• 한국정밀공학회지
• /
• 제32권11호
• /
• pp.989-995
• /
• 2015

In the literature, various stochastic anomaly detection methods, such as limit checking and PCA-based approaches, have been applied to weld defect detection. However, it is still a challenge to identify meaningful defect patterns from very limited sensor signals of laser welding, characterized by intermittent, discontinuous, very short, and non-stationary random signals. In order to effectively analyze the physical characteristics of laser weld signals: plasma intensity, weld pool temperature, and back reflection, we first transform the raw data of laser weld signals into the form of event logs. This is done by multidimensional discretization and event-codification, after which the event logs are decoded to extract weld defect patterns by $Na{\ddot{i}}ve$ Bayes classifier. The performance of the proposed method is examined in comparison with the commercial solution of PRECITEC's LWM$^{TM}$ and the most recent PCA-based detection method. The results show higher performance of the proposed method in terms of sensitivity (1.00) and specificity (0.98).

• Nuclear Engineering and Technology
• /
• 제53권9호
• /
• pp.2788-2802
• /
• 2021

Multigroup cross section (MG XS) generation by the UNIST in-house Monte Carlo (MC) code MCS for fast reactor analysis using nodal diffusion codes is reported. The feasibility of the approach is quantified for two sodium fast reactors (SFRs) specified in the OECD/NEA SFR benchmark: a 1000 MW_th metal-fueled SFR (MET-1000) and a 3600 MW_th oxide-fueled SFR (MOX-3600). The accuracy of a few-group XSs generated by MCS is verified using another MC code, Serpent 2. The neutronic steady-state whole-core problem is analyzed using MCS/RAST-K with a 24-group XS set. Various core parameters of interest (core k_eff, power profiles, and reactivity feedback coefficients) are obtained using both MCS/RAST-K and MCS. A code-to-code comparison indicates excellent agreement between the nodal diffusion solution and stochastic solution; the error in the core k_eff is less than 110 pcm, the root-mean-square error of the power profiles is within 1.0%, and the error of the reactivity feedback coefficients is within three standard deviations. Furthermore, using the super-homogenization-corrected XSs improves the prediction accuracy of the control rod worth and power profiles with all rods in. Therefore, the results demonstrate that employing the MCS MG XSs for the nodal diffusion code is feasible for high-fidelity analyses of fast reactors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4300-4314
• /
• 2019

With the development of video-related applications, media content has increased dramatically through applications. There is a substantial amount of near-duplicate videos (NDVs) among Internet videos, thus NDVR is important for eliminating near-duplicates from web video searches. This paper proposes a novel NDVR system that supports large-scale retrieval and contributes to the efficient and accurate retrieval performance. For this, we extracted keyframes from each video at regular intervals and then extracted both commonly used features (LBP and HSV) and new image features from each keyframe. A recent study introduced a new image feature that can provide more robust information than existing features even if there are geometric changes to and complex editing of images. We convert a vector set that consists of the extracted features to binary code through a set of hash functions so that the similarity comparison can be more efficient as similar videos are more likely to map into the same buckets. Lastly, we calculate similarity to search for NDVs; we examine the effectiveness of the NDVR system and compare this against previous NDVR systems using the public video collections CC_WEB_VIDEO. The proposed NDVR system's performance is very promising compared to previous NDVR systems.

• Current Optics and Photonics
• /
• 제2권6호
• /
• pp.612-622
• /
• 2018

In wave-front-sensor-less adaptive optics (WFS-less AO) systems, the Jacopo Antonello (JA) method belongs to the model-based class and requires few iterations to achieve acceptable distortion correction. However, this method needs a lot of measurements, especially when it deals with moderate or severe aberration, which is undesired in free-space optical communication (FSOC). On the contrary, the stochastic parallel gradient descent (SPGD) algorithm only requires three time measurements in each iteration, and is widely applied in WFS-less AO systems, even though plenty of iterations are necessary. For better and faster compensation, we propose a WFS-less hybrid approach, borrowing from the JA method to compensate for low-order wave front and from the SPGD algorithm to compensate for residual low-order wave front and high-order wave front. The correction results for this proposed method are provided by simulations to show its superior performance, through comparison of both the Strehl ratio and the convergence speed of the WFS-less hybrid approach to those of the JA method and SPGD algorithm.

• Design & Manufacturing
• /
• 제16권3호
• /
• pp.50-57
• /
• 2022

The qualities of the products produced by injection molding are strongly influenced by the process variables of the injection molding machine set by the engineer. It is very difficult to predict the qualities of the injection molded product considering the stochastic nature of the manufacturing process, since the processing conditions have a complex impact on the quality of the injection molded product. It is recognized that the artificial neural network(ANN) is capable of mapping the intricate relationship between the input and output variables very accurately, therefore, many studies are being conducted to predict the relationship between the results of the product and the process variables using ANN. However in the condition of a small number of data sets, the predicting performance and robustness of the ANN model could be reduced due to too many input variables. In the present study, the ANN model that predicts the length of the injection molded product for multiple combinations of process variables was developed. And the accuracy of each ANN model was compared for 8 process variables and 4 important process inputs that were determined by the feature selection. Based on the comparison, it was verified that the performance of the ANN model increased when only 4 important variables were applied.

• Smart Structures and Systems
• /
• 제29권3호
• /
• pp.485-498
• /
• 2022

In near-fault earthquake prone areas, the velocity pulse-like seismic waves often results in excessive horizontal displacement for structures, which may result in severe structural failure during large or near-fault earthquakes. The recently developed isolator-gap damper (IGD) systems provide a solution for the large horizontal displacement of long period base-isolated structures. However, the hysteresis characteristics of the IGD system are significantly different from the traditional hysteretic behavior. At present, the hysteretic behavior is difficult to be reflected in the structural analysis and performance evaluation especially under random earthquake excitations for lacking of effective analysis models which prevent the application of this kind of IGD system. In this paper, we propose a mathematical hysteretic model for the IGD system that presents its nonlinear hysteretic characteristics. The equivalent linearization is conducted on this nonlinear model, which requires the variances of the IGD responses. The covariance matrix for the responses of the structure and the IGD system is obtained for random earthquake excitations represented by the Kanai-Tajimi spectrum by solving the Lyapunov equation. The responses obtained by the equivalent linearization are verified in comparison with the nonlinear responses by the Monte Carlo simulation (MCS) analysis for random earthquake excitations.

• Structural Engineering and Mechanics
• /
• 제82권3호
• /
• pp.325-341
• /
• 2022

Previous major earthquakes indicated that the earthquake induced ground motions are typical non-stationary processes, which are non-stationary in both amplification and frequency. For the convenience of aseismic design and analysis, it usually assumes that the ground motions at structural supports are stationary processes. The development of time-frequency analysis technique makes it possible to evaluate the non-stationary responses of engineering structures subjected to non-stationary inputs, which is more general and realistic than the analysis method commonly used in engineering. In this paper, the wavelet-based stochastic vibration analysis methodology is adopted to calculate the non-stationary responses of multi-support structures. For comparison, the stationary response based on the standard random vibration method is also investigated. A frame structure and a two-span bridge are analyzed. The effects of non-stationary spatial ground motion and local site conditions are considered, and the influence of structural property on the structural responses are also considered. The analytical results demonstrate that the non-stationary spatial ground motions have significant influence on the response of multi-support structures.

• International Journal of Computer Science & Network Security
• /
• 제23권10호
• /
• pp.115-128
• /
• 2023

Deep learning has been incorporating various optimization techniques motivated by new pragmatic optimizing algorithm advancements and their usage has a central role in Machine learning. In recent past, new avatars of various optimizers are being put into practice and their suitability and applicability has been reported on various domains. The resurgence of novelty starts from Stochastic Gradient Descent to convex and non-convex and derivative-free approaches. In the contemporary of these horizons of optimizers, choosing a best-fit or appropriate optimizer is an important consideration in deep learning theme as these working-horse engines determines the final performance predicted by the model. Moreover with increasing number of deep layers tantamount higher complexity with hyper-parameter tuning and consequently need to delve for a befitting optimizer. We empirically examine most popular and widely used optimizers on various data sets and networks-like MNIST and GAN plus others. The pragmatic comparison focuses on their similarities, differences and possibilities of their suitability for a given application. Additionally, the recent optimizer variants are highlighted with their subtlety. The article emphasizes on their critical role and pinpoints buttress options while choosing among them.

• 대한교통학회지
• /
• 제22권7호
• /
• pp.99-106
• /
• 2004

본 연구에서는 바이레벨 문제를 풀기 위한 2가지 접근법, 즉 Cournot-Nash 게임과 Stackelbgerg 게임을 서로 비교하기 위한 것으로, 하위문제가 결정적인 통행배정문제(deterministic traffic assignment)인 경우와 확률적 통행배정문제(stochastic traffic assignment)인 경우로 구분하여 분석한다. 바이레벨 프로그램(bi-level program)은 상위문제(upper level program)과 하위 문제(lower level program)로 구성된 수리적인 문제로 상위문제는 목적하는 특정함수를 최적화시키는 형태이며, 하위문제는 통행자의 행태를 반영하는 형태로 구축된다. 기존에 제시된 알고리듬중 바이레벨문제의 대표적인 풀이 알고리듬인 IOA(Iterative Optimization Assignment) 알고리듬과 기종점 통행행렬추정(OD matrix estimation)에 주로 사용되는 IEA(Iterative Estimation Assignment)은 상위문제와 하위문제가 서로 독립적으로 존재하면서 설계변수와 통행량을 서로 주고받는 형태를 갖고 있어 Cournot-Nash 게임형태이다. 이에 반해, 최근에 제시된 민감도분석(Sensitivity analysis)을 기초로 한 알고리듬들은 상위문제에서 결정된 설계변수 변화에 대해 하위문제의 통행량변화를 민감도를 통해 고려하기 때문에 Stackelbeg게임이라고 볼 수 있다. 본 연구에서는 이들 알고리듬들을 비교하는 데 연구의 목적이 있으며, 기존에 제시된 기법과는 다른 좀 더 효율적인 접근법을 제시한다. 예제 교통망을 이용하여 제시된 모형들을 비교해본 결과, 결정적인 통행배정모형을 하위문제로 설정한 경우에는 두가지 접근법 모두 동일한 상위목적함수 값을 보여 우위를 판단할 수 없었지만, 확정적 통행배정모형으로 설정한 경우, Stackelberg게임 접근법이 Cournot-Nash게임 접근법 보다 더 우수함을 확인할 수 있었다.

• 한국광학회지
• /
• 제34권1호
• /
• pp.1-12
• /
• 2023

본 연구에서는 다채널 결맞음 빔결합 시스템을 위한 위상제어 방식으로 covariant matrix adaption evolution strategy (CMA-ES) 알고리즘 및 stochastic parallel gradient descent (SPGD) 알고리즘을 결합한 이중 위상제어 알고리즘을 제안하고 그 동작 특성을 전산모사를 통해 분석한다. 제안하는 CMA-ES/SPGD 이중 위상제어 알고리즘은 결합된 최종 출력광 세기가 미리 설정된 특정값에 도달하기 전까지는 그 위상제어 최적화를 CMA-ES 알고리즘을 통해 진행하고, 그 이후에는 SPGD 알고리즘으로 전환하여 진행하는 순차적 이중 구조를 취한다. 이를 이상적인 7채널과 19채널 광섬유 결합기 기반 결맞음 빔결함 시스템에 적용하였을 때, 위상제어 최적화 평균 수렴시간이 기존의 SPGD 알고리즘만 단독적용한 경우에 비해 약 10% 단축됨을 확인하였다. 뿐만 아니라, 동일한 결맞음 빔결함 시스템에서 실제 환경과 유사하게 각 채널광에 위상잡음을 부가적으로 인가한 경우, 본 연구에서 제안하는 이중 위상제어 알고리즘을 적용할 경우 주어진 조건에서 그 평균 수렴시간이 기존의 SPGD 알고리즘만 단독적용한 경우에 비해 7채널 시스템의 경우 약 17%, 19채널 시스템의 경우 약 16-27% 정도 단축됨을 확인하였다. 본 연구에서 제안한 CMA-ES/SPGD 이중 위상제어 알고리즘은 향후 실제 대기 환경과 같이 위상잡음 효과를 무시할 수 없는 조건에서 결맞음 빔결합을 구현시 매우 유용하게 활용될 수 있을 것으로 기대된다.