT Signal Using Deep Learning

An algorithm has been developed to detect sabotage, etc. by converting surveillance camera images and rule documents into graph structures by deep learning. In the verification using the demo video, the judgment accuracy of 90% or more was obtained. A basic technology has been established to realize an interface with natural language processing AI with image AI....
英字タイトル:
Detection of malicious acts on nuclear security by combining image recognition and natural language processing

Our aim is to develop a technology to suppress the expansion of accident damage by improving the reactor structural resilience as a solution to the problem of restoring the safety function of structures after destruction, which has been an issue since the Fukushima Daiichi Nuclear Power Plant accident. In this research, the visualization method of resilience of nuclear structures was proposed in order to visualize the capacity to mitigate and to recover safety function loss by applying and improving the res...
英字タイトル:
Visualization of resilience improvement effect by fracture control technology using resilience index

n order to complete the decommissioning of the Fukushima Daiichi Nuclear Power Plant, it is necessary to develop a method to retrieve the fuel debris remaining in the RPV on a large scale. In the existing method, the gradually picking debris using a robot arm is being studied. But the method has complicated processes, and it requires a great deal of time and cost. Therefore, a method to solidify the fuel debris and internal structures in the RPV by filling the geopolymer, which is a material with excellent ...
英字タイトル:
Study on Development of Large Scale Retrieval Method of Fuel Debris at Fukushima Daiichi Nuclear Power Plant

Nuclear power generation with improved safety and reliability is a promising technological option for the achievement of a carbon-neutral society. In addition to the decarbonization of electric power systems, it is expected to contribute to the decarbonization of non-electric power fields such as carbon recycling. In this presentation, the author will give an overview of the energy situation surrounding nuclear energy and consider the role of nuclear power in achieving carbon neutrality in 2050 through nume...
英字タイトル:
The Role of Nuclear Energy in Energy Best Mix for Carbon Neutrality

For predicting the fuel debris distribution in Fukushima Daiichi Nuclear Power Plants (1FNPPs), it is essential to figure out the melt spreading behavior on primary containment vessel (PCV) floor. In this paper, we analyzed VULCANO spreading experiment programs using a particle method called “Moving Particle Full-Implicit method (MPFI)” which conserves an angular momentum. Phase change model was installed into MPFI method. two experiments having different corium characteristics were analyzed to confirm the ...
英字タイトル:
Evaluation of spreading-solidification behavior of high-temperature and highly viscous fluid by particle method with angular momentum conservation

The conventional purpose in the field of structural strength has been to prevent damage to design basis events (DBE). For beyond design basis events (BDBE), it is necessary to mitigate the impact on safety on the premise that damage will occur. The authors propose a mitigation method that suppresses the consequence into a fracture mode with a large impact by reducing the load due to a fracture with a small impact on safety. We will introduce the research results for individual component, extend the applicab...
英字タイトル:
New approach to beyond design basis events in structural strength field