• Smart Structures and Systems
• /
• v.14 no.6
• /
• pp.1081-1103
• /
• 2014

Real-time hybrid simulation (RTHS) has emerged as an important tool for testing large and complex structures with a focus on rate-dependent specimen behavior. Due to the real-time constraints, accurate dynamic control of servo-hydraulic actuators is required. These actuators are necessary to realize the desired displacements of the specimen, however they introduce unwanted dynamics into the RTHS loop. Model-based actuator control strategies are based on linearized models of the servo-hydraulic system, where the controller is taken as the model inverse to effectively cancel out the servo-hydraulic dynamics (i.e., model-based feedforward control). An accurate model of a servo-hydraulic system generally contains more poles than zeros, leading to an improper inverse (i.e., more zeros than poles). Rather than introduce additional poles to create a proper inverse controller, the higher order derivatives necessary for implementing the improper inverse can be calculated from available information. The backward-difference method is proposed as an alternative to discretize an improper continuous time model for use as a feedforward controller in RTHS. This method is flexible in that derivatives of any order can be explicitly calculated such that controllers can be developed for models of any order. Using model-based feedforward control with the backward-difference method, accurate actuator control and stable RTHS are demonstrated using a nine-story steel building model implemented with an MR damper.

• The KIPS Transactions:PartA
• /
• v.11A no.4
• /
• pp.243-250
• /
• 2004

Monitoring is used to see if a real-time system provides a service on time. Generally, monitoring for real-time focuses on investigating the current status of a real-time system. To support a stable performance of a real-time system, it should have not only a function to see the current status of real-time process but also a function to predict executions of real-time processes, however. The legacy prediction model has some limitation to apply it to a real-time monitoring. First, it performs a static prediction after a real-time process finished. Second, it needs a statistical pre-analysis before a prediction. Third, transition probability and data about clustering is not based on the current data. We propose the execution prediction model based on learning algorithm to solve these problems and apply it to real-time monitoring. This model gets rid of unnecessary pre-processing and supports a precise prediction based on current data. In addition, this supports multi-level prediction by a trend analysis of past execution data. Most of all, We designed the model to support dynamic prediction which is performed within a real-time process' execution. The results from some experiments show that the judgment accuracy is greater than 80% if the size of a training set is set to over 10, and, in the case of the multi-level prediction, that the prediction difference of the multi-level prediction is minimized if the number of execution is bigger than the size of a training set. The execution prediction model proposed in this model has some limitation that the model used the most simplest learning algorithm and that it didn't consider the multi-regional space model managing CPU, memory and I/O data. The execution prediction model based on a learning algorithm proposed in this paper is used in some areas related to real-time monitoring and control.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.274-283
• /
• 2022

Korea is facing a number difficulties arising from rising housing prices. As 'housing' takes the lion's share in personal assets, many difficulties are expected to arise from fluctuating housing prices. The purpose of this study is creating housing price prediction model to prevent such risks and induce reasonable real estate purchases. This study made many attempts for understanding real estate instability and creating appropriate housing price prediction model. This study predicted and validated housing prices by using the LSTM technique - a type of Artificial Intelligence deep learning technology. LSTM is a network in which cell state and hidden state are recursively calculated in a structure which added cell state, which is conveyor belt role, to the existing RNN's hidden state. The real sale prices of apartments in autonomous districts ranging from January 2006 to December 2019 were collected through the Ministry of Land, Infrastructure, and Transport's real sale price open system and basic apartment and commercial district information were collected through the Public Data Portal and the Seoul Metropolitan City Data. The collected real sale price data were scaled based on monthly average sale price and a total of 168 data were organized by preprocessing respective data based on address. In order to predict prices, the LSTM implementation process was conducted by setting training period as 29 months (April 2015 to August 2017), validation period as 13 months (September 2017 to September 2018), and test period as 13 months (December 2018 to December 2019) according to time series data set. As a result of this study for predicting 'prices', there have been the following results. Firstly, this study obtained 76 percent of prediction similarity. We tried to design a prediction model of real estate transaction price with the LSTM Model based on AI and Bigdata. The final prediction model was created by collecting time series data, which identified the fact that 76 percent model can be made. This validated that predicting rate of return through the LSTM method can gain reliability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.20-25
• /
• 2021

The target-object classification method was implemented using a deep-learning-based detection model in real-time images. The object detection model was a deep-learning-based detection model that allowed extensive data collection and machine learning processes to classify similar target-objects. The recognition model was implemented by changing the processing structure of the detection model and combining developed the vision-processing module. To classify the target-objects, the identity and similarity were defined and applied to the detection model. The use of the recognition model in industry was also considered by verifying the effectiveness of the recognition model using the real-time images of an actual soccer game. The detection model and the newly constructed recognition model were compared and verified using real-time images. Furthermore, research was conducted to optimize the recognition model in a real-time environment.

• Transactions of the Korean hydrogen and new energy society
• /
• v.26 no.2
• /
• pp.184-191
• /
• 2015

As the power electronics system increases the frequency, the power loss and thermal management are paid more attention. This research presents a real time model of dissipation power with junction temperature response for 120kw IGBT inverter which is applied to the thermal management of high power IGBT inverter. Since the computational time is critical for real time simulation, look-up tables of IGBT module characteristic curve are implemented. The power loss from IGBT provides a clue to calculate the temperature of each module of IGBT. In this study, temperature of each layer in IGBT is predicted by lumped capacitance analysis of layers with convective heat transfer. The power loss and temperature of layers in IGBT is then communicated due to mutual dependence. In the dynamic model, PWM pulses are employed to calculation real time IGBT and diode power loss. Under Matlab/Simulink$^{(R)}$ environment, the dynamic model is validated with experiment. Results showed that the dynamic response of power loss is closely coupled with effective thermal management. The convective heat transfer is enough to achieve proper thermal management under guideline temperature.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.150-150
• /
• 2018

The Numerical Weather Prediction (NWP) models provide information for weather forecasts. The highly nonlinear and complex interactions in the atmosphere are simplified in meteorological models through approximations and parameterization. Therefore, the simplifications may lead to biases and errors in model results. Although the models have improved over time, the biased outputs of these models are still a matter of concern in meteorological and hydrological studies. Thus, bias removal is an essential step prior to using outputs of atmospheric models. The main idea of statistical bias correction methods is to develop a statistical relationship between modeled and observed variables over the same historical period. The Model Output Statistics (MOS) would be desirable to better match the real time forecast data with observation records. Statistical post-processing methods relate model outputs to the observed values at the sites of interest. In this study three methods are used to remove the possible biases of the real-time outputs of the Weather Research and Forecast (WRF) model in Imjin basin (North and South Korea). The post-processing techniques include the Linear Regression (LR), Linear Scaling (LS) and Power Scaling (PS) methods. The MOS techniques used in this study include three main steps: preprocessing of the historical data in training set, development of the equations, and application of the equations for the validation set. The expected results show the accuracy improvement of the real-time forecast data before and after bias correction. The comparison of the different methods will clarify the best method for the purpose of the forecast skill enhancement in a real-time case study.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.91-98
• /
• 2016

We propose a method to train a model that can predict the probability of a crime being committed. CCTV data by matching criminal events are required to train the crime prediction model. However, collecting CCTV data appropriate for training is difficult. Thus, we collected actual criminal records and converted them to an appropriate format using variables by considering a crime prediction environment and the availability of real-time data collection from CCTV. In addition, we identified new specific crime types according to the characteristics of criminal events and trained and tested the prediction model by applying neural network partial least squares for each crime type. Results show a level of predictive accuracy sufficiently significant to demonstrate the applicability of CCTV to real-time crime prediction.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.1
• /
• pp.13-25
• /
• 2000

A simulation model is developed to analyze the large-structure driving system and its integrated behavior in the whole weapon system. It models every component in the driving system such as mechanical and electrical characteristics, and it is programmed by simulation language in a way which strongly reflects the system's real time dynamics and reduces computation time as well. A useful parameter identification method is proposed, and it is tuned on the given physical system. The model is validated through comparing to real test, and it is applied to analysis and prediction of integrated system functions relating to the fire control system.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.3
• /
• pp.141-147
• /
• 2005

In the field of electrical industry, embedded computing environment including hardware and software is getting more important as the industry shifts to the knowledge-based one. Java could play a great role as bridging technology in such a transition because it provides a lot of benefits like dynamic application download, compatibility of cross platform, and its own security solution. However, the Java technology has a limitation of real-time problem when it is applied to the embedded computing system of the electrical industry. To solve the problem, a novel java-native combination model has been proposed and designed to a firmware level. This scheme has been employed in four kinds of control boards. The result shows that the proposed model has great potential to implement the real-time processing in control of the devices.

• Journal of Information Processing Systems
• /
• v.7 no.1
• /
• pp.1-16
• /
• 2011

With the increasing number of vehicles in use in our daily life and the rise of traffic congestion problems, many methods and models have been developed for real time optimisation of traffic lights. Nevertheless, most methods which consider real time physical queue sizes of vehicles waiting for green lights overestimate the optimal cycle length for such real traffic control. This paper deals with the development of a generic hybrid model describing both physical traffic flows and control of signalised intersections. The firing times assigned to the transitions of the control part are considered dynamic and are calculated by a simplified optimisation method. This method is based on splitting green times proportionally to the predicted queue sizes through input links for each new cycle time. The proposed model can be easily translated into a control code for implementation in a real time control system.