• Journal of the Korean Institute of Gas
• /
• v.16 no.1
• /
• pp.33-38
• /
• 2012

Analysis on gas accidents by types occurred has been made to prevent the recurrence of accidents, through analysis of past history of gas accident occurring environment. The number of gas accidents has been decreasing, but still accidents are occurring steadily. Gas-using environment and gas accidents are estimated to be closely connected since gas-using types are changing by time period, weather, etc. in terms of accident contents. As a result of analysing gas accidents by 7 meteorological elements, such as the mean temperature, the highest temperature, the lowest temperature, relative humidity, the amount of clouds, precipitation and wind velocity, it has been found out that gas accidents are influenced by temperature or relative humidity, and accident occurs more frequently when the sky is clean and wind velocity is slow. Possibility of gas accidents can be provided in real time, using the proposed model made to predict gas accidents in connection with the weather forecast service. Possibility and number of gas accidents will be checked real time by connecting to the business system of Korea Gas Safety Corp., and it is considered that it would be positively used for preventing gas accidents.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.10
• /
• pp.1-7
• /
• 2009

Nowadays there are many studies and there's huge development about RFID and WSN which have great developmental potential to many kinds of applications. In particular, the healthcare field is expected to could be securing international competitive power in u-Healthcare and combined medical treatment industry and service. More and more real time application apply RFID and WSN technology to identify, data collect and locate objects. Wide deployment of RFID and WSN will generate an unprecedented volume of primitive data in a short time. Duplication and redundancy of primitive data will affect real time performance of application. Thus, emerging applications must filter primitive data and correlate them for complex pattern detection and transform them to events that provide meaningful, actionable information to end application. In this paper, we design a complex event processing system. This system will process RFID and WSN primitive data and event and perform data transformation. Integrate RFID and WSN system had applied each now in medical treatment through this study and efficient data transmission and management forecast that is possible.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.648-658
• /
• 2018

Regarding the fact that wind power forecast accuracy is gradually improved as time is approaching, this paper proposes a two-stage rolling dispatch approach based on model predictive control (MPC), which contains an intra-day rolling optimal scheme and a real-time rolling base point tracing scheme. The scheduled output of the intra-day rolling scheme is set as the reference output, and the real-time rolling scheme is based on MPC which includes the leading rolling optimization and lagging feedback correction strategy. On the basis of the latest measured thermal unit output feedback, the closed-loop optimization is formed to correct the power deviation timely, making the unit output smoother, thus reducing the costs of power adjustment and promoting wind power accommodation. We adopt chance constraint to describe forecasts uncertainty. Then for reflecting the increasing prediction precision as well as the power dispatcher's rising expected satisfaction degree with reliable system operation, we set the confidence level of reserve constraints at different timescales as the incremental vector. The expectation of up/down reserve shortage is proposed to assess the adequacy of the upward/downward reserve. The studies executed on the modified IEEE RTS system demonstrate the effectiveness of the proposed approach.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6B
• /
• pp.743-750
• /
• 2008

Due to unusual climate change and global warming, drought and flood happen frequently not only in Korea but also in all over the world. It leads to the serious damages and injuries in urban areas as well as rural areas. Since the concentration time is short and the flood flows increase urgently in urban stream basin, the chances of damages become large once heavy storm occurs. A decision support system for flood forecasting and warning in urban stream is developed as an alternative to alleviate the damages from heavy storm. It consists of model base management system based on ANFIS (Adaptive Neuro Fuzzy Inference System), database management system with real time data building capability and user friendly dialog generation and management system. Applying the system to the Tanceon river basin, it can forecast and warn the stream flows from the heavy storm in real time and alleviate the damages.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2002.05a
• /
• pp.43-50
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict streamflow and flash floods. Previously, neural networks were used to develop a Quantitative Precipitation Forecasting (QPF) model that highly improved forecasting skill at specific locations in Pennsylvania, using both Numerical Weather Prediction (NWP) output and rainfall and radiosonde data. The objective of this study was to improve an existing artificial neural network model and incorporate the evolving structure and frequency of intense weather systems in the mid-Atlantic region of the United States for improved flood forecasting. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as life time, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships between weather system, rainfall production and streamflow response in the study area. The new Quantitative Flood Forecasting (QFF) model was applied to predict streamflow peaks with lead-times of 18 and 24 hours over a five year period in 4 watersheds on the leeward side of the Appalachian mountains in the mid-Atlantic region. Threat scores consistently above .6 and close to 0.8 ∼ 0.9 were obtained fur 18 hour lead-time forecasts, and skill scores of at least 4％ and up to 6％ were attained for the 24 hour lead-time forecasts. This work demonstrates that multisensor data cast into an expert information system such as neural networks, if built upon scientific understanding of regional hydrometeorology, can lead to significant gains in the forecast skill of extreme rainfall and associated floods. In particular, this study validates our hypothesis that accurate and extended flood forecast lead-times can be attained by taking into consideration the synoptic evolution of atmospheric conditions extracted from the analysis of large-area remotely sensed imagery While physically-based numerical weather prediction and river routing models cannot accurately depict complex natural non-linear processes, and thus have difficulty in simulating extreme events such as heavy rainfall and floods, data-driven approaches should be viewed as a strong alternative in operational hydrology. This is especially more pertinent at a time when the diversity of sensors in satellites and ground-based operational weather monitoring systems provide large volumes of data on a real-time basis.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.3
• /
• pp.144-151
• /
• 2005

This paper presents a forecasting technique of the short-term marginal price (SMP) using an Artificial Neural Network (ANN). The SW forecasting is a very important element in an electricity market for the optimal biddings of market participants as well as for market stabilization of regulatory bodies. Input data are organized in two different approaches, time-axis and day-axis approaches, and the resulting patterns are used to train the ANN. Performances of the two approaches are compared and the better estimate is selected by a composition rule to forecast the SMP. By combining the two approaches, the proposed composition technique reflects the characteristics of hourly, daily and seasonal variations, as well as the condition of sudden changes in the spot market, and thus improves the accuracy of forecasting. The proposed method is applied to the historical real-world data from the Korea Power Exchange (KPX) to verify the effectiveness of the technique.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.10
• /
• pp.126-133
• /
• 2007

This paper proposes information technology based data mining to forecast short term power demand. A time-series analyses have been applied to power demand forecasting, but this method needs not only heavy computational calculation but also large amount of coefficient data. Therefore, it is hard to analyze data in fast way. To overcome time consuming process, the author take advantage of universally easily available information technology based data-mining technique to analyze patterns of days and special days(holidays, etc.). This technique consists of two steps, one is constructing decision tree, the other is estimating and forecasting power flow using decision tree analysis. To validate the efficiency, the author compares the estimated demand with real demand from the Korea Power Exchange.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.59-67
• /
• 2006

This paper proposes a forecasting method for court auction information system using exponential smoothing. The system forecast a highest bid price for claim analysis, and it is designed to offer an quota information by the bid price. For this realization, we implemented input interface of object data and web interface of information support. Input interface can be input, update and delete function and web interface is support some information of court auction object. We propose a forecasting method using exponential smoothing of a highest bid price for auto-claim analysis with real time information support and the results are verified the feasibility of the proposed method by experiment.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.3
• /
• pp.61-67
• /
• 2020

The fourth industrial revolution encourages manufacturing industry to pursue a new paradigm shift to meet customers' diverse demands by managing the production process efficiently. However, it is not easy to manage efficiently a variety of tasks of all the processes including materials management, production management, process control, sales management, and inventory management. Especially, to set up an efficient production schedule and maintain appropriate inventory is crucial for tailored response to customers' needs. This paper deals with the optimized inventory policy in a steel company that produces granule products under supply contracts of three targeted on-time delivery rates. For efficient inventory management, products are classified into three groups A, B and C, and three differentiated production cycles and safety factors are assumed for the targeted on-time delivery rates of the groups. To derive the optimized inventory policy, we experimented eight cases of combined safety stock and data analysis methods in terms of key performance metrics such as mean inventory level and sold-out rate. Through simulation experiments based on real data we find that the proposed optimized inventory policy reduces inventory level by about 9%, and increases surplus production capacity rate, which is usually used for the production of products in Group C, from 43.4% to 46.3%, compared with the existing inventory policy.