• Computers and Concrete
• /
• v.10 no.6
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• Journal of the Korean Society for Railway
• /
• v.10 no.6
• /
• pp.772-778
• /
• 2007

For the wear characteristics assessment of Saemaul train passing through curves, an analysis model for multi-car system has been developed. By using this model and ADAMS/Rail, sensitivity analyses have been conducted for the wear characteristics by changing the related parameters. At low speed, the wear number and the sliding mean of right wheel showed higher than left wheel, while those of left wheel showed higher than right wheel at high speed. According to the decrease of curve radius, the wear number and the sliding mean were increased. When the length of transition curve was increased, the wear number and the sliding mean was increased. And according to increase of cant, the wear number and the sliding mean were increased.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.1
• /
• pp.95-104
• /
• 2012

Although the educational institutions of computers have evolved to train students in pace with the changes of computing, many students still believe that computer programming is hard to be mastered. The reluctance of students toward programming languages have been tied to the decrease of computer-related majors and now many countries are in short of computer programmers. By investigating the similarities among eleven popular programming languages, this research is intended to measure the relative distances and understand the dimensions that scattered the languages.

• Design & Manufacturing
• /
• v.1 no.1
• /
• pp.1-5
• /
• 2007

Double injection molding process is very efficient molding-method for molding the products which is consist of multi-materials. Fuel-tube holder which is necessary for automobil power train and circulation systems is composed of plastic and rubber materials to minimize the vibration and pulsation noises. In existing process, fuel-tube holder was made by the insert molding process or assembly process after molding. If fuel-tube holder is manufactured by double injection molding process, it may be realize to improve the product quality, efficiency of molding-process and retrenchment of manufacturing cost. In this study, for manufacturing fuel-tube holder by double injection molding process, the analysis of joining characteristics between PA6(polyamide 6) and TPE(thermoplastic elastomer) was executed and the double injectin mold for molding fuel-tube holder with core toggle mechanism was fabricated. Finally, fuel-tube holder was molding using fabricated double injection mold.

• Earthquakes and Structures
• /
• v.15 no.4
• /
• pp.431-441
• /
• 2018

This study provides fragility-based assessment of seismic performance of reinforced concrete bridges. Seismic fragility curves were created using nonlinear analysis (NA) and artificial neural networks (ANNs). Nonlinear response history analyses were performed, in order to calculate the seismic performances of the bridges. To this end, 306 bridge-earthquake cases were considered. A multi-layered perceptron (MLP) neural network was implemented to predict the seismic performances of the selected bridges. The MLP neural networks considered herein consist of an input layer with four input vectors; two hidden layers and an output vector. In order to train ANNs, 70% of the numerical results were selected, and the remained 30% were employed for testing the reliability and validation of ANNs. Several structures of MLP neural networks were examined in order to obtain suitable neural networks. After achieving the most proper structure of neural network, it was used for generating new data. A total number of 600 new bridge-earthquake cases were generated based on neural simulation. Finally, probabilistic seismic safety analyses were conducted. Herein, fragility curves were developed using numerical results, neural predictions and the combination of numerical and neural data. Results of this study revealed that ANNs are suitable tools for predicting seismic performances of RC bridges. It was also shown that yield stresses of the reinforcements is one of the important sources of uncertainty in fragility analysis of RC bridges.

• Journal of Korean Society for Atmospheric Environment
• /
• v.10 no.4
• /
• pp.224-232
• /
• 1994

A new neural network model has been developed to predict short-term air pollution concentration. In addition, a multiple regression model widely used in statistical analysis was tested. These models were applied for prediction of daily maximum ozone concentration in Seoul during the summer season of 1991. The time periods between May and September 1989 and 1990 were utilized to train set of learning patterns in neural network model, and to estimate multiple regression model. To evaluate the results of the different models, several Performance indices were used. The results indicated that the multiple regression model tended to underpredict the daily maximum ozone concentration with small r$^{2}$(0.38). Also, large errors were found in this model; 21.1 ppb for RMSE, 0.324 for NMSE, and -0.164 for MRE. On the other hand, the results obtained from the neural network model were very promising. Thus, we can know that this model has a prominent efficiency in the adaptive control for the non-linear multi- variable systems such as photochemical oxidants. Also, when the recent new information was added in the neural network model, prediction accuracy was increased. From the new model, the values of RMSE, NMSE and r$^{2}$ were 13.2ppb, 0.089, 0.003 and 0.55 respectively.

• Transactions of Materials Processing
• /
• v.19 no.7
• /
• pp.411-415
• /
• 2010

A sandwich panel which is comprised of truss cores faced with solid face sheets is lightweight and multi-functional. So it is widely used to not only structural material but also heat transfer media in transportation field such as airplane, train and vessel. There are various core topologies such as pyramidal and tetrahedral truss, square honeycombs and kagome truss. The study focused on analytical approach to optimize compression and shear quality of the unit cell of PCM with pyramidal configuration. With various unit cell models which have the same core weight per unit area but different truss member angle, analytical solution for effective stress ($\bar{\sigma},\bar{\tau}$), peak stress ($\bar{\sigma}_{peak},\bar{\tau}_{peak}$) by yielding and buckling, relative density ($\bar{\rho}_c$) and effective stiffness ($\bar{E},\bar{G}$) have been computed and compared each other. With this approach, the most optimal core configuration was predicted. The result has become the efficient guidelines for the design of PCM core structure.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.1086-1092
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of a given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a mega model that has a regression model made by sampling data through simulation. In this paper, the neural network is used a mega model that have twenty-nine design variables and forty-six responses. After this mega model is constructed, multi-objective optimal solutions are achieved by using the differential evolution. This paper shows that this optimization method using the neural network and the differential evolution is a very efficient tool to solve the complex optimization problem.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.2
• /
• pp.177-185
• /
• 2001

This study shows the process design and forming analysis of permalloy shielding can that support the automobile multi-display parts to indicate the accurate information of car. This study is particularly important, since the strain and thickness of permalloy shielding can is known to affect the magnetic properties such as coercivity and permeability quite thickness of permalloy shielding can is known to affect the magnetic properties such as coercivity and permeability quite sensitively. The objective functions are strain and thickness deviation. The punch radius, die radius and blank holding force are considered as design parameters. Orthogonal array (OA) table and characteristics are applied to neural network (NN) as train data. After training, the optimal and robust condition of design parameters is selected. This study shows the correlation between the design methodology of NN and the statistical design of experiments (DOE) approach.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.761-772
• /
• 2009

The introduction of KTX (Korea Train eXpress) provided passengers with a much faster mode of transport, and KTX has become a model railway system. Express railway stations are emphasized as public transit transfer centers, but their service evaluations were not performed appropriately so far. It is possible to know the level of service by developing valuation criteria for their evaluations. The evaluation of transfer centers mainly consists of two parts; connective service with other travel m odes, and transfer service inside transfer stations. Connection is defined as the inter-connection of multi-transportation vehicles, and transfer means that a passenger changes his travel mode to another. Such connective service and transfer service are evaluated by the level of service in terms of transfer facilities, the appropriateness of station layout and the quality of information throughout the facilities. We developed the service evaluation indicators of connective facilities and referred to the indicators of transfer facilities. We examined the 7 stations in Korea that are currently in operation and standardized the methodology of the evaluation process by applying the indicators suggested in this study.