• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2012년도 제42회 동계 정기 학술대회 초록집
• /
• pp.241-241
• /
• 2012

Semiconductor industry has been taking the advantage of improvements in process technology in order to maintain reduced device geometries and stringent performance specifications. This results in semiconductor manufacturing processes became hundreds in sequence, it is continuously expected to be increased. This may in turn reduce the yield. With a large amount of investment at stake, this motivates tighter process control and fault diagnosis. The continuous improvement in semiconductor industry demands advancements in process control and monitoring to the same degree. Any fault in the process must be detected and classified with a high degree of precision, and it is desired to be diagnosed if possible. The detected abnormality in the system is then classified to locate the source of the variation. The performance of a fault detection system is directly reflected in the yield. Therefore a highly capable fault detection system is always desirable. In this research, time series modeling of the data from an etch equipment has been investigated for the ultimate purpose of fault diagnosis. The tool data consisted of number of different parameters each being recorded at fixed time points. As the data had been collected for a number of runs, it was not synchronized due to variable delays and offsets in data acquisition system and networks. The data was then synchronized using a variant of Dynamic Time Warping (DTW) algorithm. The AutoRegressive Integrated Moving Average (ARIMA) model was then applied on the synchronized data. The ARIMA model combines both the Autoregressive model and the Moving Average model to relate the present value of the time series to its past values. As the new values of parameters are received from the equipment, the model uses them and the previous ones to provide predictions of one step ahead for each parameter. The statistical comparison of these predictions with the actual values, gives us the each parameter's probability of fault, at each time point and (once a run gets finished) for each run. This work will be extended by applying a suitable probability generating function and combining the probabilities of different parameters using Dempster-Shafer Theory (DST). DST provides a way to combine evidence that is available from different sources and gives a joint degree of belief in a hypothesis. This will give us a combined belief of fault in the process with a high precision.

• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.87-94
• /
• 2017

Many industrial accidents have occurred continuously in the manufacturing industries, construction industries, and service industries of Korea. Fatal accidents have occurred most frequently in the construction industries of Korea. Especially, the trend analysis of the accident rate and fatal accident rate is very important in order to prevent industrial accidents in the construction industries systematically. This paper considers forecasting of the accident rate and fatal accident rate with static and dynamic time series analysis methods in the construction industries. Therefore, this paper describes the optimal accident rate and fatal accident rate by minimization of the sum of square errors (SSE) among regression analysis method (RAM), exponential smoothing method (ESM), double exponential smoothing method (DESM), auto-regressive integrated moving average (ARIMA) model, proposed analytic function model (PAFM), and kalman filtering model (KFM) with existing accident data in construction industries. In this paper, microsoft foundation class (MFC) soft of Visual Studio 2008 was used to predict the accident rate and fatal accident rate. Zero Accident Program developed in this paper is defined as the predicted accident rate and fatal accident rate, the zero accident target time, and the zero accident time based on the achievement probability calculated rationally and practically. The minimum value for minimizing SSE in the construction industries was found in 0.1666 and 1.4579 in the accident rate and fatal accident rate, respectively. Accordingly, RAM and ARIMA model are ideally applied in the accident rate and fatal accident rate, respectively. Finally, the trend analysis of this paper provides decisive information in order to prevent industrial accidents in construction industries very systematically.

• 한국정보통신학회논문지
• /
• 제26권1호
• /
• pp.58-63
• /
• 2022

코로나19의 일일 확진자 수는 천명 후반대에서 2천명대를 유지하고 있으며, 백신접종률이 증가함에도 불구하고 확진자수가 쉽게 줄어들지 않는 상황이다. 변이바이러스는 계속해서 등장하고, 현재는 뮤 변이 바이러스까지 국내에 유입되었다. 본 논문은 코로나 예방전략을 위해 SARIMA 모델을 통해 코로나19 국내 확진자 수를 예측한다. ADF Test와 KPSS Test를 통해 데이터에 추세와 계절성이 있음을 확인한다. SARIMA(p,d,q)(P,D,Q,S)의 p, d, q, P, D, Q의 값은 모형 차수결정 정리로 파라미터를 추출한다. ACF와 PACF를 통해 p, q 파라미터를 추론한다. 차분, 로그변환, 계절성제거 등을 통해 데이터를 정상성 형태로 변환하고, 도식화 하여 파라미터를 도출하고, 계절성이 있다면 S를 정하고, SARIMA P,D,Q를 정하고, 계절성을 제외한 차수에 대해 ACF와 PACF를 보고 ARIMA p,d,q를 정한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.362-362
• /
• 2023

한정된 수자원의 이용 및 관리로 매년 물 부족과 물 배분 의사결정 문제가 발생하고 있다. 50년간(1965~2014년) 수자원의 총량은 약 1.2배 증가한 반면 인구수 약 1.8배, 생·공·농업용수의 수요는 약 5배가 증가(국회입법조사처, 2018) 했을 뿐 아니라, 기후변화의 영향으로 인한 강수량의 변화와 지역별 편차가 커져 지속가능한 물관리 필요성이 증대되고 있다. 따라서 효율적인 물관리를 위해서는 관리부처가 분절되어 있는 물순환 계통의 데이터를 통합하는 것이 우선시되어야 하고 이를 통해 물순환 모니터링/평가/예측 기술을 개발할 수 있다. 본 연구에서는 생활용수 물순환 계통 통합 DB를 정의 및 구축하였다. 도시의 관점에서 물순환 시스템을 순차적으로 물 유입(수원~취수장)/전달(정수장~급수지역)/유출(하(폐)수처리장~방류구)의 개념으로 설정하고 DB정의서를 마련하였다. 연구대상지는 가뭄이 장기화가 되고 있는 전라남도중 물순환 계통이 비교적 단순한 네트워크로 형성되어 있는 함평군 도시지역으로 선정하였다. 연구 기간은 총 5년(2017년 1월 1일~2021년 12월 31일)이고 일 단위 실계측자료 위주의 원자료를 구축하였다. 이를 이상치 탐지, 제거, 대체의 과정을 거쳐 품질 보정하고 정제된 시계열 자료에 대한 특성 분석을 하였다. 그 결과, 물순환 계통 내 주요 지점 간의 상관관계 및 지연시간을 통한 물흐름의 시계열적 특성을 파악할 수 있었으며 모형의 적합도를 판단하는 데 활용되는 통계량과 유의미하지 않은 잔차의 자기상관성을 볼 때 물 유입-전달-유출의 단기 예측을 위한 ARIMA(Auto-regressive Integrated Moving Average) 모형의 구축도 가능할 것으로 판단되었다. 다만 여름철 발생하는 방류량의 첨두값을 설명하기 위해서는 강우에 의한 불명수 발생으로 증가하는 방류량을 묘사할 수있어야 하므로 향후에는 물순환계통 외 해당 지역의 불명수(강우 효과)도 하수 방류량의 주요 입력 요인으로 추가 검토할 필요가 있다.

• Advances in environmental research
• /
• 제4권4호
• /
• pp.233-246
• /
• 2015

High amounts of air pollution in crowded urban areas are always considered as one of the major environmental challenges especially in developing countries. Despite the errors in air pollution prediction, the forecasting of future data helps air quality management make decisions promptly and properly. We studied the air quality of the Aqdasiyeh location in Tehran using factor analysis and the Box-Jenkins time series methods. The Air Quality Control Company (AQCC) of the Municipality of Tehran monitors seven daily air quality parameters, including carbon monoxide (CO), Nitrogen Monoxide (NO), Nitrogen dioxide ($NO_2$), $NO_x$, ozone ($O_3$), particulate matter ($PM_{10}$) and sulfur dioxide ($SO_2$). We applied the AQCC data for our study. According to the results of the factor analysis, the air quality parameters were divided into two factors. The first factor included CO, $NO_2$, NO, $NO_x$, and $O_3$, and the second was $SO_2$ and $PM_{10}$. Subsequently, the Box- Jenkins time series was applied to the two mentioned factors. The results of the statistical testing and comparison of the factor data with the predicted data indicated Auto Regressive Integrated Moving Average (0, 0, 1) was appropriate for the first factor, and ARIMA (1, 0, 1) was proper for the second one. The coefficient of determination between the factor data and the predicted data for both models were 0.98 and 0.983 which may indicate the accuracy of the models. The application of these methods could be beneficial for the reduction of developing numbers of mathematical modeling.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.152-159
• /
• 2023

This study endeavors to enrich investment prospects in cryptocurrency by establishing a rationale for investment decisions. The primary objective involves evaluating the predictability of four prominent cryptocurrencies - Bitcoin, Ethereum, Litecoin, and EOS - and scrutinizing the efficacy of trading strategies developed based on the prediction model. To identify the most effective prediction model for each cryptocurrency annually, we employed three methodologies - AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and Prophet - representing traditional statistics and artificial intelligence. These methods were applied across diverse periods and time intervals. The result suggested that Prophet trained on the previous 28 days' price history at 15-minute intervals generally yielded the highest performance. The results were validated through a random selection of 100 days (20 target dates per year) spanning from January 1st, 2018, to December 31st, 2022. The trading strategies were formulated based on the optimal-performing prediction model, grounded in the simple principle of assigning greater weight to more predictable assets. When the forecasting model indicates an upward trend, it is recommended to acquire the cryptocurrency with the investment amount determined by its performance. Experimental results consistently demonstrated that the proposed trading strategy yields higher returns compared to an equal portfolio employing a buy-and-hold strategy. The cryptocurrency trading model introduced in this paper carries two significant implications. Firstly, it facilitates the evolution of cryptocurrencies from speculative assets to investment instruments. Secondly, it plays a crucial role in advancing deep learning-based investment strategies by providing sound evidence for portfolio allocation. This addresses the black box issue, a notable weakness in deep learning, offering increased transparency to the model.

• 한국환경과학회지
• /
• 제15권8호
• /
• pp.701-718
• /
• 2006

The average ratio of the daily UV-B to total solar (75) irradiance at Busan (35.23$^{\circ}$N, 129.07$^{\circ}$E) in Korea is found as 0.11%. There is also a high exponential relationship between hourly UV-B and total solar irradiance: UV-B=exp (a$\times$(75-b))(R$^2$=0.93). The daily variation of total ozone is compared with the UV-B irradiance at Pohang (36.03$^{\circ}$N, 129.40$^{\circ}$E) in Korea using the Total Ozone Mapping Spectrometer (TOMS) data during the period of May to July in 2005. The total ozone (TO) has been maintained to a decreasing trend since 1979, which leading to a negative correlation with the ground-level UV-B irradiance doting the given period of cloudless day: UV-B=239.23-0.056 TO (R$^2$=0.52). The statistical predictions of daily total ozone are analyzed by using the data of the Brewer spectrophotometer and TOMS in East Asia including the Korean peninsula. The long-term monthly averages of total ozone using the multiplicative seasonal AutoRegressive Integrated Moving Average (ARIMA) model are used to predict the hourly mean UV-B irradiance by interpolating the daily mean total ozone far the predicting period. We also can predict the next day's total ozone by using regression models based on the present day's total ozone by TOMS and the next day's predicted maximum air temperature by the Meteorological Mesoscale Model 5 (MM5). These predicted and observed total ozone amounts are used to input data of the parameterization model (PM) of hourly UV-B irradiance. The PM of UV-B irradiance is based on the main parameters such as cloudiness, solar zenith angle, total ozone, opacity of aerosols, altitude, and surface albedo. The input data for the model requires daily total ozone, hourly amount and type of cloud, visibility and air pressure. To simplify cloud effects in the model, the constant cloud transmittance are used. For example, the correlation coefficient of the PM using these cloud transmissivities is shown high in more than 0.91 for cloudy days in Busan, and the relative mean bias error (RMBE) and the relative root mean square error (RRMSE) are less than 21% and 27%, respectively. In this study, the daily variations of calculated and predicted UV-B irradiance are presented in high correlation coefficients of more than 0.86 at each monitoring site of the Korean peninsula as well as East Asia. The RMBE is within 10% of the mean measured hourly irradiance, and the RRMSE is within 15% for hourly irradiance, respectively. Although errors are present in cloud amounts and total ozone, the results are still acceptable.