• Nuclear Engineering and Technology
• /
• 제56권4호
• /
• pp.1284-1295
• /
• 2024

Due to increasing operational security demands, digital and intelligent condition monitoring of nuclear power plants is becoming more significant. However, establishing an accurate and effective anomaly detection model is still challenging. This is mainly because of data characteristics of nuclear power data, including the lack of clear class labels combined with frequent interference from outliers and anomalies. In this paper, we introduce a Transformer-based unsupervised model for anomaly detection of nuclear power data, a modified loss function based on the maximum correntropy criterion (MCC) is applied in the model training to improve the robustness. Experimental results on simulation datasets demonstrate that the proposed Trans-MCC model achieves equivalent or superior detection performance to the baseline models, and the use of the MCC loss function is proven can obviously alleviate the negative effect of outliers and anomalies in the training procedure, the F1 score is improved by up to 0.31 compared to Trans-MSE on a specific dataset. Further studies on genuine nuclear power data have verified the model's capability to detect anomalies at an earlier stage, which is significant to condition monitoring.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.570-574
• /
• 2003

In most boundary estimation algorithms estimation in EIT (Electrical Impedance Tomography), anomaly boundaries can be expressed with Fourier series and the unknown coefficients are estimated with proper inverse algorithms. Furthermore, the number of anomalies is assumed to be available a priori. The prior knowledge on the number of anomalies may be unavailable in some cases, and we need to determine the number of anomalies with other methods. This paper presents an algorithm for the boundary estimation in EIT (Electrical Impedance Tomography) using the prior information from the conventional Newton-Raphson method. Although Newton-Raphson method generates so poor spatial resolution that the anomaly boundaries are hardly reconstructed, even after a few iterations it can give general feature of the object to be imaged such as the number of anomalies, their sizes and locations, as long as the anomalies are big enough. Some numerical experiments indicate that the Newton-Raphson method can be used as a good predictor of the unknown boundaries and the proposed boundary discrimination algorithm has a good performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.490-492
• /
• 2005

Unattended continuous containment/surveillance systems for safeguards of nuclear facility result in large amounts of image and radiation data, which require much time and effort to inspect. Therefore, it is necessary to develop system that automatically pinpoints and diagnoses the anomalies from data. In this regards, this paper presents the nuclear material containment/surveillance system that integrates visual image and radiation data.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권3호
• /
• pp.1119-1123
• /
• 2014

Head and neck cancers (HNC) are extremely complex disease types and it is likely that chromosomal instability is involved in the genetic mechanisms of its genesis. However, there is little information regarding the background levels of chromosome instability in these patients. In this pilot study, we examined spontaneous chromosome instability in short-term lymphocyte cultures (72 hours) from 72 study subjects - 36 newly diagnosed HNC squamous cell carcinoma patients and 36 healthy ethnic controls. We estimated chromosome instability (CIN) using chromosomal aberration (CA) analysis and nuclear level anomalies using the Cytokinesis Block Micronucleus Cytome Assay (CBMN Cyt Assay). The proliferation rates in cultures of peripheral blood lymphocytes (PBL) were assessed by calculating the Cytokinesis Block Proliferation Index (CBPI). Our results showed a significantly higher mean level of spontaneous chromosome type aberrations (CSAs), chromatid type aberration (CTAs) dicentric chromosomes (DIC) and chromosome aneuploidy (CANE UP) in patients (CSAs, $0.0294{\pm}0.0038$; CTAs, $0.0925{\pm}0.0060$; DICs, $0.0213{\pm}0.0003$; and CANE UPs, $0.0308{\pm}0.0035$) compared to controls (CSAs, $0.0005{\pm}0.0003$; CTAs, $0.0058{\pm}0.0015$; DICs, $0.0005{\pm}0.0003$; and CANEUPs, $0.0052{\pm}0.0013$) where p<0.001l. Similarly, spontaneous nuclear anomalies showed significantly higher mean level of micronuclei (MNi), nucleoplasmic bridges (NPBs) and nuclear buds (NBUDs) among cases (MNi, $0.01867{\pm}0.00108$; NPBs, $0.0156{\pm}0.00234$; NBUDs, $0.00658{\pm}0.00068$) compared with controls (MNi, $0.00027{\pm}0.00009$; NPBs, $0.00002{\pm}0.00002$; NBUDs, $0.00011{\pm}0.00007$).The evaluation of CBPI supported genomic instability in the peripheral blood lymphocytes showing a significantly lower proliferation rate in HNC patients ($1.525{\pm}0.005552$) compared to healthy subjects ($1.686{\pm}0.009520$) (p<0.0001). In conclusion, our preliminary results showed that visible spontaneous genomic instability and low rate proliferation in the cultured peripheral lymphocytes of solid tumors could be biomarkers to predict malignancy in early stages.

• 한국발생생물학회:학술대회논문집
• /
• 한국발생생물학회 2005년도 제5회 발생공학 국제심포지엄 및 학술대회
• /
• pp.16-22
• /
• 2005

• 한국수정란이식학회:학술대회논문집
• /
• 한국수정란이식학회 2005년도 제5회 발생공학 국제심포지엄 및 학술대회
• /
• pp.16-22
• /
• 2005

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2003년도 추계공동학술대회
• /
• pp.135-144
• /
• 2003

In this paper, the implementation techniques of intelligent nuclear material surveillance system based on the SOM(Self Organized Mapping) was described. Unattended continuous surveillance systems for nuclear facility result in large amounts of data, which require much time and effort to inspect. Therefore, it is necessary to develop system that automatically pinpoints and diagnoses the anomalies from data. In this regards, this paper presents a novel concept of a continuous surveillance system that integrates visual image and radiation data by the use of neural networks based on self-organized feature mapping

• Nuclear Engineering and Technology
• /
• 제54권11호
• /
• pp.3985-3995
• /
• 2022

The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types of radiation like Total Ionizing Dose (TID) can cause permanent damages on such nanoscale electronic devices, and current state-of-the-art technologies to tackle TID make use of expensive radiation-hardened devices. This paper focuses on a novel and different approach: using machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle TID effects and monitor them to replace before they stop working. This condition has a research challenge to anticipate when the board results in a total failure due to TID effects. We observed internal measurements of FPGA boards under gamma radiation and used three different anomaly detection machine learning (ML) algorithms to detect anomalies in the sensor measurements in a gamma-radiated environment. The statistical results show a highly significant relationship between the gamma radiation exposure levels and the board measurements. Moreover, our anomaly detection results have shown that a One-Class SVM with Radial Basis Function Kernel has an average recall score of 0.95. Also, all anomalies can be detected before the boards are entirely inoperative, i.e. voltages drop to zero and confirmed with a sanity check.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2001년도 Proceedings ICPE 01 2001 International Conference on Power Electronics
• /
• pp.52-55
• /
• 2001

This paper is to see the availability of electrical signatures as a means for evaluating the performance and monitoring mechanical anomalies of (MOVs). To estimate motor torque, two methods such as d-q frame conversion and air-gap method are suggested and estimated results are compared with measured values. The error between measured and estimated torques is within acceptable error bound with below $1\%$ under varied load. Frequency domain analysis of calculated torque has been done as well. It is shown that monitoring of peak frequency could give useful clues to detect anomalies of MOV. As results, electrical signatures at MOV motor is expected to be an available tool for estimation of motor capacity and monitoring of electrical and mechanical abnormalities.

• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.603-622
• /
• 2023

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.