http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
방사성폐기물 핵종분석 검증용 이상 탐지를 위한 인공지능 기반알고리즘 개발
장승수,이장희,김영수,김지석,권진형,김송현 (사)한국방사선산업학회 2023 방사선산업학회지 Vol.17 No.1
The amount of radioactive waste is expected to dramatically increase with decommissioningof nuclear power plants such as Kori-1, the first nuclear power plant in South Korea. Accuratenuclide analysis is necessary to manage the radioactive wastes safely, but research on verification ofradionuclide analysis has yet to be well established. This study aimed to develop the technology thatcan verify the results of radionuclide analysis based on artificial intelligence. In this study, we proposean anomaly detection algorithm for inspecting the analysis error of radionuclide. We used the datafrom ‘Updated Scaling Factors in Low-Level Radwaste’ (NP-5077) published by EPRI (Electric PowerResearch Institute), and resampling was performed using SMOTE (Synthetic Minority OversamplingTechnique) algorithm to augment data. 149,676 augmented data with SMOTE algorithm was used totrain the artificial neural networks (classification and anomaly detection networks). 324 NP-5077 reportdata verified the performance of networks. The anomaly detection algorithm of radionuclide analysiswas divided into two modules that detect a case where radioactive waste was incorrectly classified ordiscriminate an abnormal data such as loss of data or incorrectly written data. The classification networkwas constructed using the fully connected layer, and the anomaly detection network was composedof the encoder and decoder. The latter was operated by loading the latent vector from the end layer ofthe classification network. This study conducted exploratory data analysis (i.e., statistics, histogram, correlation, covariance, PCA, k-mean clustering, DBSCAN). As a result of analyzing the data, it iscomplicated to distinguish the type of radioactive waste because data distribution overlapped each other. In spite of these complexities, our algorithm based on deep learning can distinguish abnormal data fromnormal data. Radionuclide analysis was verified using our anomaly detection algorithm, and meaningfulresults were obtained.
방사성물질 측정망 현황 및 하천·호소 내 인공방사성물질 (<sup>134</sup>Cs, <sup>137</sup>Cs, <sup>131</sup>I) 조사
김지유,정현지,안미정,홍정기,강태구,강태우,조윤해,한영운,설빛나,김완석,김경현,Kim, Jiyu,Jung, Hyun-ji,An, Mijeong,Hong, Jung-Ki,Kang, Taegu,Kang, Tae-Woo,Cho, Yoon-Hae,Han, Yeong-Un,Seol, Bitna,Kim, Wansuk,Kim, Kyunghyun 한국분석과학회 2015 분석과학 Vol.28 No.6
본 연구에서는「공공수역 방사성물질 측정망 운영 계획」에 따른 모니터링 수행 내용을 소개하였고, 하천 및 호소 60 개 지점을 대상으로 인공방사성물질(<sup>134</sup>Cs, <sup>137</sup>Cs, <sup>131</sup>I)의 농도를 조사하여 우리나라 지표수 내 방사성물질의 실태를 파악하고자 하였다. 채취된 시료는 마리넬리 비커를 이용한 감마분광 분석기법으로 분석하였다. <sup>134</sup>Cs와 <sup>137</sup>Cs은 모든 지점에서 MDA 미만으로 조사되었고, <sup>131</sup>I는 한 지점(0.533±0.058 Bq/L)을 제외한 모든 지점의 농도가 MDA 미만으로 나타났다. <sup>131</sup>I는 의료용으로 사용하는 물질로 환자의 배설물로 인해 하수처리장 인근 하천수에서 빈번하게 검출되는 물질로 알려져 있다. 따라서 <sup>131</sup>I가 검출된 원인을 파악하기 위해 하수처리장 방류지점을 포함한 <sup>131</sup>I가 검출된 상류수계 6개 지점을 추가 조사하였다. 조사결과, 하수처리장 처리수 방류지점에서부터 하류방향으로 <sup>131</sup>I가 지속적으로 검출되었으며, 농도는 0.257±0.034~0.799±0.051 Bq/L 범위로 조사되었다. 추가조사를 통해 하수처리장 방류수가 하천수의 <sup>131</sup>I 검출에 영향을 미치는 것으로 나타났다. A survey of the artificial radionuclides in rivers and lakes was conducted to investigate their levels in surface water. Water samples were collected at 60 points and analyzed by gamma-ray spectrometry with a measurement time of 10,000 seconds for <sup>134</sup>Cs, <sup>137</sup>Cs, and <sup>131</sup>I. The obained values were lower than MDA for all points, except one point for <sup>131</sup>I that was 0.533±0.058 Bq/L. <sup>131</sup>I is known as a radioactive material that occurs frequently in sewage treatment plants. Because it is often used for medical treatments and subject to spreading into the environment due to the excretion from the patients. For the point where <sup>131</sup>I was detected, we conducted additional investigation on the upstream river point and the effluent points of nearby sewage treatment plant to find the source of <sup>131</sup>I. <sup>131</sup>I was not detected at the upstream points of one of the upstream sewage treatment plants but found at the downstream points with the level being 0.257±0.034 to 0.799±0.051 Bq/L, proving the sewage treatment plant was the <sup>131</sup>Isource.
Sheng Qi,Shanqiang Wang,Ye Chen,Kun Zhang,Xianyun Ai,Jinglun Li,Haijun Fan,Hui Zhao 한국원자력학회 2022 Nuclear Engineering and Technology Vol.54 No.1
An artificial neural network (ANN) that identifies radionuclides from low-count gamma spectra of a NaIscintillator is proposed. The ANN was trained and tested using simulated spectra. 14 target nuclides wereconsidered corresponding to the requisite radionuclide library of a radionuclide identification devicementioned in IEC 62327-2017. The network shows an average identification accuracy of 98.63% on thevalidation dataset, with the gross counts in each spectrum Nc ¼ 100~10000 and the signal to noise ratioSNR ¼ 0.05e1. Most of the false predictions come from nuclides with low branching ratio and/or similardecay energies. If the Nc>1000 and SNR>0.3, which is defined as the minimum identifiable condition, theaveraged identification accuracy is 99.87%. Even when the source and the detector are covered with leadbricks and the response function of the detector thus varies, the ANN which was trained using nonshieldingspectra still shows high accuracy as long as the minimum identifiable condition is satisfied. Among all the considered nuclides, only the identification accuracy of 235U is seriously affected by theshielding. Identification of other nuclides shows high accuracy even the shielding condition is changed,which indicates that the ANN has good generalization performance.
방사성물질 측정망 현황 및 하천·호소 내 인공방사성물질 (<SUP>134</SUP>Cs, <SUP>137</SUP>Cs, <SUP>131</SUP>I) 조사
김지유(Jiyu Kim),정현지(Hyun-ji Jung),안미정(Mijeong An),홍정기(Jung-Ki Hong),강태구(Taegu Kang),강태우(Tae-Woo Kang),조윤해(Yoon-Hae Cho),한영운(Yeong-Un Han),설빛나(Bitna Seol),김완석(Wansuk Kim),김경현(Kyunghyun Kim) 한국분석과학회 2015 분석과학 Vol.28 No.6
Ju-Yong Yun,최석원,김창규,Jong-Yi Moon,Byung-Hwan Rho 대한방사선방어학회 2005 방사선방어학회지 Vol.30 No.4
The concentrations of natural and artificial radionuclides in soil and gamma ray dose rate in air at 233 locations in Korea have been determined. The national mean concentrations of 232Th, 226Ra , 40K , 137Cs and 90Sr in soil were 60±31, 33±14, 673±238, 35±9.3 and 5.0±3.4 Bq kg-1, respectively. The mean gamma-ray dose rate at 1 m above the ground was 79 18 nGy h-1. 137Cs concentration had highly significant correlation with organic matter content and cation exchange capacity. 90Sr concentration had slightly coherent with pH. The results have been compared with other global radioactivity and radiation measurements.
김지유,강태우,홍정기,안미정,장채원,김경현,한영운,강태구 한국분석과학회 2016 분석과학 Vol.29 No.6
137Cs was investigated in river bottom sediments located in South-Han River basin and it was compared with international case studies to estimate the concentration level of 137Cs in river sediment of Korea. The obtained values of 137Cs which was analyzed by gamma-ray spectrometry were in the range of <MDA~ 3.80 ± 0.14 Bq/kg·dry and similar to the 137Cs activities in soil of Korea. According to international case studies, 137Cs activities were between 3.7 to 15,396 Bq/kg·dry, when pollutants such as nuclear power plant accidents and radiation leaks were present near the rivers. The 137Cs activities showed a variety of distribution depending on the country, when pollution occurs and survey time. Also, 137Cs activities of river sediments without pollution sources were mostly less than 10 Bq/kg·dry in other countries. It was comparable with the obtained 137Cs activities in this study. The obtained values provide useful information on the background concentration of 137Cs in river sediment and will be able to use a basis for determining contamination of 137Cs in the river.
Yun, Ju-Yong,Choi, Seok-Won,Kim, Chang-Kyu,Moon, Jong-Yi,Rho, Byung-Hwan The Korean Association for Radiation Protection 2005 방사선방어학회지 Vol.30 No.4
The concentrations of natural and artificial radionuclides in soil and gamma ray dose rate in air at 233 locations in Korea have been determined. The national mean concentrations of $^{232}Th,\;^{226}Ra,\;^{40}K,\;^{137}Cs\;and\;^{90}Sr$ in soil were $60{\pm}31,\;33{\pm}14,\;673{\pm}238,\;35{\pm}9.3\;and\;5.0{\pm}3.4\;Bq\;kg^{-1}$, respectively. The mean gamma-ray dose rate at 1 m above the ground was $7918\;nGy\;h^{-1}$. $^{137}Cs$ concentration had highly significant correlation with organic matter content and cation exchange capacity. $^{90}Sr$ concentration had slightly coherent with pH. The results have been compared with other global radioactivity and radiation measurements.