• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1907-1910
• /
• 2003

Miniaturized machine tool can be used to produce 3D features based on CNC and PC-NC technology in the micro/meso scale. Wide applications of CNC technology are developed and there are lots of know-hows in the cutting process and their CNC application. It helps micro/meso scale structure to machine components, which can be used directly for practical applications. In the present research, as the machine tool is miniaturized, the manufacturing machine tools costs less when compared to the equipment used in other micromachining technologies. Moreover, with advancement of micro tool technology, the cutting process can be used to produce micro/meso scale parts. In conclusion, the proposed system can reduce the cost by utilizing the current machining technology, and as a result, complex micro/meso parts can be produced efficiently with high productivity.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.579-584
• /
• 1999

The purpose of the present paper are not to develope machine tools of new concepts and advanced mechanisms but to introduce and apply new methods and concepts in the design procedure by using and changing the previously existing technologies. In this paper 3D modeller was proposed for designing machine tools and the design and the better manufacturability checking than 2D one so that design error was dramatically reduced. As designer may easily understand the real shape of a part and assembly object, it's easy to draw the drawings not only in a conceptual design but also in a detailed design. Also, design automation software enabled designer to consider the real important design parameters by reducing time to spend in estimating and calculating the strength of the model by the computer aided automatic calculation instead of a tedious and complex calculation by manual method and help him to easily make the decision for selecting the stocks and design the structure of part or unit of machine tools.

• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.94-102
• /
• 2016

This paper proposes a new prediction method to reduce times and labor of repetitive multi-physics simulation. To achieve exact results from the whole simulation processes, complex modeling and huge amounts of time are required. Current multi-physics analysis focuses on the simulation method itself and the simulation environment to reduce times and labor. However this paper proposes an alternative way to reduce simulation times and labor by exploiting machine learning algorithm trained with data set from simulation results. Through comparing each machine learning algorithm, Gaussian Process Regression showed the best performance with under 100 training data and how similar results can be achieved through machine-learning without a complex simulation process. Given trained machine learning algorithm, it's possible to predict the result after changing some features of the simulation model just in a few second. This new method will be helpful to effectively reduce simulation times and labor because it can predict the results before more simulation.

• Neurospine
• /
• v.15 no.4
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.8
• /
• pp.98-104
• /
• 2013

AC machines are in wide use in industry and d-q transformation from 3 phase of a, b, c is commonly used to analyze these kinds of machines. The equivalent circuits of d and q axis are, however, generally cross coupled and difficult to analyze. In this study, a modeling technique of AC machine including induction and PM synchronous motors using matrix vector is proposed. With that model, it can not only explain the AC machines physically but also make it simple to analyze them. The separating process of d and q components is not needed in this model and this model can be applied to analyze asymmetric motors like IPMSM machine. With this technique, the model becomes simple, easy to understand physically, and yields results that are the same as those from other models. These simulation results of the proposed model for induction motor are compared with those of other models to verify the method proposed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.332-336
• /
• 1997

To order to remain competitive, a manufacturing company need to maintain the optimal condition of its manufacturing system. Machine tools as an important element of a manufacturing system comprises complex mechanical as well as electronic components. So, diagnosing the troubles of machine tools is tricky process which requires a lot of experience and knowledge. Since providing machine tool users with necessary serices at the right time is very difficult,a remote diagnosis system is to be regarded as a good alternative, with which users can diagnose and fix the machine troubles. This paper presents a method to implement a remote machine tool diagnosis system using the world wide web technology and backward reasoning expert system.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.6
• /
• pp.627-635
• /
• 2019

In this study, we developed for processing complex features using CAM software that satisfies precision for example practice and related qualification tests suiTable for CNC training purposes. In addition, functions such as location control, speed control, and processing path generation, which are the main functions of CNC machining machines, were constructed using small equipment parts, servo motors, inverters, general purpose PCs, and commercial NC software and researched with the goal of developing low-cost education equipment. In the static accuracy inspection, the degree of machine when measuring the parallelism of the X, Y and Z axes and the vibration of the main shaft did not reach the allowable value. However, we have obtained a finished product that satisfies the CNC machine book sample shape machining, detailed functions of the position control function of the CNC machine tool, linear interpolation function, circular interpolation function, and tool offset function. In the qualification test shape processing, a shape with a degree of 1/100 mm was processed to obtain position accuracy that satisfied the tolerance.

• Journal of Convergence Society for SMB
• /
• v.1 no.1
• /
• pp.75-83
• /
• 2011

Unified Modeling Language (UML) is widely accepted in industry and particularly UML State Machine Diagram is popular for describing the dynamic behavior of classes. This paper discusses deadlock detection of System using UML State Machine Diagram. Since a State Machine Diagram is used for indivisual class' behavior, all the State Machine Diagrams of the classes in the system are combined to make a big system-wide State Machine Diagram to describe system behavior. Generally this system-wide State Machine Diagram is very complex and contains invalid state and transitions. To make it a usable and valid State Machine Diagram, synchronization and externalization are applied. The reduced State Machine Diagram can be used for describing system behavior thus conventional model-checking technique can be applied. This paper shows how deadlock detection of system can be applied with simple examples. All the procedures can be automatically done in the tool.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.60-67
• /
• 2008

The vibrations and noise origin in electric material is due to several coupled physical phenomena. The revolving electric machine complete modeling is complex; it does not allow simple parametric machine structure studies for various operation modes. This work presents a simple electromagnetic model which makes possible the machine principal parts flow estimation from flux density. Special interest is given in determining Switched Reluctance Machine (S.R.M) radial acceleration in accordance with the current supply. Our focus will be only on the magnetic origin efforts that are dominating in the S.R.M. The efforts calculation versus the current is presented in the case of a machine with a linearized rate. These efforts are considered as a tangential force producing the torque and a radial force that generates no torque. The application is realized on a 6/4 low power S.R.M type (6 stator teeth and 4 teeth rotor). The mechanical response is substituted in a transfer function. The model takes account of the power supply of the machine, the relation between the current supply and the efforts as well as the vibratory response of the machine to these efforts. Finally, the model is validated by comparison with similar experimental results within the framework of the definite assumptions.

• Geomechanics and Engineering
• /
• v.29 no.3
• /
• pp.249-258
• /
• 2022

A disc cutter is an excavation tool on a tunnel boring machine (TBM) cutterhead; it crushes and cuts rock mass while the machine excavates using the cutterhead's rotational movement. Disc cutter wear occurs naturally. Thus, along with the management of downtime and excavation efficiency, abrasioned disc cutters need to be replaced at the proper time; otherwise, the construction period could be delayed and the cost could increase. The most common prediction models for TBM performance and for the disc cutter lifetime have been proposed by the Colorado School of Mines and Norwegian University of Science and Technology. However, design parameters of existing models do not well correspond to the field values when a TBM encounters complex and difficult ground conditions in the field. Thus, this study proposes a series of machine learning models to predict the disc cutter lifetime of a shield TBM using the excavation (machine) data during operation which is response to the rock mass. This study utilizes five different machine learning techniques: four types of classification models (i.e., K-Nearest Neighbors (KNN), Support Vector Machine, Decision Tree, and Staking Ensemble Model) and one artificial neural network (ANN) model. The KNN model was found to be the best model among the four classification models, affording the highest recall of 81%. The ANN model also predicted the wear rate of disc cutters reasonably well.