• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.5
• /
• pp.447-454
• /
• 2015

Design and application of hardware-in-the-loop simulation (HILS) for design of CNC-controlled machine tool feed drives is discussed. The CNC machine tool is a complex mechatronics system where the complexity results from the software-based controller composed of a variety of functionalities and advanced control algorithms. Therefore, using a real CNC controller in the control simulation has merits considering the efforts and accuracy of the simulation modeling. In this paper challenges in HILS for a CNC controlled feed drive, such as minimization of time delay and transmission error that are caused by discretization of the feed drive model, is elaborated. Using an experimental HILS setup of a machine tool feed drive applications in controller gain selection and CNC diagnostics are presented.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.781-784
• /
• 2005

The feed drive inclination significantly influences product quality, machine tool accuracy and life time. However, the accurate measurement of the inclination needs the skilled engineers and the accurate leveling instruments such as spirits or electric levels. In this study a novel methodology for the estimation of inclination angle of machine tool feed drive is proposed. The proposed methodology utilizes the motor current signals and a new mathematical model of machine tool feed drive considering inclination. The experiment results showed that the proposed method successfully estimates the inclination angle, as well as newly proposed model also enhances the accuracy of the machine tool feed drive model by introducing the inclination effects.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.364-373
• /
• 2022

Image morphing methods make seamless transition changes in the image and mask the meaningful information attached to it. This can be detected by traditional machine learning algorithms and new emerging deep learning algorithms. In this research work, scope of different Hybrid learning approaches having combination of Deep learning and Machine learning are being analyzed with the public dataset CASIA V1.0, CASIA V2.0 and DVMM to find the most efficient algorithm. The simulated results with CNN (Convolution Neural Network), Hybrid approach of CNN along with SVM (Support Vector Machine) and Hybrid approach of CNN along with Random Forest algorithm produced 96.92 %, 95.98 and 99.18 % accuracy respectively with the CASIA V2.0 dataset having 9555 images. The accuracy pattern of applied algorithms changes with CASIA V1.0 data and DVMM data having 1721 and 1845 set of images presenting minimal accuracy with Hybrid approach of CNN and Random Forest algorithm. It is confirmed that the choice of best algorithm to find image forgery depends on input data type. This paper presents the combination of best suited algorithm to detect image morphing with different input datasets.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.15 no.5
• /
• pp.437-444
• /
• 2015

In simulation-based circuit optimization, many simulation runs may be wasted while evaluating infeasible designs, i.e. the designs that do not meet the constraints. To avoid such a waste, this paper investigates the use of support vector machine (SVM) classifiers in predicting the design's feasibility prior to simulation and the optimal selection of the SVM parameters, namely, the Gaussian kernel shape parameter ${\gamma}$ and the misclassification penalty parameter C. These parameters affect the complexity as well as the accuracy of the model that SVM represents. For instance, the higher ${\gamma}$ is good for detailed modeling and the higher C is good for rejecting noise in the training set. However, our empirical study shows that a low ${\gamma}$ value is preferable due to the high spatial correlation among the circuit design candidates while C has negligible impacts due to the smooth and clean constraint boundaries of most circuit designs. The experimental results with an LC-tank oscillator example show that an optimal selection of these parameters can improve the prediction accuracy from 80 to 98% and model complexity by $10{\times}$.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.10a
• /
• pp.13-18
• /
• 1998

The assessment of machined surface is difficult because the freeform surface must be evaluated by surface fairness as well as dimensional accuracy. In this paper, the methodology of freeform surface generation using measured data on the machine tool is presented. The reliability of measured points data is obtained by measuring error compensation. The compensated data are formulated through Non-uniform G-spline surface modeling. In order to improve the surface fairness, the generated model si smoothened by parameterization The validity and usefulness of the proposed method are examined through computer simulation and experiments on the machine tool.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.4 s.175
• /
• pp.937-945
• /
• 2000

The assessment of machined surface is difficult because the freeform surface must be evaluated by surface fairness as well as dimensional accuracy. In this study, the machined freeform surface is modeled by interpolating the data measured on the machine tool into the mathematical continuous surface, and then the surface model is improved with the parameterization to minimize surface fairness. The accuracy reliability of the measured data is confirmed through compensation of volumetric errors of the machine tool and of probing errors. Non-uniform B-spline surface interpolation method is adopted to guarantee the continuity of surface model. Surface fairness is evaluated with the consideration of normal curvature on the interpolated surface. The validity and usefulness of the proposed method is examined through computer simulation and experiment on the machine tool.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1991.11a
• /
• pp.116-120
• /
• 1991

Technique of length measurement error is widely used in the accuracy assessment of CMMS(Coordinate measuring machines) and machine tools, as it is simple and direct measurement within the working volume of a machine. In this paper, a new method is proposed for the evaluation of the length measurement error in relation to the volumetric accuracy. lD, 2D, and 3D measuring lines are considered for recpective length measurement error: 1D, 2D, and 3D length measurement uncertainties are evaluated from volumetric accuracy. The relationship between the volumetric accuracy md length measurement error to is discussed. PC based system for length measurement error evaluation and simulation is developed.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.55.3-55.3
• /
• 2019

We present a pipeline to estimate baryonic properties of a galaxy inside a dark matter (DM) halo in DM-only simulations using a machine trained on high-resolution hydrodynamic simulations. As an example, we use the IllustrisTNG hydrodynamic simulation of a (75 h^-1 Mpc)³ volume to train our machine to predict e.g., stellar mass and star formation rate in a galaxy-sized halo based purely on its DM content. An extremely randomized tree (ERT) algorithm is used together with multiple novel improvements we introduce here such as a refined error function in machine training and two-stage learning. Aided by these improvements, our model demonstrates a significantly increased accuracy in predicting baryonic properties compared to prior attempts --- in other words, the machine better mimics IllustrisTNG's galaxy-halo correlation. By applying our machine to the MultiDark-Planck DM-only simulation of a large (1 h^-1 Gpc)³ volume, we then validate the pipeline that rapidly generates a galaxy catalogue from a DM halo catalogue using the correlations the machine found in IllustrisTNG. We also compare our galaxy catalogue with the ones produced by popular semi-analytic models (SAMs). Our so-called machine-assisted semi-simulation model (MSSM) is shown to be largely compatible with SAMs, and may become a promising method to transplant the baryon physics of galaxy-scale hydrodynamic calculations onto a larger-volume DM-only run. We discuss the benefits that machine-based approaches like this entail, as well as suggestions to raise the scientific potential of such approaches.

• Journal of the Korean Society of Industry Convergence
• /
• v.13 no.4
• /
• pp.197-203
• /
• 2010

Laser welding is widely used for precision welding because of superior mechanical properties and high productivity. Generally the accuracy of the welding is determined by the distribution of the bead which is affected by the structural vibrations of the equipment. This study was originated to stabilize a laser welding machine to minimize the bead distribution for the precise joining. The structural properties of the laser welding machine have been investigated to analyze the major factors of the vibrations to cause the bead distribution. The ideas for the design improvement have been applied to the simulation model to identify the effects and further to achieve the stability design and to minimize the bead distribution. The result shows that a few simple design alterations can substantially suppress the structural vibrations and improve the welding accuracy. The procedure used for this study can also be applied to similar welding equipments for improving the structural stability and the welding accuracy.

• Journal of the Korean Society of Industry Convergence
• /
• v.4 no.4
• /
• pp.365-369
• /
• 2001

This paper presented a new model of virtualized CNC milling machine. The model verifies the over cut, the under cut and the surface roughness using NC file generated from CAM and cutting condition. The model uses Z-map model to verify workpiece. In this paper, the model used the velocities of x, y and z direction and obtained a center point of a hall end mill for modeling Z-map of workpiece. To investigate the performance of the model, simulation study was carried out. As the results, the model gave geometry accuracy of workpiece, the surface roughness and the chip loads in finish cutting that can predict tool chipping. The virtualized CNC machine can he used a flat end mill, a ball end mill and a rounded end mill.