• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.7
• /
• pp.44-51
• /
• 1998

Two-step neural network is designed for determining electrical discharge machining parameters in low erosion. The first neural network, which is used as a classification network, checks whether the current conditions are appropriate to electrical discharge machining in low tool erosion. If the conditions are appropriate to EDM in low erosion, suitable EDM parameters are generated by the second neural network. Theoretically known EDM conditions are produced and also utilized for training the second neural network. The trained neural network is tested how well suitable EDM machining conditions are generated under unknown machining situations Experimental result shows that the proposed two-step neural network approach could be effectively used for determining EDM parameters in low tool erosion. The results also have a practical contribution to EDM area in that it could be applied for maintaining low tool wear as well as obtaining maximum machining rates simultaneously.

• IE interfaces
• /
• v.11 no.1
• /
• pp.145-153
• /
• 1998

In this paper, two parts of neural networks were proposed for determination of optimal EDM parameters. One is pattern recognition neural network that can be selecting expert neural network suitable to the EDM mode. The other is expert neural network that can be determining optimal EDM parameters such as pulse on time and pulse off time. Prior to determination of EDM parameters, Peak current, which is related to the EDM area closely, determined base on EDM area that is calculated from CAD data, firstly. Then, the other EDM parameters determined by the expert neural network that is selected to the EDM mode.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.5
• /
• pp.43-49
• /
• 1998

Adaptive neural network approach is presented for determining Electrical Discharge Machining (EDM) parameters. Electrical Discharge Machining has been widely used with its capability of machining hard metals and tough shapes. In the past few years, EDM has been established in tool-room and large-scale production. However. in spite of it's wide application, an universal selection method of EDM parameters has not been established yet. No attempt has been tried before to suggest a logical method in determining essential machine parameters considering the machining rate and resulting surface roughness integrity. The paper presents a method, which is focusing on determining appropriate machining parameters. Depending on the electrode wear and surface roughness, an adaptive neural network is designed for providing suitable machining guideline.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12A
• /
• pp.1160-1170
• /
• 2010

Existing multipath routing mechanism has much overhead to maintain the state of nodes on the multipath route and does not guarantees completely disjoint multipath construction from source to destination. In this paper, we propose an Explicit Disjoint Multipath (EDM) routing algorithm to enhance energy efficiency through removing the flooding mechanism for route discovery process, minimizing the number of nodes participating in route update and balancing the traffic load for entire network. EDM constructs logical pipelines which can create disjoint multipaths in logical way. Then it physically performs anchor node based geographic routing along the logical pipeline in order to build multipath to the destination. EDM can provide the distribution effect of traffic load over the network, help to balance the energy consumption and therefore extend the network lifetime.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.393-398
• /
• 2007

According to the Korean datum change to a world geodetic system, the EDM area should be readjusted to provide consistent product over the country. The data set for EDM area is extracted from the previous KTN1987 DB and checked for the moved markers in XY network adjustment which provides quality verification. Then, EDM data set for the seven areas are rebuilt for the adjustment. Since the data is still based on the old datum, the coordinates of the data are transformed by applying the coordinate transformation parameters. Here, the transformation parameters, which were determined for the conversion of 1:50,000 topographic maps by NGII, were used. For each EDM point, the geoidal height from EGM96 model is applied to obtain the ellipsoidal height based on the GRS80. The measured distance projected onto GRS80 is adjusted using BL network adjustment by fixing 2nd order or 3rd order GPS control points. The results from the readjustment show the minimum standard error of 1.37" and the maximum standard error of 2.13". Considering the measurement accuracy of EDM (1.6" corresponding to about 2cm) and GPS position for fixed points (2cm), this result is considered to be reasonable and it is good for the practical use.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1D
• /
• pp.167-173
• /
• 2011

This paper analyzes the procedure of calculating how the results of national control points (triangulation points), based on Bessel datum, have been transformed into those of KGD2002, based on the world geodetic system. GPS and EDM data observed from 1974 to 2008 were used for this purpose. A large-scale integrated GPS network was constructed to estimate the results of KGD2002 and new national control points about 12,000 were decided through multiple stages of data processing. The accuracy of these results is ${\pm}0.015m$ (95%) in the horizontal direction and ${\pm}0.030m$ (95%) in the vertical direction. The adjusted results verified by the construction of an integrated GPS/EDM network were compared with the results of KGD2002. In conclusion, the bulletin results are thought to be appropriate because the coordinate differences (RMSE) are ${\pm}0.0025m$ and ${\pm}0.008m$ in horizontal and vertical directions respectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.04a
• /
• pp.1044-1048
• /
• 1997

Wire-cut EDM is used in Die manufacturing as the part of non-traditional cutting process, But,the determination of it's cutting condition with high efficiency and precision is difficult due to the influence of cutting environment and cutting mechanism. In this study, we examine the cutting performance of the SKD11 and Brass in wire-cut EDM and make the neural network which have the configuration of 5-12-2 and back-propagation learning rule. Through the neural network, we can appraise the cutting performance before working and determine the optimal cutting condition. By introducing this method to the W-cut EDM, we can enhance the cutting efficiency.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.5
• /
• pp.465-474
• /
• 2007

This paper focuses on examining and evaluating results of the Korean Geodetic Datum 2002 (KGD2002) of the national horizontal network adjustment. To this end, 137 geodetic control points were independently observed by GPS technology. After processing all the observations, their results were compared with ones derived by the national network adjustment which was recently performed to determine new KGD 2002 coordinate sets over the national geodetic control points. The comparisons results showed that RMSE was ${\pm}2.7cm$ and ${pm}6.5cm$ in horizontal and vertical component in the case of GPS network, whereas RMSE was ${\pm}3.0cm$, in horizontal component in the case of EDM network.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.13 no.5
• /
• pp.201-208
• /
• 1993

The emergence of the Global Positioning System(GPS) with its benefits of speed and economy now offers an opportunity to analyse, strengthen, densify and constitute the control network, in addition to providing mapping, cadastral and engineering control under the unfavorable conditions. This research aims at the using of GPS compared to conventional geodetic positioning techniques in Korean primary control networks. A GPS test network of 10km baselines, which is measured and analysed by Wild GPS-System 200, are compared to the distances from EDM and official coordinates, and relative GPS heights are transformed to the height differences on the mean sea level. The results of this study confirms that using GPS merely as a new type of instrument is the most powerful method for the densification of the control points retaining existing networks and existing computational procedures.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.8 no.1
• /
• pp.51-56
• /
• 1990

Recently, Electronic Distance Meter(EDM) is widely used for the traverse surveying and trilateration net. In this study, the closed traverse network is precisely adjusted by simultaneous adjustment of the observed angle and distance, using the Electronic Total Stations (Set 3). And also, it is examined that each kind accidental errors appear observed angles according to the observed distance and the number of repeating angle. In addition to the result, of checking between the simultaneous adjustment, the compass rule and transit rule, simultaneous adjustment in combination of the observed angle and distance is more accurate and effective than other adjustment.