• 한국추진공학회지
• /
• 제16권6호
• /
• pp.32-40
• /
• 2012

가스터빈 희박 예혼합 연소기에서 발생하는 연소 불안정의 고유 주파수 및 초기 성장률의 예측을 위하여 선형 열음향 해석 모델이 소개되었다. 모델 검증을 위하여 입출구 조건이 잘 정의되고, 상대적으로 이전 연구 결과에서 적용된 연소기에 비하여 구조가 간단한 모델 연소기가 선정되었다. 정의된 연소기에서 음향 해석을 위한 선형 관계식이 유도되었고, 이를 통하여 선형 안정성 해석 방안이 제시되었다. 해석 결과 연소 불안정의 특성에 대한 전체적인 변화 경향은 성공적으로 예측하였으나, 주파수의 절대값에 있어서는 실제 실험 결과보다 다소 작은 값을 예측하는 것으로 나타났다. 이러한 주파수의 예측 오차는 짧은 화염보다는 긴 화염에서 더욱 두드러지는 것으로 나타났다.

• 한국항공우주학회지
• /
• 제36권5호
• /
• pp.407-419
• /
• 2008

본 연구에서는 축 대칭 원뿔 형상 위의 압축성 경계층의 천이 지점을 선형 안정성 이론과 -method를 이용하여 예측하였다. 축 대칭 좌표계에서의 압축성 유동 지배 방정식으로부터 압축성 원뿔 경계층의 선형 안정성 방정식을 얻었으며 안정성 방정식을 2차 정확도의 유한 차분법을 이용하여 계산하는 수치 프로그램을 개발하였다. 개발 된 코드로 원뿔 경계층의 안정성 특성 및 2차원 교란의 증폭률을 계산하고 실험결과와의 비교를 통해 검증을 수행하였다. 얻어진 교란의 증폭률을 활용하여 -method를 통해 천이지점 예측을 수행하였다. 풍동 시험 및 비행 시험 결과와의 비교를 통해 비행 조건에 있는 마하수 4와 8사이의 원뿔 경계층에 대한 본 연구의 천이지점의 예측 능력을 확인하였다. 또한 벽면 냉각이 경계층 내부 교란의 안정성 및 천이 지점에 미치는 영향을 분석하였다.

• 한국자동차공학회논문집
• /
• 제12권2호
• /
• pp.117-122
• /
• 2004

The fatigue life in wheels was predicted by simulating the experimental method using Finite-Element analysis. Based on a high frequency fatigue property, calculations of the stresses in wheels were performed by simulating the rotating bending fatigue test. Wheels made of an aluminum alloy(A356.2) were tested using a bending fatigue tester. Results from bending fatigue test showed a linear correlation between bending moment and stress amplitude. Consequently, Finite-Element calculations were performed by a linear analysis. In order to find stress-cycles curves, spoke parts of wheel were tested using a rotary bending fatigue tester. Also, highly accurate Finite-Element analysis requires regression lines and confidence intervals from these results. In conclusion, if the fatigue data related to the material and manufacturing procedure are reliable, the prediction on fatigue lift in wheels can be carried out with high accuracy.

• 정보처리학회논문지B
• /
• 제9B권4호
• /
• pp.421-428
• /
• 2002

지금까지 삽입(Embedding)백터를 이용한 국소적예측방법은 고차미분방정식으로부터 생성된 카오스 시계열을 예측할 때, 파라메타 $\tau$의 추정이 정확하지 않으면 예측성능은 떨어졌다. 지금까지 지연시간 ($\tau$)의 값을 추정하는 방법은 많이 제안되어있지만 실제로 고차원미분방정식부터 생성되어진 수많은 시계열에 모두 적용 가능한 방법은 아직 없다. 이것을 기울기 백터를 이용한 기울기 선형모델을 도입하는 것에 의해 정확한 지연시간 ($\tau$)의 값을 추정하지 않아도 예측성능에 만족할 수 있는 결과를 표시했다. 이것을 이론뿐이 아니고 경제시계열에도 적용해서 종래의 예측방법과 비교해서 그 유효성을 표시했다.

• Nuclear Engineering and Technology
• /
• 제44권4호
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

• Educational Technology International
• /
• 제15권2호
• /
• pp.71-88
• /
• 2014

A variety of studies to predict students' performance have been conducted since educational data such as web-log files traced from Learning Management System (LMS) are increasingly used to analyze students' learning behaviors. However, it is still challenging to predict students' learning achievement in blended learning environment where online and offline learning are combined. In higher education, diverse cases of blended learning can be formed from simple use of LMS for administrative purposes to full usages of functions in LMS for online distance learning class. As a result, a generalized model to predict students' academic success does not fulfill diverse cases of blended learning. This study compares two blended learning classes with each prediction model. The first blended class which involves online discussion-based learning revealed a linear regression model, which explained 70% of the variance in total score through six variables including total log-in time, log-in frequencies, log-in regularities, visits on boards, visits on repositories, and the number of postings. However, the second case, a lecture-based class providing regular basis online lecture notes in Moodle show weaker results from the same linear regression model mainly due to non-linearity of variables. To investigate the non-linear relations between online activities and total score, RF (Random Forest) was utilized. The results indicate that there are different set of important variables for the two distinctive types of blended learning cases. Results suggest that the prediction models and data-mining technique should be based on the considerations of diverse pedagogical characteristics of blended learning classes.

• 한국음향학회지
• /
• 제15권5호
• /
• pp.38-43
• /
• 1996

본 논문에서는 잡음 및 주변 환경에 강인한 것으로 알려져 있는 특징 벡터들을 이용한 인식 성능을 비교하였다. 아울러 스펙트럼 차감법을 적용하여 높은 인식 성능을 얻도록 하였다. 본 논문에서는 환경 변화에 강인한 인식 성능을 얻기 위하여 SMC(Short time Modified Coherence) 분석, 루트(root) 켑스트럼 분석, LDA(Linear Discriminant Analysis), PLP(Perceptual Linear Prediction), RASTA(RelAtive SpecTrAl) 처리 등을 이용하여 인식 실험을 수행하였다. 실험을 위하여 반연속 HMM을 이용한 단독음 인식 시스템을 구현하였고 전시장 및 컴퓨터실의 잡음을 첨가하여 0, 10 및 20dB의 SNR에 대한 인식 실험을 수행하였다. 실험 결과, LPCC(Linear Prediction Cepstral Coefficient)를 이용한 경우에 비하여 SMC나 루트처리를 이용한 멜 켑스트럼(루트_멜 켑스트럼)을 이용한 경우 10dB의 SNR에서 각각 9.86%, 12.68% 향상된 가장 좋은 인식률을 얻었다. 또한 멜 켑스트럼과 루트_멜 켑스트럼을 스펙트럼 차감법과 결합하여 잡음을 제거한 경우 10dB에서 각각 16.7%, 8.4% 향상된 94.91%, 94.28%의 인식률을 얻을 수 있었다.

• 대한산업공학회지
• /
• 제40권3호
• /
• pp.283-290
• /
• 2014

In the flat panel display industry, to meet production target quantities and the deadline of production, the scheduler and dispatching systems are major production management systems which control the order of facility production and the distribution of WIP (Work In Process). Especially the delivery time is a key factor of the dispatching system for the time when a lot can be supplied to the facility. In this paper, we use survival analysis methods to identify main factors of the delivery time and to build the delivery time forecasting model. To select important explanatory variables, the cox proportional hazard model is used to. To make a prediction model, the accelerated failure time (AFT) model was used. Performance comparisons were conducted with two other models, which are the technical statistics model based on transfer history and the linear regression model using same explanatory variables with AFT model. As a result, the mean square error (MSE) criteria, the AFT model decreased by 33.8% compared to the statistics prediction model, decreased by 5.3% compared to the linear regression model. This survival analysis approach is applicable to implementing the delivery time estimator in display manufacturing. And it can contribute to improve the productivity and reliability of production management system.

• Journal of Korea Artificial Intelligence Association
• /
• 제1권1호
• /
• pp.11-16
• /
• 2023

Accurate hospital case modeling and prediction are crucial for efficient healthcare. In this study, we demonstrate the implementation of regression analysis methods in machine learning systems utilizing mathematical statics and machine learning techniques. The developed machine learning model includes Bayesian linear, artificial neural network, decision tree, decision forest, and linear regression analysis models. Through the application of these algorithms, corresponding regression models were constructed and analyzed. The results suggest the potential of leveraging machine learning systems for medical research. The experiment aimed to create an Azure Machine Learning Studio tool for the speedy evaluation of multiple regression models. The tool faciliates the comparision of 5 types of regression models in a unified experiment and presents assessment results with performance metrics. Evaluation of regression machine learning models highlighted the advantages of boosted decision tree regression, and decision forest regression in hospital case prediction. These findings could lay the groundwork for the deliberate development of new directions in medical data processing and decision making. Furthermore, potential avenues for future research may include exploring methods such as clustering, classification, and anomaly detection in healthcare systems.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.203-206
• /
• 1996

Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.