scholarly journals Consistency Index-Based Sensor Fault Detection System for Nuclear Power Plant Emergency Situations Using an LSTM Network

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1651 ◽  
Author(s):  
Jeonghun Choi ◽  
Seung Jun Lee

A nuclear power plant (NPP) consists of an enormous number of components with complex interconnections. Various techniques to detect sensor errors have been developed to monitor the state of the sensors during normal NPP operation, but not for emergency situations. In an emergency situation with a reactor trip, all the plant parameters undergo drastic changes following the sudden decrease in core reactivity. In this paper, a machine learning model adopting a consistency index is suggested for sensor error detection during NPP emergency situations. The proposed consistency index refers to the soundness of the sensors based on their measurement accuracy. The application of consistency index labeling makes it possible to detect sensor error immediately and specify the particular sensor where the error occurred. From a compact nuclear simulator, selected plant parameters were extracted during typical emergency situations, and artificial sensor errors were injected into the raw data. The trained system successfully generated output that gave both sensor error states and error-free states.

2021 ◽  
Author(s):  
Yukihisa Sanada ◽  
Yoshimi Urabe ◽  
Toshiharu Misonou ◽  
Takehiko Shiribiki ◽  
Takahiro Nakanishi ◽  
...  

Abstract Large quantities of volatile radionuclides were released into the atmosphere and the hydrosphere following the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident on March 11, 2011. Monitoring of radiocesium in sediment is important for evaluating the behavior of radiocesium in the environment and its effect on aquatic organisms. In this study, the radiocesium distribution in the surface sediment around the FDNPP was visualized as a radiocesium map using periodical survey data from a towed gamma-ray detection system. The uncertainty of the radiocesium map was evaluated via comparison with a large amount of sediment core sample data. The characteristics of the radiocesium distribution were examined considering the seafloor topography and a geological map, which were obtained via acoustic wave survey. The characteristics of the formation of 137Cs anomaly at the estuaries were analyzed using a contour map of 137Cs concentration combined with water depth. Validation of the created map showed that it was comparable with actual sediment core samples. The map generated using the towed radiation survey depicted the 137Cs concentration distribution as the position resolution of a 1 km mesh. Finally, the 137Cs concentration decreased with time in consideration of such uncertainty.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yukihisa Sanada ◽  
Yoshimi Urabe ◽  
Toshiharu Misonou ◽  
Takehiko Shiribiki ◽  
Takahiro Nakanishi ◽  
...  

AbstractLarge quantities of volatile radionuclides were released into the atmosphere and the hydrosphere following the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident on March, 2011. Monitoring of radiocesium in sediment is important for evaluating the behavior of radiocesium in the environment and its effect on aquatic organisms. In this study, the radiocesium distribution in the surface sediment around the FDNPP was visualized as a radiocesium concentration map using periodical survey data from a towed gamma-ray detection system. The uncertainty of the radiocesium map was evaluated via comparison with a large amount of sediment core sample data. The characteristics of the radiocesium distribution were examined considering the seafloor topography and a geological map, which were obtained via acoustic wave survey. The characteristics of the formation of 137Cs anomaly at the estuaries were analyzed using a contour map of 137Cs concentration combined with water depth. Validation of the created map showed that it was comparable with actual sediment core samples. The map generated using the towed radiation survey depicted the 137Cs concentration distribution as the position resolution of a 1 km mesh. Finally, the 137Cs concentration decreased with time in consideration of such uncertainty.


Author(s):  
V. I. Orlovskaya ◽  
A. G. Trifonov

The paper presents the results of radiation risk assessment for the staff of a nuclear power plant design during design basis accident (spent nuclear fuel assembly falling on fuel in reactor core or storage pool during refueling operations) and a beyond design basis accident (large leakage of the primary coolant with failure of the active part of the emergency cooling system and complete blackout for 24 h). The assessment is based on state-of-the-art radiation risk models from the United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) and the International Commission on Radiological Protection (ICRP). The calculation of risk indicators for occupational exposure of NPP staff in emergency situations was carried out on the basis of data obtained using a computational module created in the COMSOL 5.6 multiphysics software, doses from a radioactive cloud and internal exposure due to inhalation for such radionuclides as 134Cs, 137Cs, 131I, 133I, 90Sr. A feature of this approach is the detailed consideration of the NPP industrial site infrastructure, which allows obtaining a more accurate assessment of the radionuclide air distribution and fallout.


Sign in / Sign up

Export Citation Format

Share Document