• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2229-2236
• /
• 2021

In nuclear-related facilities, such as nuclear power plants, research reactors, accelerators, and nuclear waste storage sites, radiation detection, and mapping are required to prevent radiation overexposure. Sensor network systems consisting of radiation sensor interfaces and wxireless communication units have become promising tools that can be used for data collection of radiation detection that can in turn be used to draw a radiation map. During data collection, malfunctions in some of the sensors can occasionally occur due to radiation effects, physical damage, network defects, sensor loss, or other reasons. This paper proposes a reproduction strategy for radiation maps using a U-net model to compensate for the loss of radiation detection data. To perform machine learning and verification, 1,561 simulations and 417 measured data of a sensor network were performed. The reproduction results show an accuracy of over 90%. The proposed strategy can offer an effective method that can be used to resolve the data loss problem for conventional sensor network systems and will specifically contribute to making initial responses with preserved data and without the high cost of radiation leak accidents at nuclear facilities.

• Smart Structures and Systems
• /
• v.5 no.1
• /
• pp.81-94
• /
• 2009

A vibration-impedance-based monitoring method is proposed to predict the loss of prestress forces in prestressed concrete (PSC) girder bridges. Firstly, a global damage alarming algorithm using the change in frequency responses is formulated to detect the occurrence of damage in PSC girders. Secondly, a local damage detection algorithm using the change in electro-mechanical impedance features is selected to identify the prestress-loss in tendon and anchoring members. Thirdly, a prestress-loss prediction algorithm using the change in natural frequencies is selected to estimate the extent of prestress-loss in PSC girders. Finally, the feasibility of the proposed method is experimentally evaluated on a scaled PSC girder model for which acceleration responses and electro-mechanical impedances were measured for several damage scenarios of prestress-loss.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Nuclear Engineering and Technology
• /
• v.51 no.1
• /
• pp.198-206
• /
• 2019

A new methodology to analyze the nuclear material accountability for pyroprocessing system is developed. The $Pu-to-^{244}Cm$ ratio quantification is one of the methods for Pu accountancy in pyroprocessing. However, an uncertainty in the $Pu-to-^{244}Cm$ ratio due to the non-uniform composition in used fuel assemblies can affect the accountancy of Pu. A random variable, LOPu, is developed to analyze the probability of detection for Pu diversion of hypothetical scenarios at a pyroprocessing facility considering the uncertainty in $Pu-to-^{244}Cm$ ratio estimation. The analysis is carried out by the hypothesis testing and the event tree method. The probability of detection for diversion of 8 kg Pu is found to be less than 95% if a large size granule consisting of small size particles gets sampled for measurements. To increase the probability of detection more than 95%, first, a new Material Balance Area (MBA) structure consisting of more number of Key Measurement Points (KMPs) is designed. This multiple KMP-measurement for the MBA shows the probability of detection for 8 kg Pu diversion is greater than 96%. Increasing the granule sample number from one to ten also shows the probability of detection is greater than 95% in the most ranges for granule and powder sizes.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2419-2425
• /
• 2017

In this paper, a system for the precise detection of arcs is proposed for a rigid catenary using a spectrometer. For this purpose, a miniature rigid catenary contact-loss simulator was used. Experiments were performed by varying the amplitude of the excitation frequency with which a real arc can occur using a simulator in the range of 5 to 15 mm. The range of the radiated wavelength of the copper, which is a material in the rigid catenary, and the irradiance were measured using a spectrometer according to the generated contact loss. In addition, the amount was monitored over time and its characteristics were analyzed. The voltage and current of the load were analyzed when the arc occurred due to contact loss. The analytical results will be applied to detect rigid catenary arcs and used as a monitoring system for real vehicles developed in the future. This will prevent abrasion and disconnection in rigid catenary systems.

• Smart Structures and Systems
• /
• v.22 no.1
• /
• pp.57-70
• /
• 2018

For the long-term structural health monitoring of civil structures, the effect of ambient temperature variation has been regarded as one of the critical issues. In this study, a principal component analysis (PCA)-based algorithm is proposed to filter out temperature effects on electromechanical impedance (EMI) monitoring of prestressed tendon anchorages. Firstly, the EMI monitoring via a piezoelectric interface device is described for prestress-loss detection in the tendon anchorage system. Secondly, the PCA-based temperature filtering algorithm tailored to the EMI monitoring of the prestressed tendon anchorage is outlined. The proposed algorithm utilizes the damage-sensitive features obtained from sub-ranges of the EMI data to establish the PCA-based filter model. Finally, the feasibility of the PCA-based algorithm is experimentally evaluated by distinguishing temperature changes from prestress-loss events in a prestressed concrete girder. The accuracy of the prestress-loss detection results is discussed with respect to the EMI features before and after the temperature filtering.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.215-221
• /
• 2017

Audiological rehabilitation by itself can provide satisfactory services through acquisition of background information on hearing loss, audiological evaluation, analysis of electroacoustic characteristics of hearing aids, and determining acoustic gain. However, hearing can be exacerbated, and sound pressure level of hearing aids can be lowered. Moreover, breakdown of hearing aids can happen. Therefore, the early detection of hearing loss and regular follow-up observations are very important. The aim of this study concern the direction of effective audiological rehabilitation by checking the clinical cases where hearing aids fitting failures were found.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.890-895
• /
• 2004

This paper describes constant alarm rates process of millimeter wave radar that exits on non-stationary target detection schemes in the ground clutter conditions. The comparison of various CFAR processes such as CA(Cell-Average)-CFAR, GO(Greatest Of)/SO(Smallest Of)-CFAR and OS(Order Statistics)-CFAR performance are applied. Using matlab software, we show the performance and loss between detection probability and signal to noise ratio. When rang bins increase, this results show the OS-CFAR process performance is better than any others and satisfies the optimal detection probability without loss of detection in the homogeneous clutter.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.1-5
• /
• 2015

The V-grooved single-mode fiber in which a surface part of the core was removed was investigated as a quasi-distributed water detection sensor. In the normal state, the V-grooved region is filled and covered with a specific RI (Refractive Index)-matched medium, and the sensor experiences minimal optical loss. As water invades the V-grooved region, the material is dissolved and removed, and a considerable optical loss occurs owing to the large RI difference between the fiber core and water. The experimental results showed the feasibility of the device as a sensor element of the quasi-distributed water detection sensor system based on general optical time domain reflectometry (OTDR).

• Journal of Electrical Engineering and Technology
• /
• v.2 no.1
• /
• pp.19-28
• /
• 2007

The paper discussed various techniques for islanding detection and described in detail the working principles of ROCOF and vector shift relays. A simulator was used to investigate why the stability of both types of relays maybe affected by network and load switching, short-circuit faults and in the case of a ROCOF relay the loss of bulk generation or the tripping of a transmission feeder. Finally, to enhance the reliability of Loss of Mains protection, a new islanding detection technique based on a GPS synchronized phasor measurement system was proposed.