• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.170-174
• /
• 2004

Despite the widespread use in the various manufacturing industries, the full automation of the robotic CO$_2$ welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an Radial basis function network model to predict the weld top-bead width as a function of key process parameters in the robotic CO$_2$ welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to verify performance. of the developed model.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.4
• /
• pp.274-283
• /
• 2005

Coronary Perfusion Pressure(CPP) is known for the most important parameter related to the Return of Spontaneous Circulation (ROSC), however, clinically measuring CPP is difficult either invasive or non-invaisive method. En this paper, we analyze the correlation between the extracted parameter from VF ECG wave and the CPP with the statistical method, and predict CPP value using the extracted parameters within significance level. the extracted parameters are median frequency(MF), peak frequency(PF), average segment amplitude(ASA), MSA(maximum segment amplitude), Two parameters, MF, and ASA are selected in order to predict CPP value with general regression neural network, and then we evaluated the agreement statistics between the simulated CPP and the measured CPP. In conclusion, the mean and variance of the difference between the simulated CPP and the measured CPP are 8.9716±1.3526 mmHg, and standard deviation 6.4815 mmHg with one hundred-times training and test results. the simulated CPP and the measured CPP are agreed with the overall accuracy $90.68\%$ and kappa coefficient $81.14\%$ as a discriminant parameter of ROSC.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.1
• /
• pp.61.1-61.1
• /
• 2013

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.66-70
• /
• 2005

The full automation of welding has not yet been achieved partly because the mathematical model for the process parameters of a given welding task is not fully understood and quantified. Several mathematical models to control welding quality, productivity, microstructure and weld properties in arc welding processes have been studied. However, it is not an easy task to apply them to the various practical situations because the relationship between the process parameters and the bead geometry is non-linear and also they are usually dependent on the specific experimental results. Practically, it is difficult, but important to know how to establish a mathematical model that can predict the result of the actual welding process and how to select the optimum welding condition under a certain constraint. In this paper, an attempt has been made to develop an neural network model to predict the weld top-bead height as a function of key process parameters in the welding. and to compare the developed model and a simple neural network model using two different training algorithms in order to select an optimal neural network model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.120-125
• /
• 2020

Supply chain managers seek to achieve global optimization by solving problems in the supply chain's business process. However, companies in the supply chain hide the adverse information and inform only the beneficial information, so the information is distorted and cannot be the information that describes the entire supply chain. In this case, supply chain managers can directly collect and analyze supply chain activity data to find and manage the companies described by the data. Therefore, this study proposes a method to collect the order-inventory information from each company in the supply chain and detect the companies whose data characteristics are explained through deep learning. The supply chain consists of Manufacturer, Distributor, Wholesaler, Retailer, and training and testing data uses 600 weeks of time series inventory information. The purpose of the experiment is to improve the detection accuracy by adjusting the parameter values of the deep learning network, and the parameters for comparison are set by learning rate (lr = 0.001, 0.01, 0.1) and batch size (bs = 1, 5). Experimental results show that the detection accuracy is improved by adjusting the values of the parameters, but the values of the parameters depend on data and model characteristics.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.1958-1960
• /
• 2001

In this paper, we propose the design methodology of target tracking system using the identification of TS fuzzy model based on genetic algorithm(GA) and RLS algorithm. In general, the objective of target tracking is to estimate the future trajectory of the target based on the past position of the target obtained from the sensor. In the conventional and mathematical nonlinear filtering method such as extended Kalman filter(EKF), the performance of the system may be deteriorated in highly nonlinear situation. In this paper, to resolve these problems of nonlinear filtering technique, the error of EKF by nonlinearity is compensated by identifying TS fuzzy model. In the proposed method, after composing training datum from the parameters of EKF, by identifying the premise and consequent parameters and the rule numbers of TS fuzzy model using GA, and by tuning finely the consequent parameters of TS fuzzy model using recursive least square(RLS) algorithm, the error of EKF is compensated. Finally, the proposed method is applied to three dimensional tracking problem, and the simulation results shows that the tracking performance is improved by the proposed method.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2005.05a
• /
• pp.241-244
• /
• 2005

Though the history of finite element analysis in field of powder metallurgy is not short, industrial engineer is still being dependent on the trial and error approach based on engineer's experience in selecting process conditions. This problem is mainly due to the difficulty in establishing models for the behavior of a powder compact during compaction and sintering as well as finding material parameters for the models and the absence of CAE software with which industrial engineer can easily investigate the effect of process conditions on the quality of product. Therefore, we established very simple and cheap procedure to find material parameters for powder compaction behavior and implemented it in self-developed commercial CAE software for powder metallurgy, PMsolver. Basically, the development strategy of PMsolver lies on simplification and convenience so as for industrial engineers to use it with least training. Using PMsolver, optimal process conditions were found for some geometry and powders. Prior to process condition design, the accuracy of finite element analysis was verified.

• Transactions of Materials Processing
• /
• v.24 no.3
• /
• pp.167-175
• /
• 2015

In the current study, the design methodology has been developed to produce shoe mold for a suitable walking shoes of the general Korean using ANN (Artificial Neural Network). To design the suitable and comfortable shoes for the Korean, the shapes of foots were measured for 513 people. In this research, the foot length, breadth and ankle were considered as design parameters. In order to find the optimal foot shape for the average value of design parameters, the average value of design parameters and the other measurements were used as input and output to the ANN. After training, the various foot measurements were predicted by ANN. Base on the ANN results, the walking shoes were manufactured by considering these measurements and designing a shoe mold. From the results, the proposed method could give a more systematic and feasible means for manufacturing walking shoes with greater usefulness and better generality.

• Journal of Powder Materials
• /
• v.26 no.5
• /
• pp.369-374
• /
• 2019

The properties of powder metallurgy products are related to their densities. In the present work, we demonstrate a method to apply artificial neural networks (ANNs) trained on experimental data to predict the bulk density of barium titanates. The density is modeled as a function of pressure, press rate, heating rate, sintering temperature, and soaking time using the ANN method. The model predictions with the training and testing data result in a high coefficient of correlation (R2 = 0.95 and Pearson's r = 0.97) and low average error. Moreover, a graphical user interface for the model is developed on the basis of the transformed weights of the optimally trained model. It facilitates the prediction of an infinite combination of process parameters with reasonable accuracy. Sensitivity analysis performed on the ANN model aids the identification of the impact of process parameters on the density of barium titanates.

• Computers and Concrete
• /
• v.27 no.4
• /
• pp.305-317
• /
• 2021

The bond between the concrete and bar is a main factor affecting the performance of the reinforced concrete (RC) members, and since the steel corrosion reduces the bond strength, studying the bond behavior of concrete and GFRP bars is quite necessary. In this research, a database including 112 concrete beam test specimens reinforced with spliced GFRP bars in the splitting failure mode has been collected and used to estimate the concrete-GFRP bar bond strength. This paper aims to accurately estimate the bond strength of spliced GFRP bars in concrete beams by applying three soft computing models including multivariate adaptive regression spline (MARS), Kriging, and M5 model tree. Since the selection of regularization parameters greatly affects the fitting of MARS, Kriging, and M5 models, the regularization parameters have been so optimized as to maximize the training data convergence coefficient. Three hybrid model coupling soft computing methods and genetic algorithm is proposed to automatically perform the trial and error process for finding appropriate modeling regularization parameters. Results have shown that proposed models have significantly increased the prediction accuracy compared to previous models. The proposed MARS, Kriging, and M5 models have improved the convergence coefficient by about 65, 63 and 49%, respectively, compared to the best previous model.