• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1440-1444
• /
• 2011

Memory-device is one of the auxiliary components of point-switch machine; connecting front-rod and tongue-rail. The right side and left side of memory-device are different from each other. When there would be a derailing accident of rolling stock or motor-car, the memory-device properly bends and protects the internal of point-switch machine. Memory-device is one of the important site maintenance spare parts. Memory-device for each of right and left side should be secured so that they can be installed on correct side during an exchange work. This study suggests the development of memory-device with different left and right side and the performance test of it. The study intends to contribute in the convenience improvement of maintenance by improving the unification of memory-device.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.477-482
• /
• 2005

Recently, client computing trend has been changed from server oriented information application to network based P2P(Peer to Peer) services. The conventional client/server method has the merit of accessing abundant information, on the other side P2P has the merit of synchronized community support and information exchange. P2P has four meaning of point to point, peer to peer, person to person and path to profitability. In manufacturing system field, the second meaning is interested. P2P is classified to three type such as conventional client/server, hybrid P2P and pure P2P. The third is really peer to peer concept. The related technologies with P2P are P2P searching, XML, cooperation, IPv6, computing sharing and P2P communication. This paper describes the scheme of P2P and related contents. And through the P2P based technology, a P2P-based collaborative machine and a vertical portal machine are introduced in this paper. The scheme of the machines mentioned above is suggested for cooperation in manufacturing system and u-Manufacturing.

• Proceedings of the KIEE Conference
• /
• 2004.10a
• /
• pp.43-45
• /
• 2004

This paper represents the improvement of floating point operation for AC servo motor controller based on fixed point operation DSP. TMS320F2812 has fixed point operation processing structure. The controller parameters are modified to the digitized data by scaling the original parameters. TMS320F 2812 is a 32-bit processor, and it could have enough accuracy to get the digitized data this procedure is implemented and the experiments controling a AC servo system.

• Journal of the Korean Society of Industry Convergence
• /
• v.13 no.4
• /
• pp.205-209
• /
• 2010

Even the domestically small-and medium-sized companies progressed development in the monitoring equipment of inspecting run out in steel wheel aiming to supply and generalize through developing the monitoring equipment for securing quality technology and enhancing quality-test level. Run-Out value in vehicle wheel was measured with Computer & Servo system by using Low-Point marking machine control system, which is this development product. Low-Point value was operated and calculated. It marked by revolving wheel as much as the demanded measurement value based on 1ST harmony curve. Thus, the shipment of inferior product, which occurs in the measurement by the existing worker, could be blocked in advance. In the existing case, 60 sec. was required for inspecting 1 product. However, it came to bring about a rise in production volume through shortening inspection time to 8 seconds and improving workers' operating environment.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1202-1211
• /
• 2018

In this paper, induction machine operation efficiency and torque is improved using Machine Learning based Gene Optimization (ML-GO) Technique is introduced. Optimized Genetic Algorithm (OGA) is used to select the optimal induction machine data. In OGA, selection, crossover and mutation process is carried out to find the optimal electrical machine data for induction machine design. Initially, many number of induction machine data are given as input for OGA. Then, fitness value is calculated for all induction machine data to find whether the criterion is satisfied or not through fitness function (i.e., objective function such as starting to full load torque ratio, rotor current, power factor and maximum flux density of stator and rotor teeth). When the criterion is not satisfied, annealed selection approach in OGA is used to move the selection criteria from exploration to exploitation to attain the optimal solution (i.e., efficient machine data). After the selection process, two point crossovers is carried out to select two crossover points within a chromosomes (i.e., design variables) and then swaps two parent's chromosomes for producing two new offspring. Finally, Adaptive Levy Mutation is used in OGA to select any value in random manner and gets mutated to obtain the optimal value. This process gets iterated till finding the optimal value for induction machine design. Experimental evaluation of ML-GO technique is carried out with performance metrics such as torque, rotor current, induction machine operation efficiency and rotor power factor compared to the state-of-the-art works.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.109-118
• /
• 1999

The objective of this research is to develop an effective inspection planning strategy for sculpture surfaces in OMM(On-Machine Measurement) process. As a first step, effective measuring point locations are determined to obtain optimum results for given sampling numbers. Two measuring point selection methods are suggested in this study based on newly proposed CAD/CAM/CAI integration concept: (1) by the prediction of cutting errors, (2) by considering cutter contact points to avoid the measurement errors caused by cusps. As a next step, the TSP(Traveling Salesman Problem)algorithm is applied to minimize the probe moving distance. Appropriate simulations and experiments are performed to verify the proposed inspection planning strategy in this study, and the results are analyzed.

• Journal of the Optical Society of Korea
• /
• v.18 no.5
• /
• pp.523-530
• /
• 2014

Machine material and structural strain are critical factors for appraising mechanical properties and safety. Particularly in three and four-point bending tests, which appraise the deflection and flexural strain of an object due to external force, measurements are made by the crosshead movement or deflection meter of a universal testing machine. The Digital Image Correlation (DIC) method is one of the non-contact measurement methods. It uses the image analyzing method that compares the reference image with the deformed image for measuring the displacement and strain of the objects caused by external force. Accordingly, the advantage of this method is that the object's surface roughness, shape, and temperature have little influence. However, its disadvantage is that it requires extensive time to compare the reference image with the deformed image for measuring the displacement and strain. In this study, an algorithm is developed for DIC that can improve the speed of image analysis for measuring the deflection and strain of an object caused by a three-point bending load. To implement this algorithm for improving the speed of image analysis, LabVIEW 2010 was used. Furthermore, to evaluate the accuracy of the developed fast correlation algorithm, the deflection of an aluminum specimen under a three-point bending load was measured by using the universal test machine and DIC measurement system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1245-1248
• /
• 2004

This paper presents a new technique to analyze data on the coordinate x, y, z and apply these data to design the motion control to improve the efficiency of the engraving machine so that it can engrave accordingly in 3 dimensions. First, the tool path on the x-y plane is analyzed to be synchronized with the z-axis. The digital data is then sent to the motion control to guide the movement of the engrave point on the x-y plane. Tool path moves along the x-axis with zero degree and different values of the y-axis according to the coordinate of the digital data and the analysis along z-axis to determine the depth for engraving. The depth can be specified from the gray level with the 256 levels of resolution. The data obtained includes the distances on x-axis, y-axis, and z-axis, the acceleration of the engrave point's movement, and the speed of the engrave point's movement. These data is then transfered to the motion control to guide the movement of the engrave point along the z-axis associated with the x-y plane. The results indicate that engraving using this technique is fast and continuous. The specimen obtained looks perfect in 3D view.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.6
• /
• pp.1081-1090
• /
• 2015

This work proposes a theoretic framework for the performance assessment of an access point in the IP network that accommodates MD (Machine Data) and HD (Human Data). First, we investigate typical resource allocation methods in LTE for MD and HD. After that we carry out a Max-Min analysis about the surplus and deficiency of network resource seen from MD and HD. Finally, we evaluate the performance via numerical experiment.