• Nuclear Engineering and Technology
• /
• 제54권4호
• /
• pp.1230-1244
• /
• 2022

This paper proposes an algorithm for signal validation using unsupervised methods in emergency situations at nuclear power plants (NPPs) when signals are rapidly changing. The algorithm aims to determine the stuck failures of signals in real time based on a variational auto-encoder (VAE), which employs unsupervised learning, and long short-term memory (LSTM). The application of unsupervised learning enables the algorithm to detect a wide range of stuck failures, even those that are not trained. First, this paper discusses the potential failure modes of signals in NPPs and reviews previous studies conducted on signal validation. Then, an algorithm for detecting signal failures is proposed by applying LSTM and VAE. To overcome the typical problems of unsupervised learning processes, such as trainability and performance issues, several optimizations are carried out to select the inputs, determine the hyper-parameters of the network, and establish the thresholds to identify signal failures. Finally, the proposed algorithm is validated and demonstrated using a compact nuclear simulator.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 정기총회 및 추계학술대회 논문집 학회본부
• /
• pp.317-319
• /
• 1993

The function estimation characteristics of neural networks can be used for sensor signal validation of a system. In case of applying the neural networks to signal validation, it is a important problem that the redundant sensor signals used as a input signal of neural networks should be validated. In this paper, we simplify the conventional parity space method in order to input the validated signal to the neural networks and also propose the sensor signal validation method, which estimates the reliable sensor output combining neural networks with the simplified parity space method. The acceptability of the proposed signal validation method is demonstrated by using the simulation data in safety injection accident of nuclear power plants.

• 제어로봇시스템학회논문지
• /
• 제4권6호
• /
• pp.765-771
• /
• 1998

An artificial neural network(NN) technique is developed for hardware redundant sensor validation. Since the measurement space is a continuous space with many operating regions, it is difficult to train a NN to correctly detect failure in an accurate measurement system. A conventional backpropagation NN is modified to include an additional preprocessing layer that extracts classification features from scalar measurements. This feature extraction means transform the measurement space to parity space. The NN is independent of the state variable being measured, the instrument range, and the signal tolerance. This NN resembles the parity space approach to signal validation, except that analytical parity equations are unneeded and the NN pattern recognition capability is utilized for decision making.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.175-177
• /
• 1995

The sensor signal validation and failure detection system must be able to detect, isolate, and identify sensor degradation as well as provide a reconstruction of the measurements. In this study, this is accomplished by combining the neural network, the Generalized Consistency Checking(GCC), and the Sequential Probability Ratio Test(SPRT) method in a decision estimator module. The GCC method is a computationally efficient system for redundant sensors, while the SPRT provides the ability to make decisions based on the degradation history of a sensor. The methodology is also extended to the detection of noise degradation. The acceptability of the proposed method is demonstration by using the simulation data in safety injection accident of nuclear power plants. The results show that the signal validation and sensor failure detection system is able to detect and isolate a bias failure and noise type failures under transient conditions. And also, the system is able to provide the validated signal by reconstructing the measurement signals in the failure conditions considered.

• 한국군사과학기술학회지
• /
• 제17권1호
• /
• pp.108-114
• /
• 2014

This paper describes a method to set an intensity-based initial validation gate for tracking filter while preserves the ability of tracking a target with maximum speed. First, we collected real data set of signal versus distance of an airplane target. And at each data point, we computed maximum distance the target can move. And a function is modeled to expect the maximum moving pixels on the lateral direction based on the intensity of the detected target in IR image sequence. The initial prediction error covariance can be computed using this function to decide the size of the initial validation gate. The simulation results show the proposed method can set the appropriate initial validation gates to track the targets with the maximum speed.

• 한국시뮬레이션학회논문지
• /
• 제25권3호
• /
• pp.15-28
• /
• 2016

수중환경에서 운영되는 무기체계 획득을 위한 설계/개발을 진행하기 위해 수중음향채널 모델링 및 시뮬레이션을 통한 분석은 필수적이다. 일반적으로 수중음향채널 분석을 위해 사용되는 수중음향 전파 수치해석 모델은 음선이론 법, 정규방식 법, 포물선방정식 법, 파수적분 법이 있으나 다중 주파수 분석일 경우 유효성과 신호처리 및 분석에 제한적이다. 본 논문은 단일 및 다중 주파수 분석 및 신호처리 및 분석이 용이한 기존 의사 스펙트럼 시간영역 법 수중음향 수치해석 모델에 수중환경 소음 모델을 적용하여 실제 수중환경과 유사한 합성환경 수중음향채널을 모델링 하였다. 이렇게 구현된 합성환경 수중음향채널 모델의 유효성을 확인하기 위해 단일 주파수 신호 시나리오 4가지 다중 주파수 신호 시나리오 4가지 및 잠수함 기동에 따른 방사소음 분석 시나리오 시뮬레이션을 통해 의사 스펙트럼 시간영역 법 합성환경 수중음향채널 모델 유효성을 확인하였다.

• Nuclear Engineering and Technology
• /
• 제26권3호
• /
• pp.367-373
• /
• 1994

원전 계측제어계통의 설계구현에서는 알고리즘및 독립적 검토의 복잡성을 피하기 위해 되도록 간단한 신호검증방법이 일차적으로 요청된다. 본 논문은 다중채널측정 시스템의 채널간의 일치성검사를 기본으로 하여 개발된 신호검증 알고리즘을 제안한다. 이 방법은 간략화한 고정편차 추정법을 포함하며, 추정된 고정편차의 크기를 고려한 가중인자를 사용하여 가중평균을 구한다. 제시된 방법의 성능을 확인하기 위하여 가상의 다중입력 조건으로 실험하였다.

• Communications for Statistical Applications and Methods
• /
• 제22권2호
• /
• pp.159-172
• /
• 2015

This paper considers the problem of reconstructing an underlying signal from noisy data. This paper presents a reconstruction method based on synchrosqueezed wavelet transform recently developed for multiscale representation. Synchrosqueezed wavelet transform based on continuous wavelet transform is efficient to estimate the instantaneous frequency of each component that consist of a signal and to reconstruct components. However, an objective selection method for the optimal number of intrinsic mode type functions is required. The proposed method is obtained by coupling the synchrosqueezed wavelet transform with cross-validation scheme. Simulation studies and musical instrument sounds are used to compare the empirical performance of the proposed method with existing methods.

• Journal of Biosystems Engineering
• /
• 제41권3호
• /
• pp.208-220
• /
• 2016

Purpose: Fusel oil is a potent volatile aroma compound found in many alcoholic beverages. At low concentrations, it makes an essential contribution to the flavor and aroma of fermented alcoholic beverages, while at high concentrations, it induced an off-flavor and is thought to cause undesirable side effects. In this work, we introduce Fourier transform near-infrared (FT-NIR) spectroscopy as a rapid and nondestructive technique for the quantitative determination of fusel oil in the Korean alcoholic beverage "soju". Methods: FT-NIR transmittance spectra in the 1000-2500 nm region were collected for 120 soju samples with fusel oil concentrations ranging from 0 to 1400 ppm. The calibration and validation data sets were designed using data from 75 and 45 samples, respectively. The net analyte signal (NAS) was used as a preprocessing method before the application of the partial least-square regression (PLSR) and principal component regression (PCR) methods for predicting fusel oil concentration. A novel variable selection method was adopted to determine the most informative spectral variables to minimize the effect of nonmodeled interferences. Finally, the efficiency of the developed technique was evaluated with two different validation sets. Results: The results revealed that the NAS-PLSR model with selected variables ($R^2_{\upsilon}=0.95$, RMSEV = 100ppm) did not outperform the NAS-PCR model (($R^2_{\upsilon}=0.97$, RMSEV = 7 8.9ppm). In addition, the NAS-PCR shows a better recovery for validation set 2 and a lower relative error for validation set 3 than the NAS-PLSR model. Conclusion: The experimental results indicate that the proposed technique could be an alternative to conventional methods for the quantitative determination of fusel oil in alcoholic beverages and has the potential for use in in-line process control.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2005년도 추계학술발표회
• /
• pp.1071-1072
• /
• 2005