• 한국정밀공학회지
• /
• 제15권7호
• /
• 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.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 하계학술대회 논문집 D
• /
• pp.784-786
• /
• 1997

In this Paper, the effective method of determining the water discharge of a pondage hydro-unit for hydro dispatch is proposed. The water discharge of a pondage hydro-unit can be determined subtracting the spillage discharge from summation of the inflow and the pondage according to variation of the water level of the reservoir. Proposed method calculates the inflow using the duration curve, the water level from initial level on January 1, and the spillage discharge from the water discharge.

• 한국정밀공학회지
• /
• 제15권5호
• /
• 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.

• 한국정밀공학회지
• /
• 제15권2호
• /
• pp.7-13
• /
• 1998

This paper presents a methodology for determining machining conditions in Electric Discharge Wire-Cut. Unification of two phase neural network approach with an automatic generation of machining parameters is designed. The first phase neural network, which is 1 to M backward-mapping neural net, produces approximate machining conditions. Using approximate conditions, all possible conditions are newly created by the proposed automatic generation procedure. The second phase neural net, which is a M to 1 forward-mapping neural net, determines the best one among the generated candidates. Simulation results with ANN are given to verify that the presenting methodology could apply for determining machining parameters in Electric Discharge Wire-Cut.

• Journal of the Korean Data and Information Science Society
• /
• 제21권2호
• /
• pp.279-289
• /
• 2010

이 논문에서는 호흡곤란을 주호소로 내원한 668명의 환자를 대상으로 입퇴원 결정을 위한 간편한 통계모형을 제안한다. 이것을 위해 55개 변수 중 임상전문가에 의해 중요하다고 선택된 11개 변수를 설명변수로 이용하였다. 먼저 변환과정으로 11개 연속형 변수 각각에 대해 실제 입원과 퇴원 환자의 커널밀도함수에 의해 퇴원구간을 설정하였다. 다음으로 11개 설명변수 중 퇴원구간에 속한 변수의 개수를 가지고 환자의 퇴원여부를 결정하는 최적 모형을 선택하였다. 입원과 퇴원 환자수의 불균형 때문에 최적 모형의 선택기준으로는 민감도와 특이도의 산술평균과 민감도와 정확률의 조화평균을 이용하였다. 그 결과 11개의 검사결과 중 7개 이상에서 퇴원구간이 나오면 퇴원을 결정하는 것이 최적 모형이 되었다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권1호
• /
• pp.125-133
• /
• 2013

이 논문에서는 호흡곤란을 주호소로 내원한 668명의 환자를 대상으로 11개 혈액검사 결과를 이용하여 퇴원여부를 결정하는 벌점 이항 로지스틱 회귀 기반 통계모형을 유도하였다. 구체적으로 $L^2$ 벌점에 근거한 능형 모형과 $L^1$ 벌점에 근거한 라소 모형을 고려하였다. 이 모형의 예측력 비교 대상으로는 일반 로지스틱 회귀의 11개 전체 변수를 사용한 모형과 변수선택된 모형이 사용되었다. 10-묶음 교차타당성 (10-fold cross-validation) 비교 결과 능형 모형의 예측력이 우수한 것으로 나타났다.

• 한국CDE학회논문집
• /
• 제4권4호
• /
• pp.355-359
• /
• 1999

This paper presents a method for determining machining parameters in electrical discharge machining process (EDM) based on discharge area. The parameters are the peak value of currents, the pulse-on time, and the pulse-off time, on which the EDM performance depends chiefly. The optimal machining parameters are closely related on discharge area, which can be calculated from a tool electrode and a discharge height. In the paper the discharge area is obtained from NC code for machining the tool electrode instead of its geometric model. The method consists of following three steps. First a Z-Map model is constructed from the NC code. Secondly, the discharge area is obtained from the Z-Map model and a Z-height. Finally, the machining parameters are calculated from the discharge area. An introduced example shows that the machining parameters are calculated by the using a Z-map model obtained from the machining data for a tool electrode.

• 한국정밀공학회지
• /
• 제17권1호
• /
• pp.27-33
• /
• 2000

This paper presents a method for determining machining parameters in 3-dimentional electrical discharge machining(EDM). The parameters are the peak value of currents, the pulse-on time, and the pulse-off time. It is known that they influence the performance of EDM more than the other else. The parameters are determined from the discharge area between a tool electrode and a work piece. The discharge area is directly influenced by the geometry of a tool surface and the tool discharge position. The discharge area on a tool discharge position is calculated from intersection curves between the tool surface and a horizontal plane. The grid search method is applied to determine the intersection curves. An example is introduced to show that the machining parameters are obtained from the surface geometry of a tool electrode.

• 한국생산제조학회지
• /
• 제9권5호
• /
• pp.58-64
• /
• 2000

This paper proposes a method for determining optimal EDM parameters based on discharge area from the physical model of a tool electrode. Main parameters, which affect the EDM performance, are peak value of currents, pulse-on time, and pulse-off time. Such parameters are closely dependent on the discharge area in EDM process. In this paper the discharge area is estimated from the CMM scanning data to the tool electrode. The method is very useful when any geometric information to the tool electrode is not provided from tool modeler or producer. The method consists of following four steps. First a triangulation mesh is constructed from the CMM data. Secondly, the z-map is modeled from the triangulated mesh. Thirdly, the discharge area is estimated from intersection between the z-map model and a z-height plane. Finally, the machining parameters are easily calculated by some known EDM equations to the discharge area. An example is introduced to show that the machining parameters are calculated from the CMM data to a tool electrode.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2007년도 정기총회 및 학술발표대회
• /
• pp.387-390
• /
• 2007

The mixing characteristics of heated water discharged from different types of effluents are simulated using a commercial software, Flow-3D model. In order to verify the model, the comparison of numerical results with the experimental data are conducted for each type of effluent, the submerged and surface overfall. It is observed that the numerical results show a reasonable agreement with the experimental data. Based on this study the application to the heated water discharge problem in the field can be expected as a further study and it can be the fundamental data when determining the type of effluent in a powerplant.