• 한국정보전자통신기술학회논문지
• /
• 제15권1호
• /
• pp.69-75
• /
• 2022

지금까지 발전 설비 터빈 블레이드의 이상 탐지는 사람에 의해 진행되어왔다. 하지만 발전 설비 노후화로 인한 이상 탐지 수요 증가와 터빈 블레이드의 이상을 검사하는 검사자 간의 기량 차로 인해 발생하는 검출 결과의 상이성으로 인해, 이러한 터빈 블레이드 이상 탐지 수요 증가와 인적 요소로 인해 발생하는 오류를 줄이고 높은 신뢰성의 터빈 블레이드 이상 검출성능을 안정적으로 제공할 수 있는 기법 개발의 필요성이 지속해서 제기되어 왔다. 이번 논문에서는 최근 다양한 분야에서 인상적인 성능 향상을 달성한 깊은 신경망을 이용한 발전 설비 터빈 블레이드의 이상 탐지 기술을 제안한다. 실험 결과는 제안된 기술이 인적 요소의 개입을 최소화함과 동시에 안정적인 이상 검출성능을 달성함을 증명한다.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.94-98
• /
• 2021

As the world's population grows, the food industry becomes increasingly important. Among them, agriculture is an industry that produces stocks of people all over the world, which is very important food industry. Despite the growing importance of agriculture, however, a large number of crops are lost every year due to pests and malnutrition. So, we propose a plant anomaly detection system for managing crops incorporating deep learning and drones with various possibilities. In this paper, we develop a system that analyzes images taken by drones and GPS of the drone's movement path and visually displays them on a map. Our system detects plant anomalies with 97% accuracy. The system is expected to enable efficient crop management at low cost.

• Structural Engineering and Mechanics
• /
• 제88권6호
• /
• pp.569-581
• /
• 2023

This paper introduces a system to detect and diagnose anomalies in pumped storage hydropower plants. We collect data from various types of sensors, including those monitoring temperature, vibration, and power. The data are classified according to the operation modes (pump and turbine operation modes) and normalized to remove the influence of the external environment. To detect anomalies and diagnose their types, we adopt a multivariate normal distribution analysis by learning the distribution of the normal data. The feasibility of the proposed system is evaluated using actual monitoring data of a pumped storage hydropower plant. The proposed system can be used to implement condition monitoring systems for other plants through modifications.

• 융합정보논문지
• /
• 제12권1호
• /
• pp.31-38
• /
• 2022

본 논문은 전문가 독립적 비지도 신경망 학습 기반 다변량 시계열 데이터 분석 모델인 MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder)의 실제 현장에서의 적용과 Auto-encoder 기반인 MSCRED 모델의 한계인, 학습 데이터가 오염되지 않아야 된다는 점을 극복하기 위한 학습 데이터 샘플링 기법인 Subset Sampling Validation을 제시한다. 라벨 분류가 되어있는 발전소 장비의 진동 데이터를 이용하여 1) 학습 데이터에 비정상 데이터가 섞여 있는 상황을 재현하고, 이를 학습한 경우 2) 1과 같은 상황에서 Subset Sampling Validation 기법을 통해 학습 데이터에서 비정상 데이터를 제거한 경우의 Anomaly Score를 비교하여 MSCRED와 Subset Sampling Validation 기법을 유효성을 평가한다. 이를 통해 본 논문은 전문가 독립적이며 오류 데이터에 강한 이상 진단 프레임워크를 제시해, 다양한 다변량 시계열 데이터 분야에서의 간결하고 정확한 해결 방법을 제시한다.

• Nuclear Engineering and Technology
• /
• 제52권10호
• /
• pp.2262-2273
• /
• 2020

Digital twin technology can provide significant value for the prognostics and health management (PHM) of critical plant components by improving insight into system design and operating conditions. Digital twinning of systems can be utilized for anomaly detection, diagnosis and the estimation of the system's remaining useful life in order to optimize operations and maintenance processes in a nuclear plant. In this regard, a conceptual framework for the application of digital twin technology for the prognosis of Control Element Drive Mechanism (CEDM), and a data-driven approach to anomaly detection using coil current profile are presented in this study. Health management of plant components can capitalize on the data and signals that are already recorded as part of the monitored parameters of the plant's instrumentation and control systems. This work is focused on the development of machine learning algorithm and workflow for the analysis of the CEDM using the recorded coil current data. The workflow involves features extraction from the coil-current profile and consequently performing both clustering and classification algorithms. This approach provides an opportunity for health monitoring in support of condition-based predictive maintenance optimization and in the development of the CEDM digital twin model for improved plant safety and availability.

• 한국지능시스템학회논문지
• /
• 제26권3호
• /
• pp.233-238
• /
• 2016

본 논문은 차세대 침입탐지 시스템을 위해서 데이터 융합에서의 불확실한 데이터 처리의 알고리즘을 제안한다. 차세대 침입탐지는 사이버 공간에서 생성되어지는 정보를 지식으로 만들어내기 위해 수많은 네트워크 센서로부터의 데이터가 수집되어진다. 수집된 센서 정보를 지식의 수준으로 이끌어내기 위해서 데이터 융합의 과정이 필요하다. 이를 위해 본 논문에서는 Demster-Shafer 증거이론 추론적 기법을 통하여 서로 다른 데이터들의 특징을 분석하여 불확실한 데이터가 어느 구간에서 신뢰구간을 갖는지를 분류하여, 불확실한 데이터에 대한 표현을 이루어낸다. 본 실험내용에서는 이러한 불확실성 데이터에 대한 이상탐지를 위해 iris plant 데이터세트를 이용한 신뢰구간에 따른 분류를 실행하였다. 이에 대해 각 신뢰구간을 통해서 데이터 분류가 가능하다는 것을 검증하였다.

• 전기전자학회논문지
• /
• 제24권2호
• /
• pp.403-408
• /
• 2020

태양광 발전은 특성상 간헐성과 불확실성이 항상 존재하기 때문에 정확한 예측은 어려우며, 실시간 발전량 진단을 위한 이상감지 기술이 중요하다. 본 논문에서는 다양한 파라미터의 상관관계를 도출하고 최근접 이웃 알고리즘을 적용하여 정상데이터와 비정상데이터를 분류한다. 두 분류의 결과는 발전 시스템의 결함에 의한 아웃라이어와 구름 등에 의해 단기간 동안 발생하는 부분 음영 및 전체 음영의 일시적인 전력손실을 보여준다. 100kW 발전소 데이터를 대상으로 머신러닝 분석을 수행하여 테스트 결과를 산출하였으며 실제 이상치와 이상치 후보지를 검증하였다.

• 산업경영시스템학회지
• /
• 제43권1호
• /
• pp.123-131
• /
• 2020

There have been a lot of studies in the past for the method of predicting the failure of a machine, and recently, a lot of researches and applications have been generated to diagnose the physical condition of the machine and the parts and to calculate the remaining life through various methods. Survival models are also used to predict plant failures based on past anomaly cycles. In particular, special machine that reflect the fluid flow and process characteristics of chemical plants are connected to hundreds or thousands of sensors, so there are not many factors that need to be considered, such as process and material data as well as application of derivative variables. In this paper, the data were preprocessed through time series anomaly detection based on unsupervised learning to predict the abnormalities of these special machine. Next, clustering results reflecting clustering-based data characteristics were applied to produce additional variables, and a learning data set was created based on the history of past facility abnormalities. Finally, the prediction methodology based on the supervised learning algorithm was applied, and the model update was confirmed to improve the accuracy of the prediction of facility failure. Through this, it is expected to improve the efficiency of facility operation by flexibly replacing the maintenance time and parts supply and demand by predicting abnormalities of machine and extracting key factors.

• 방사선산업학회지
• /
• 제17권1호
• /
• pp.19-32
• /
• 2023

The amount of radioactive waste is expected to dramatically increase with decommissioning of nuclear power plants such as Kori-1, the first nuclear power plant in South Korea. Accurate nuclide analysis is necessary to manage the radioactive wastes safely, but research on verification of radionuclide analysis has yet to be well established. This study aimed to develop the technology that can verify the results of radionuclide analysis based on artificial intelligence. In this study, we propose an anomaly detection algorithm for inspecting the analysis error of radionuclide. We used the data from 'Updated Scaling Factors in Low-Level Radwaste' (NP-5077) published by EPRI (Electric Power Research Institute), and resampling was performed using SMOTE (Synthetic Minority Oversampling Technique) algorithm to augment data. 149,676 augmented data with SMOTE algorithm was used to train the artificial neural networks (classification and anomaly detection networks). 324 NP-5077 report data verified the performance of networks. The anomaly detection algorithm of radionuclide analysis was divided into two modules that detect a case where radioactive waste was incorrectly classified or discriminate an abnormal data such as loss of data or incorrectly written data. The classification network was constructed using the fully connected layer, and the anomaly detection network was composed of the encoder and decoder. The latter was operated by loading the latent vector from the end layer of the 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 is complicated 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 from normal data. Radionuclide analysis was verified using our anomaly detection algorithm, and meaningful results were obtained.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1996년도 춘계학술발표회논문집(2)
• /
• pp.499-504
• /
• 1996

Current Probabilistic Safety Assessment (PSA) techniques are not usually utilized for day-to-day applications in nuclear power plants. The major reason for this anomaly is the complexity of plant models developed for PSA studies and the multitude of resulting fault trees. This impediment can be overcome by the use of simplified plant models. However, oversimplified models usually result in loss of valuable information and therefore. simplification approaches have to be used judiciously in order to achieve accurate and meaningful results. For this reason. development of an appropriate simplification approach must be performed using extreme caution followed with results verification in sequence as well as system levels. If there are no significant differences between the simplified and the original models, the simplified model can be efficiently used in the application of the PSA. This paper presents a methodology for how to develop a suitable simplification technique and the results of its verification for sample systems and sequences. The results show that the utilization of simplified plant models will significantly reduce the number of fault trees with no significant loss of accuracy.