• 한국국방경영분석학회지
• /
• 제37권1호
• /
• pp.39-48
• /
• 2011

야전에 저장된 탄약의 수명을 예측하는 것은 군의 전투지원 핵심요소로 실무적으로 매우 중요한 의미가 있다. 본 연구는 6년간 수행한 155mm 추진장약(KD541)의 ASRP(Ammunition Stockpile Reliability Program : 저장탄약신뢰성평가) 결과를 기초로 추진장약 추진제의 안정제함량 변화에 따른 시계열분석 (ARIMA 모델) 방법론을 적용 저장탄약수명을 예측하였다. 이번 연구는 기존의 회귀분석 모델을 활용한 연구방법과 다르게 시계열분석을 적용하되 미니 탭 프로그램을 활용하여 시계열분석을 적용 저장탄약수명을 예측하였다. 이러한 분석결과 155mm 추진장약(KD541) 저장수명은 35~43년으로 예측되었다.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• 한국철도학회논문집
• /
• 제9권6호
• /
• pp.732-738
• /
• 2006

This research provides a scheme for Highly Accelerated Stress Test that is necessary to demonstrate reliability prediction of Korean Rapid Transit Railway Train Control System sub-equipment, which is calculated by a relevant standard for failure rate prediction of electronic products. Although determining failure information generated in the process of trial running by statistic analysis is widely accepted as a measure of confirmation for reliability prediction, this research suggests the modeling for System Life Test determined by accelerating stress factors as a measure of confirmation for reliability prediction of sub-equipment unit that is generated ahead of a trial running in System Life Cycle. Consequently, the research demonstrates sub-equipment unit reliability test, which is based on the model derived from Accelerated Stress Test, according to accuracy level and the number of samples, and conducts an official experiment by making out a reliability test procedure sheet based on test time as well.

• Journal of Power Electronics
• /
• 제17권5호
• /
• pp.1288-1297
• /
• 2017

The estimation of the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is important for intelligent battery management system (BMS). Data mining technology is becoming increasingly mature, and the RUL estimation of Li-ion batteries based on data-driven prognostics is more accurate with the arrival of the era of big data. However, the support vector machine (SVM), which is applied to predict the RUL of Li-ion batteries, uses the traditional single-radial basis kernel function. This type of classifier has weak generalization ability, and it easily shows the problem of data migration, which results in inaccurate prediction of the RUL of Li-ion batteries. In this study, a novel multi-kernel SVM (MSVM) based on polynomial kernel and radial basis kernel function is proposed. Moreover, the particle swarm optimization algorithm is used to search the kernel parameters, penalty factor, and weight coefficient of the MSVM model. Finally, this paper utilizes the NASA battery dataset to form the observed data sequence for regression prediction. Results show that the improved algorithm not only has better prediction accuracy and stronger generalization ability but also decreases training time and computational complexity.

• 한국농공학회논문집
• /
• 제63권6호
• /
• pp.131-140
• /
• 2021

It is becoming more important to utilize reclaimed lands in South Korea, due to the increasing competition for its usage among different sectors. However, the high groundwater level and poor permeability are exposing them to deterioration by salinization. Salinization is difficult to predict because the pattern changes according to various characteristics of soil and groundwater. In this study, the capillary rising time was studied by the water content profile in the soil. The prediction equation of soil salinity was developed based on simulation result of the CHEMFLO model. to enable prediction considering various soil water content and groundwater level. The two terms constituting the equation showed the coefficients of determination of 0.9816 and 0.9824, respectively. Using the prediction equation of the study, the surface salinity can be easily predicted from the initial surface salinity and the salinity of the groundwater. In the future, more precise predictions will be possible with the results of studies on the hydraulic characteristics of various reclaimed soils, changes in water content profile by seasonal and climate events.

• Elastomers and Composites
• /
• 제49권2호
• /
• pp.144-148
• /
• 2014

자동차 엔진 부품용으로 많이 사용되는 ACM 고무 샘플에 대하여 $150^{\circ}C$, $160^{\circ}C$, $170^{\circ}C$, 및 $180^{\circ}C$의 등온상태에서 시간에 따른 압축영구줄음율(CS)과 열중량감소율을 측정하여 상관관계를 구하고, 이를 비등온 TGA를 이용하는 Toop의 해석방법에 이용하여 사용온도에서의 수명을 예측하고자 하였다. 노화촉진시험으로부터 측정된 중량감소율는 CS에 대하여 선형적으로 변화하는 것이 관찰되었으며, 이로부터 CS 40%에 이르는 시간을 재료의 수명시간으로 했을 때 중량감소에 의한 전환율은 4.2%로 나타났다. TGA 곡선으로부터 Flynn-Wall-Ozawa법에 의하여 전환율 4.2%에서의 활성화에너지는 120.2 kJ/mol로 계산되었으며, 이를 Toop의 해석법에 적용하였을 때의 예측수명은 사용온도 $120^{\circ}C$에서 약 9,700 시간으로 계산되었다.

• 한국안전학회지
• /
• 제31권1호
• /
• pp.19-24
• /
• 2016

Rubber parts are widely used in many applications such as dampers, shock absorbers, and seals used in railway and automotive industries. Much research has thus far been conducted on property estimation and life prediction of rubber parts. To predict the service life of rubber parts at room temperature, most prior work adopts the well-known Arrhenius model that needs the accelerated life test in high-temperature conditions. However, they may not reflect the actual conditions of use that rubber parts are usually used under a specific strain condition during long period of time. In this context, we propose a method for the life prediction of rubber parts in actual conditions of use. The proposed method is based on the accelerated life test using stress relaxation during which three relatively high elongation percentages (100%, 200%, and 300%) are applied to the rubber specimens. Rubber specimens were prepared in accordance with KS M 6518 standard and three stress relaxation testers were fabricated for actual experiments. Finally, a inverse power model for life prediction was derived from experimental results. The predicted life was compared with the actual test life for validation.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2004년도 추계학술발표회 발표논문집
• /
• pp.943-944
• /
• 2004

• Journal of Welding and Joining
• /
• 제23권4호
• /
• pp.1-6
• /
• 2005

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 추계학술대회 논문집
• /
• pp.63-64
• /
• 2008