• Journal of international Conference on Electrical Machines and Systems
• /
• v.2 no.1
• /
• pp.23-30
• /
• 2013

This paper proposes a parametric model for inter-turn fault detection in a fault-tolerant permanent-magnet (FTPM) machine, which can predict the effect of the short-circuit fault to various physical quantity of the machine. For different faulty operations, a new effective stator inter-turn fault detection method is proposed. Finally, simulations of vector-controlled FTPM machine drives are given to verify the feasibility of the proposed method, showing that even single-coil short-circuit fault could be exactly detected.

• Journal of Welding and Joining
• /
• v.21 no.6
• /
• pp.26-32
• /
• 2003

Arc welding process has indicated that it suffers from many flaws. It's because requirement of products is diverse and factors which affects the quality is also various. Therefore, in order to stabilize the welding process, it is important to choose a proper welding machine for the each process, and to evaluate the welding process capability of each machine. In this study, rational and simple index to evaluate the welding machine was set the coefficient of resistance variation through the arc stability examination such as spatter generation weight and bead configuration uniformity etc. And the method to evaluate the process capability index was developed by application of 6$\sigma$.

• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.318-324
• /
• 2015

This paper proposes a dynamic short-term load forecasting method that utilizes a new sequential learning algorithm based on Relevance Vector Machine (RVM). The method performs general optimization of weights and hyperparameters using the current relevance vectors and newly arriving data. By doing so, the proposed algorithm is trained with the most recent data. Consequently, it extends the RVM algorithm to real-time and nonstationary learning processes. The results of application of the proposed algorithm to prediction of electrical loads indicate that its accuracy is comparable to that of existing nonparametric learning algorithms. Further, the proposed model reduces computational complexity.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1991.10a
• /
• pp.124-130
• /
• 1991

5-axis NC machining of sculptured surface using non-ballendmill cutters (eg. facemilling cutters) is widely used in the machining of turbine blades and marine propellers. Since there are more degrees of freedom in 5-axis machining than in 3-axis machining, generating "optimum" cutter paths and finding desirable cutter positions become very important in order for an efficient use of 5-axis NC machines. Also critical in 5-axis NC machining are collision avoidance, gouging checking, and efficient kinematic solutions. In this paper we discuss the above issues in generating 5-axis CL data. They are : kinematics modeling of NC machine; inverse kinematics solution; interference between machine component and surface; cutter gouging. A unique search method for obtaining optimal CL data is proposed. The proposed method has been successfully implemented in the machining of marine propellers on a dual 5-axis (ie, 9-axis) NC machine.C machine.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2017.05a
• /
• pp.152-153
• /
• 2017

In the construction site, it is necessary to estimate the compressive strength of concrete in order to adjust the demolding time of the form, and establish and adjust the construction schedule. The compressive strength of concrete is determined by various influencing factors. However, the conventional method for estimating the compressive strength of concrete has been suggested by considering only 1 to 3 specific influential factors as variables. In this study, six influential factors (Water, Cement, Fly ash, Blast furnace slag, Curing temperature, and humidity) of papers opened for 10 years were collected at three conferences in order to know the various correlations among data and the tendency of data. After using algorithm of various methods of machine learning techniques, we selected the most suitable regression analysis model for estimating the compressive strength.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.239-245
• /
• 2020

Blockchain, machine learning, and big data are among the key components of the future IT track. These technologies are used in various fields; hence their increasing application. This paper discusses the technologies developed in various research fields, such as data representation, Blockchain application, 3D shape recognition and classification, query method, classification method, and search algorithm, to provide insights into the future paradigm. In this paper, we present a summary of 18 high-quality accepted articles following a rigorous review process in the fields of Blockchain, machine learning, and big data.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.217-226
• /
• 2004

An automatic pronunciation correction system provides users with correction guidelines for each pronunciation error. For this purpose, we develop a speech recognition system which automatically classifies pronunciation errors when Koreans speak a foreign language. In this paper, we propose a machine scoring method for automatic assessment of pronunciation quality by the speech recognizer. Scores obtained from an expert human listener are used as the reference to evaluate the different machine scores and to provide targets when training some of algorithms. We use a log-likelihood score and a normalized log-likelihood score as machine scoring methods. Experimental results show that the normalized log-likelihood score had higher correlation with human scores than that obtained using the log-likelihood score.

• Journal of Korean Society for Quality Management
• /
• v.38 no.3
• /
• pp.354-362
• /
• 2010

This paper presents a non-linear control chart based on support vector machine regression (SVM-R) to improve the accuracy of fault detection of cyclic signals. The proposed algorithm consists of the following two steps. First, the center line of the control chart is constructed by using SVM-R. Second, we calculate control limits by variances that are estimated by perpendicular and normal line of the center line. For performance evaluation, we apply proposed algorithm to the industrial data of the chemical vapor deposition process which is one of the semiconductor processes. The proposed method has better fault detection performance than other existing method

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.9
• /
• pp.34-40
• /
• 2002

Machining accuracy is affected by quasi-static errors of machining center. Since machine errors have a direct influence upon both the surface finish and geometric shape of the finished workpiece, it is very important to measure the machine errors and to compensate these errors. The laser measurement method for identifying geometric errors of machine tool has the disadvantages such as high cost, long calibration time and usage of volumetric error synthesis model. Accordingly, this paper deals with analysis of the geometric errors of a machine tool using ball bar test without using complicated error synthesis model. Statistical analysis method was adopted in this paper for deriving geometric errors using hemispherical helix ball bar test. As a result of experiment, geometric errors of the vertical machining center are compensated by 88%.

• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.1
• /
• pp.60-68
• /
• 2004

The purpose of this paper is to establish an effective inspection system by using OMM (On-Machine Measurement) system based PC-NC. This system can reduce manufacturing lead time because a workpiece is inspected at every machining process and the manufacturing system which includes inspection faculty is able to realize on-line process on CNC machining center. The proposed OMM system is composed of a few algorithms for determination of inspection parameters. It is accomplished by determining the number of measuring points, their location, measuring path using fuzzy logic, Hammersley's method, TSP (Traveling Salesperson Problem) algorithm. The inspection feature applied to this system is based on machining feature. This method is tested by simulation and experiment that are analyzed measuring data and geometry tolerance.