• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.4
• /
• pp.88-99
• /
• 1995

The demand for automatic manufacturing systems is increasing. Flexible Manufacturing System(FMS) is usually considered as a soluting for the shop floor automation. One of the difficulties in FMS is the communications problem. Since various machineries with different communications protocoles are included, applying a unified scheme is almost impossible. Therefore, a systematic approach is a key point to solve the communication problem. A cell is difined as an automation unit where closely related for a job reside together. A cell is a messenger between upper level computers and lower level machine equipment. In this research, the fonctions of the cell are defined to have more capabilities than conventional cells since a cell can be often a total manufacturing system is a small to medium sized factory. The cell conducts communications with different machines through the communications schemes established here. A set of software system has been developed according to the defined communication. The software has been tested for a simulation and real experiments for proof.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.3
• /
• pp.81-86
• /
• 1993

It is well known that the interest on the on-line sensing of tool wear is growing more and more with the aim of controlling machine tools productivity from the point of view of quality. This paper describes the sensing of the amount of flank wear with vision system. To obtain a proper image He-Ne laser generator is used as the lighting source and obtained image is processed with block processing algorithm and morphological image processing method. By means of this system it is possible to evaluate the parameters of tool wear. Experimental tests performed with this system on an NC lathe have shown good performances here described and discussed.

• Structural Engineering and Mechanics
• /
• v.89 no.1
• /
• pp.47-59
• /
• 2024

In this study, a new sustainable material was proposed to prepare precast tunnel lining segments (TLS), which were produced using a fiber-reinforced slag-based geopolymer composite. Slag was used as the geopolymer binder. In addition, polypropylene and carbon fibers were added to reinforce TLSs. TLSs were examined in terms of flexural performance, load-deflection response, ductility, toughness, crack characteristics, and tunnel boring machine (TBM) thrust force. Simultaneously, numerical simulation was performed using finite element analysis. The mechanical characteristics of the geopolymer composite with a fiber content of 1% were used. The results demonstrated that the flexural performance and load-deflection response of the precast TLSs were satisfactory. Furthermore, the numerical results were capable of predicting and realistically capturing the structural behavior of precast TLSs. Therefore, fiber-reinforced slag-based geopolymer composites can be applied as precast TLSs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.233-242
• /
• 2018

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting feature point based on only R peak through optimal R wave. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30. The achieved scores indicate the average of 99.02% in R wave detection and the rate of 94.85% in PVC classification.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.8
• /
• pp.461-467
• /
• 2011

Accurate classification of input signals is the key prerequisite for variable bit-rate coding, which has been introduced in order to effectively utilize limited communication bandwidth. Especially, recent surge of multimedia services elevate the importance of speech/music classification. Among many speech/music classifier, the ones based on support vector machine (SVM) have a strong selling point, high classification accuracy, but their computational complexity and memory requirement hinder their way into actual implementations. Therefore, techniques that reduce the computational complexity and the memory requirement is inevitable, particularly for embedded systems. We first analyze implementation of an SVM-based classifier on embedded systems in terms of execution time and energy consumption, and then propose two techniques that alleviate the implementation requirements: One is a technique that removes support vectors that have insignificant contribution to the final classification, and the other is to skip processing some of input signals by virtue of strong correlations in speech/music frames. These are post-processing techniques that can work with any other optimization techniques applied during the training phase of SVM. With experiments, we validate the proposed algorithms from the perspectives of classification accuracy, execution time, and energy consumption.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1066-1071
• /
• 2005

This paper presents the two lossless auxiliary inductors-assisted voltage source type half bridge (single ended push pull: SEPP) series resonant high frequency inverter for induction heated fixing roller in copy and printing machines. The simple high-frequency inverter treated here can completely achieve stable zero current soft switching (ZCS) commutation for wide its output power regulation ranges and load variations under its constant high frequency pulse density modulation (PDM) scheme. Its transient and steady state operating principle is originally described and discussed for a constant high-frequency PDM control strategy under a stable ZCS operation commutation, together with its output effective power regulation characteristics-based on the high frequency PDM strategy. The experimental operating performances of this voltage source SEPP ZCS-PDM series resonant high frequency inverter using IGBTs are illustrated as compared with computer simulation results and experimental ones. Its power losses analysis and actual efficiency are evaluated and discussed on the basis of simulation and experimental results. The feasible effectiveness of this high frequency inverter appliance implemented here is proved from the practical point of view.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.33-42
• /
• 2010

This research propose a practical guidance system considering ocean currents in real sea operation. Optimality of generated path is not an issue in this paper. Way-points from start point to possible goal positions are selected by experienced human supervisors considering major ocean current axis. This paper also describes the implementation of a precise underwater navigation solution using multi-sensor fusion technique based on USBL, GPS, DVL and AHRS measurements in detail. To implement the precise, accurate and frequent underwater navigation solution, three strategies are chosen. The first one is the heading alignment angle identification to enhance the performance of standalone dead-reckoning algorithm. The second one is that absolute position is fused timely to prevent accumulation of integration error, where the absolute position can be selected between USBL and GPS considering sensor status. The third one is introduction of effective outlier rejection algorithm. The performance of the developed algorithm is verified with experimental data of mine disposal vehicle and deep-sea ROV.

• Journal of IKEEE
• /
• v.20 no.4
• /
• pp.398-411
• /
• 2016

SVM, a machine learning method, is widely used in image processing for it's excellent generalization performance. However, to add other data to the pre-trained data of the system, we need to train the entire system again. This procedure takes a lot of time, especially in embedded environment, and results in low performance of SVM. In this paper, we implemented an SVM trainer and classifier in an FPGA to solve this problem. We parlallelized the repeated operations inside SVM and modified the exponential operations of the kernel function to perform fixed point modelling. We implemented the proposed hardware on Xilinx ZC 706 evaluation board and used TSR algorithm to verify the FPGA result. It takes about 5 seconds for the proposed hardware to train 2,000 data samples and 16.54ms for classification for $1360{\times}800$ resolution in 100MHz frequency, respectively.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.11
• /
• pp.1429-1436
• /
• 2011

In this paper, a new tube-radius-measuring algorithm has been proposed for effectively measuring the radii of small tubes under severe noise conditions that can also perform well when metal scraps that make it difficult to measure the radius correctly are inside the tube hole. In the algorithm, we adopt a fuzzy searching method that searches for the center of the inner circle by using fuzzy parameters for distance and orientation from the initial search point. The proposed algorithm has been implemented and tested on both synthetic and real-world tube images, and the performance is compared to existing circle-detection algorithms, such as the Hough transform and RANSAC methods, to prove the accuracy and effectiveness of the algorithm. From this comparison, it is concluded that the proposed algorithm has excellent performance in terms of measurement accuracy and computation time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.42-47
• /
• 2017

In the distribution of digital image, the median filtering is used for a forgery. This paper proposed the algorithm of a image forensics detection for the classification of median filtering. For the solution of this grave problem, the feature vector is composed of 42-Dim. The detected quantity 32, 64 and 128 of forgery image edges, respectively, which are processed by the Hough transform, then it extracted from the start-end point coordinates of the Hough Lines. Also, the Hough Peaks of the Angle-Distance plane are extracted. Subsequently, both of the feature vectors are composed of the proposed scheme. The defined 42-Dim. feature vector is trained in SVM (Support Vector Machine) classifier for the MF classification of the forged images. The experimental results of the proposed MF detection algorithm is compared between the 10-Dim. MFR and the 686-Dim. SPAM. It confirmed that the MF forensic classification ratio of the evaluated performance is 99% above with the whole test image types: the unaltered, the average filtering ($3{\times}3$), the JPEG (QF=90 and 70)) compression, the Gaussian filtered ($3{\times}3$ and $5{\times}5$) images, respectively.