• Food Science and Biotechnology
• /
• 제14권5호
• /
• pp.628-633
• /
• 2005

Muscle fiber characteristics were evaluated for predictability of meat quality traits using 231 crossbred pigs. Muscle $pH_{45min}$, R-value, and $pH_{24hr}$ were selected to estimate regression equation model of drip loss and lightness, although variances of coefficient estimates could only account for small part of drip loss (about 16.3 to 25.3%) and lightness (about 16.9 to 31.7%). Muscle $pH_{24hr}$ was represented to drip loss and lightness, which explained corresponding 25.3 and 31.7% of estimation in drip loss and lightness, respectively. Area percentage of type IIb fiber significantly contributed to prediction of metabolic rate and meat quality. However, equations predicting meat quality traits based on area percentage of type IIb fiber alone are less useful than ones based on early postmortem parameters. These results suggest estimated model using both metabolic properties of muscle and postmortem metabolic rate could be used for prediction of pork quality traits.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제5권4호
• /
• pp.427-438
• /
• 2005

This paper is concerned with the problem in predicting the reliability of an LCD product, Product reliability calculation methods classify accelerated life test (ALT) and using the reliability standard as MIL-HDBK-217F and Telcordia SR-332. The reliability standard can calculate estimating value more quickly than accelerated life test. The system MTBF was calculated in accordance of Telcordia SR-332 standard which includes directions of part electronic measurement, temperature rise and environmental test data. This research is intended to obtain the useful information for each electric design step to save time and cost.

• Journal of Biosystems Engineering
• /
• 제33권1호
• /
• pp.63-68
• /
• 2008

This study was carried out to find a useful method to predict hardness of tomato using optical spectrum data. Optical spectrum of reflectance and transmittance data were collected processed by 9 kind of preprocessing methods-normalizations of mean, maximum and range, SNV (standard normal variate), MSC (multiplicative scatter correction), the first derivative and second derivative of Savitzky-Golay and Norris-Gap. With the preprocessed and non-processed original spectrum data, prediction models of hardness of tomato were developed using analytical tools of PLS (partial least squares) and MLR (multiple linear regression) and tested for their validation. The test of validation resulted that the analytical tools of PLS and MLR output similar performances while the transmittance spectra showed much better result than the reflectance spectra.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2004년도 The 3rd Annual Conference for The Korean Society for Bioinformatics Association of Asian Societies for Bioinformatics 2004 Symposium
• /
• pp.158-166
• /
• 2004

Predicting the destination of a protein in a cell gives valuable information for annotating the function of the protein. Recent technological breakthroughs have led us to develop more accurate methods for predicting the subcellular localization of proteins. The most important factor in determining the accuracy of these methods, is a way of extracting useful features from protein sequences. We propose a new method for extracting appropriate features only from the sequence data by computing pairwise sequence alignment scores. As a classifier, support vector machine (SVM) is used. The overall prediction accuracy evaluated by the jackknife validation technique reach 94.70% for the eukaryotic non-plant data set and 92.10% for the eukaryotic plant data set, which show the highest prediction accuracy among methods reported so far with such data sets. Our numerical experimental results confirm that our feature extraction method based on pairwise sequence alignment, is useful for this classification problem.

• 한국통신학회논문지
• /
• 제42권4호
• /
• pp.939-949
• /
• 2017

고장 예지 및 건전성 관리 기술(Prognostics and Health Management; PHM)은 시스템의 현재 상태를 진단하고 향후 발생 가능한 고장 시점을 신뢰성 있게 예지하는 기술로써 유지 보수 비용의 절감 및 시스템의 안정성 향상을 꾀하고자 하는 다양한 산업분야에서 활발하게 이용되고 있다. 스마트 그리드의 에너지 저장장치, 전기차, 스마트폰, 항공우주산업 등 광범위한 사용처에서 중요한 에너지원으로 사용되고 있는 배터리 또한 성능 저하 및 폭발의 위험성으로부터 자유로울 수 없기 때문에 이러한 고장 예지 및 건전성 관리 기술이 반드시 적용되어야 할 어플리케이션이다. 본 논문에서는 PHM의 기본적인 개념을 소개함과 동시에 배터리의 잔존 유효 수명(Remaining Useful Life; RUL)을 예측하는 각종 알고리즘 및 성능 평가 지표 서술에 초점을 맞추도록 한다. 더불어 배터리의 기능적 동작 원리 및 전기화학 기반의 모델링에 대한 설명을 통해 향후 잠재적인 가능성을 지닌 배터리의 전반적인 특성에 대한 깊은 이해 및 응용 기술에 대한 통찰력을 제시하고자 한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.15-16
• /
• 2020

본 논문에서는 산업 현장에서 사용되는 기계들의 건전성을 유지하고 예측하는 시스템을 개선할 수 있는 연구 결과를 비교하고 설명한다. 이번 연구에서는 딥러닝 기술을 이용함으로서 특정장치에 종속되지 않고 범용적으로 수집된 소음데이터를 사용하여 현장 적용의 유연성을 높이고, 딥러닝 모델 중 GRU를 이용하여 기존 연구 결과와 비교 실험을 하여 더 우수한 결과를 얻었다.

• International Journal of Fluid Machinery and Systems
• /
• 제2권1호
• /
• pp.21-30
• /
• 2009

Slurry wear with sand particles in rivers is a serious problem for pump operation. Therefore, a technique to predict wear volume loss is required for selecting wear resistant materials and determining specifications for the maintenance period. This paper reports a method for predicting the wear depth distribution on the blade of an impeller. Slurry wear tests of an aluminum pump impeller were conducted. Prediction results of wear depth distribution approximately correspond with the results of slurry wear tests. This technique is useful for industrial application.

• 한국산학기술학회논문지
• /
• 제16권7호
• /
• pp.4398-4404
• /
• 2015

스테인리스 강판은 동적기계구조물을 제작하기 위한 구조용 재료로 널리 사용된다. 또한 이들을 일체화 시키는 방법으로 가스용접을 많이 사용하게 되는데 가스용접에는 다양한 종류에 의해 구조물을 일체화 시킨다. 따라서 부재와 부재를 연결하는 용접부에 대한 응력분포 및 피로강도평가는 구조물의 건전성 및 수명을 연구하는데 매우 중요한 요소가 된다. 그래서 본 연구에서는 피로시험에 의해서 얻어지는 ${\Delta}P-N_f$ 관계를 유한요소해석법에 의해서 최대주응력으로 ${\Delta}{\sigma}-N_f$ 관계로 나타내어 피로설계기준을 정하였고, 이 결과를 이용해서 확률론적 통계해석기법을 적용해서 가속식을 추정하여 임의의 목표수명을 예측할 수 있는 신뢰성설계기술기법을 제시하고자 하였다.

• 한국정밀공학회지
• /
• 제28권9호
• /
• pp.1062-1069
• /
• 2011

In electro-galvanizing line to manufacture the electro-galvanized steel sheet, polishing system is required to maintain clean surface of conductor roll and to secure the quality of the steel sheet. At the same time, prediction and decision of the replacement cycle for felt material and its brush installed in the polishing system is also important because the brush is directly contacted on the conductor roll surface. In this study, the polishing system has been designed which the brush is repetitive translating according to the longitudinal direction of the conductor roll. Furthermore, the prediction on the wear-life of the felt material used for the brush is performed using the contact pressure extracted by finite element analysis. And to verify the predicted wear-life of the felt material, the experimental study is also carried out. From the comparison result between the predicted and the measured wear-life of the felt material, it is presented that the wear-life and the replacement cycle of the felt material are well predicted by considering a wear compensation factor, and the wear compensation factor is useful and reasonable.

• Tribology and Lubricants
• /
• 제14권4호
• /
• pp.7-14
• /
• 1998

A correlation between the low-cycle fatigue life and the scuffing-failure life is demonstrated using the plastic strain increment in boundary lubricated sliding. Loadings proportional to hardness with three different lubricated conditions were used to evaluate the plastic strain increments. As the results of scuffing tests using vacuum pump oils in nitrogen gas, plastic strain increment shows 0.0062, and in the mineral oils and commercial engine oils in air, plastic strain increments show 0.0042 and 0.00092. Those are very useful to describe quantitatively the real lubricated sliding conditions, and are very effective to find the relation between the low-cycle fatigue life and the scuffing-failure life.