• 상하수도학회지
• /
• 제16권6호
• /
• pp.710-716
• /
• 2002

A General Pipe Break Prediction Model that incorporates linear and exponential models in its form is developed. The model is capable of fitting pipe break trends that have linear, exponential or in between of linear and exponential trend by using a weighting factor. The weighting factor is adjusted to obtain a best model that minimizes the sum of squared errors of the model. The model essentially plots a best curve (or a line) passing through "cumulative number of pipe breaks" versus "break times since installation of a pipe" data points. Therefore, it prevents over-predicting future number of pipe breaks compared to the conventional exponential model. The optimal replacement time equation is derived by using the Threshold Break Rate equation by Loganathan et al. (2002).

• 정보학연구
• /
• 제10권2호
• /
• pp.47-64
• /
• 2007

Finite failure NHPP models presented in the literature exhibit either constant, monotonic increasing or monotonic decreasing failure occurrence rates per fault. Accurate predictions of software release times, and estimation of the reliability and availability of a software product require quantification of a critical element of the software testing process : test coverage. This model called enhanced non-homogeneous poission process(ENHPP). In this paper, exponential coverage and S-coverage model was reviewed, proposes the exponentiated exponential coverage reliability model, which maked out efficiency substituted for gamma and Weibull model(2 parameter shape illustrated by Gupta and Kundu(2001). In this analysis of software failure data, algorithm to estimate the parameters used to maximum likelihood estimator and bisection method, model selection based on SSE statistics for the sake of efficient model, was employed.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2002년도 가을 학술발표회 논문집
• /
• pp.227-236
• /
• 2002

The purpose of this study makes a retrofit and rehabilitation practice trough the analysis and the improvement for the underlying problem of current retrofit and rehabilitation methods. Therefore, the deterioration process, the damage cause, the condition classification, the fatigue mechanism and the applied quantity of strengthening methods for RC deck slabs were analyzed. Artificial neural networks are efficient computing techniques that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a management on existing reinforced concrete bridge decks from damage cause, damage type, and integrity assessment at the initial stage is need. The training and testing of the network were based on a database of 36. Four different network models were used to study the ability of the neural network to predict the desirable output of increasing degree of accuracy. The neural networks is trained by modifying the weights of the neurons in response to the errors between the actual output values and the target output value. Training was done iteratively until the average sum squared errors over all the training patterns were minimized. This generally occurred after about 5,000 cycles of training.

• 한국구조물진단유지관리공학회 논문집
• /
• 제7권1호
• /
• pp.267-277
• /
• 2003

The purpose of this study makes a retrofit and rehabilitation practice trough the analysis and the improvement for the underlying problem of current retrofit and rehabilitation methods. Therefore, the deterioration process, the damage cause, the condition classification, the fatigue mechanism and the applied quantity of strengthening methods for slab bridge decks were analysed. Artificial neural networks are efficient computing techniqures that are widely used to solve complex problems in many fields. In this study, a back-propagation neural network model for estimating a management on existing slab bridge decks from damage cause, damage type, and integrity assessment at the initial stsge is need. The training and testing of the network were based on a database of 36. Four different network models werw used to study the ability of the neural network to predict the desirable output of increasing degree of accuracy. The neural networks is trained by modifying the weights of the neurons in response to the errors between the actual output values and the target output value. Training was done iteratively until the average sum squared errors over all the training patterms were minimized. This generally occurred after about 5,000 cycles of training.

• 한국군사과학기술학회지
• /
• 제22권1호
• /
• pp.27-34
• /
• 2019

This paper presents a chamber pressure model development of K2 rifle by applying Gaussian mixture model. In order to materialize a real recoil force of a virtual reality shooting rifle in military combat training, the chamber pressure which is one of major components of the recoil force needs to be investigated and modeled. Over 200,000 data of the chamber pressure were collected by implementing live fire experiments with both K100 and M193 of 5.56 mm bullets. Gaussian mixture method was also applied to create a mathematical model that satisfies nonlinear, asymmetry, and deviations of the chamber pressure which is caused by irregular characteristics of propellant combustion. In addition, Polynomial and Fourier Regression were used for comparison of results, and the sum of squared errors, the coefficient of determination and root-mean-square errors were analyzed for performance measurement.

• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.163-171
• /
• 1997

공학 분야에서 신경망에 대한 관심은 신호처리, 로보틱스, 컨트롤, 문자인식, 패턴인식 그리고 컴퓨터 그래픽 분야등에서 연구되고 있으며, 이들은 함수근사응용과 밀접한 관련이있다. 통계학 분야에서는 패턴인식의 판별분석, 주성분분석, 회귀분석 그리고 군집분석을 위한 신경망등에 대한 연구가 활발히 이루어지고 있다. 문자인식을 위한 다층 신경망을 학습시키기 위해 역전파 알고리즘이 널리 사용되고 있으나 이 알고리즘은 긴 훈련기간, 극소점 문제, 이상치(outlier)에 민감하다는 단점을 지니고 있다. 이상치에 민감한 일반적인 역전파 알고리즘의 단점을 극복하기 위해 이상치에 민감하지 않은 로버스트 알고리즘의 필요성이 대두되었다. 본 논문에서는 통계물리에서 자주 사용하는 방법을 이용하여 제안한 로버스트 역전파 알고리즘을 문자인식에 적용하여 일반적인 역전파 알고리즘의 문자인식 성능과 비교하였다.

• Smart Structures and Systems
• /
• 제15권5호
• /
• pp.1233-1252
• /
• 2015

This study investigates the problem of crack detection in post-buckled beam-type structures. The beam under the axial compressive force has a crack, assumed to be open and through the width. The crack, which is modeled by a massless rotational spring, divides the beam into two segments. The crack detection is considered as an optimization problem, and the weighted sum of the squared errors between the measured and computed natural frequencies is minimized by the bees algorithm. To find the natural frequencies, the governing nonlinear equations of motion for the post-buckled state are first derived. The solution of the nonlinear differential equations of the two segments consists of static and dynamic parts. The differential quadrature method along with an arc length strategy is used to solve the static part, while the same method is utilized for the solution of the linearized dynamic part and the extraction of the natural frequencies of the cracked beam. The investigation includes several numerical as well as experimental case studies on the post-buckled simply supported and clamped-clamped beams having open cracks. The results show that several parameters such as the amount of applied compressive force and boundary conditions influences the outcome of the crack detection scheme. The identification results also show that the crack position and depth can be predicted well by the presented method.

• 대한전자공학회논문지
• /
• 제26권3호
• /
• pp.160-166
• /
• 1989

공간영역 예측기의 계수를 계산하기 위한 적응 알고리듬이 제안되었다. 제안된 방법은 LMS 알고리듬을 사용하여 TDL(tapped-delay-line)과 ESC(escalator) 구조를 갖는 공간영역 예측기의 계수를 계산한다. 기종존의 일반적인 예측기와 다른점은 순방향과 역방향 예측 오차의 평균 자승값의 합을 최소화하며 예측기의 계수를 계산함으로 향상된 선형예측 공간 스펙트럼을 얻을 수 있다. 제안된 방법을 선형으로 배열된 센서에 의하여 얻어진 협대역신호의 입사각 추정문제에 적용시켜 기존의 적응예측 알고리듬과 컴퓨터 시뮬레이션을 통하여 성능을 비교하였다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 춘계학술대회논문집
• /
• pp.581-586
• /
• 2000

The equivalent source method is used to calculate the internal pressure field for an enclosure which can have arbitrary boundary conditions and may include internal objects which scatter the sound. Some of the equivalent positions are chosen to be the same as the first order images of the source inside the enclosure, some are positioned on a spherical surface some distance outside the enclosure. The normal velocity on the surfaces of the enclosure walls is evaluated at a larger number of positions than there are equivalent sources. The sum of the squared difference between this velocity and the expected is minimized by adjusting the strength of the equivalent sources. The convergence of this method is checked by evaluating the velocity error at a larger number of monitoring positions. Example results are presented for various numbers of sources and evaluation points. The results showed that in general the more equivalent sources increased the accuracy of the sound field predictions but the accuracy is not too much sensitive to the numbers of evaluation points.

• 한국음향학회지
• /
• 제14권1호
• /
• pp.22-30
• /
• 1995

본 논문은 입력 신호가 복수 정현파(multiple sinusoids) 신호로 구성되고 측정 잡음이 가우시안일 때 최소평균사승(least mean fourth : LMF) 알고리듬의 수렴 특성을 새로운 해석 기법을 적용하여 이론적으로 분석하였다. LMF알고리듬은 오차 신호의 4승을 비용 함수(cost function)로 하여 gradient-descent 방법으로 구한 적응 알고리듬인데 기존 Walach 와 Widrow의 수렴 특성 분석에서는 이루어지지 않았던 계수 추정 오차에 대한 2차 모멘트의 과도기 상태 수렴 특성을 본 논문에서 새로이 제시하였다. 결론적으로 가우시안 측정 잡음의 분산과 수렴 상수의 크기에 따라 서로 다른 수렴 특성을 나타냄을 알 수 있었다. 이러한 결과는 기존 Walach 와 Widrow의 분석 기법으로서는 알 수가 없었다.