• 한국공작기계학회논문집
• /
• 제14권1호
• /
• pp.52-57
• /
• 2005

In the foe of global competition, the requirements for the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a mai or change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models for simulation and quantitative description of the industrial operations involved. In this paper, an on-line training neural network for both long-term teaming and short-term teaming was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2003년도 춘계학술대회 논문집
• /
• pp.124-129
• /
• 2003

In the face of global competitor the requirements flor the continuously increasing productivity, flexibility and quality(dimensional accuracy, mechanical properties and surface properties) have imposed a major change on steel manufacturing industries. Indeed, one of the keys to achieve this goal is the automation of the steel-making process using AI(Artificial Intelligence) techniques. The automation of hot rolling process requires the developments of several mathematical models fir simulation and quantitative description of the industrial operations involved. In this paper, a on-line training neural network for both long-term teaming and short-term teaming was developed in order to improve the prediction of rolling force in hot rolling mill. This analysis shows that the predicted rolling force is very closed to the actual rolling force, and the thickness error of the strip is considerably reduced.

• 한국정밀공학회지
• /
• 제25권12호
• /
• pp.117-124
• /
• 2008

In early design stage, the simulation of interior noise is useful for the enhancement of the noise, vibration and harshness (NVH) performance in a vehicle. The traditional transfer path analysis (TPA) technology cannot simulate the interior noise since it uses the experimental method. In order to solve this problem, in this paper, the hybrid TPA is developed as the novel approach. The hybrid TPA uses the simulated excitation force as the input force, which excites the flexible body of a car at the mount point, while the traditional TPA uses the measured force. This simulated force is obtained by numerical analysis for the FE (finite element) model of a powertrain. The interior noise is predicted by multiplying the simulated force by the vibro-acoustic transfer function (VATF) of the vehicle. The VATF is the acoustic response in the compartment of a car to the input force at the mount point of the powertrain in the flexible car body. The trend of the predicted interior noise based on the hybrid TPA very well corresponds to the measured interior noise, although there is some difference due to not only the experimental error and the simulation error but also the effect of the air-borne path.

• 한국해양환경ㆍ에너지학회지
• /
• 제16권3호
• /
• pp.211-216
• /
• 2013

대부분의 사고선박 예인력 계산을 위한 선체저항 성능 추정은 매우 간단하고 오래된 방법을 사용하고 있는데, 특히 바지선의 경우는 미국 해군 예인 매뉴얼에서 사용하는 방법과 유사한 방법을 사용하고 있다. 본 논문에서는 미국 해군 예인 매뉴얼 방법과 국내 해양수산부 고시 방법을 검토한 결과, 이는 비합리적이고 부정확한 추정 방법임을 밝혔다. 나아가, 바지선에 적용할 수 있는 합리적이고도 정확한 저항 성능 추정 방법으로 새로운 Modified-Yamagata-Barge 방법을 도출하였다.

• 대한기계학회논문집A
• /
• 제20권7호
• /
• pp.2257-2265
• /
• 1996

In the cold rolling mill, it is very important that a constrained static flow stress of rolled strip and rolling force calculation model be exactly considered to improve an prediction accuracy for rolling forces. Therefore, in this study, the values of the constrained static flow stress are used by deriving the regression equation which is a function of rolling conditions(FDT, CT) and chemical compositions(C, Si, Mn), previously applied by making the tables of yield strength for hot coils with size. And with the consideration that an elastic deformation part of an rolled strip appears at the entry and delivery side of the contacting area between the work roll and rolled strip is calculated. By applying these methods, the more accurate prediction for rolling force is obtained. As a results, the deviation of thickness is significantly reduced in the rolling direction.

• 콘크리트학회논문집
• /
• 제16권6호
• /
• pp.813-822
• /
• 2004

축하중을 받는 철근콘크리트 부재의 전단강도를 예측하기 위하여, 본 연구에서는 전단력과 축하중 및 휨모멘트를 받는 철근 콘크리트 부재의 전단거동을 예측할 수 있는 변환각 트러스 모델(TATM)을 제안하였다. TATM에서, 축력의 영향을 고려하기 위하여 축압축력이 증가할수록 고정각은 감소하며 균열 방향의 콘크리트 전단저항은 증가한다. TATM의 예측결과가 축력을 받는 철근콘크리트 부재에 대하여 정확성과 신뢰성을 가지는지 검증하기 위하여, 축력을 받는 총 67개의 전단실험 결과를 수집하였으며, TATM 및 기존의 트러스 모델(MCFT, RA-STM FA-STM)과 비교하였다. 수집한 실험결과와 해석결과를 비교한 결과, TATM에 의한 해석결과는 실험결과를 평균 0.95, 변동계수 $12.0\%$로 기존의 트러스 모델보다 더 정확히 예측하였으며, 철근능력비, 축력, 전단경간비 및 압축철근비의 영향을 받지 않았다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 추계학술대회 논문집
• /
• pp.411-415
• /
• 2004

In this paper, a double artificial neural network (ANN) approach and the efficient machining database building scheme are presented for the prediction of surface roughness in high-speed machining. In this approach, 4 machining parameters and used for the prediction of cutting force components, and the combinations of 4 parameters and the predicted cutting force components are finally used for the prediction of surface roughness. The experimental results comparing the these results with the predicted values using simple 4 input nodes have been also investigated to verify the effectiveness of the proposed approach.

• 한국정밀공학회지
• /
• 제15권8호
• /
• pp.116-125
• /
• 1998

In this paper, main target is to select parameters for prediction of tool wear and detection of tool fracture. The research about choosing parameter for prediction of tool wear is done by using force ratios. Also current sensor, tool-dynamometer, and accelerometer are used for researching detection method of tool fracture. Experiment is done using Taguchi's method in medium machining conditions. Parameter which is best for prediction of tool wear and detection of tool fracture by deviation analysis is selected. In this paper, tool wear means flank wear.

• Structural Engineering and Mechanics
• /
• 제54권4호
• /
• pp.741-754
• /
• 2015

This study evaluates prediction models for three EDPs (engineering demand parameters) using data from three symmetrical structures with RC walls designed according to the currently enforced Romanian seismic design code P100-1/2013. The three analyzed EDPs are: the maximum interstorey drift, the maximum top displacement and the maximum shear force at the base of the RC walls. The strong ground motions used in this study consist of three pairs of recordings from the Vrancea intermediate-depth earthquakes of 1977, 1986 and 1990, as well as two other pairs of recordings from significant earthquakes in Turkey and Greece (Erzincan and Aigion). The five pairs of recordings are rotated in a clockwise direction and the values of the EDPs are recorded. Finally, the relation between various IMs (intensity measures) of the strong ground motion records and the EDPs is studied and two prediction models for EDPs are also evaluated using the analysis of residuals.

• 한국전산유체공학회지
• /
• 제13권4호
• /
• pp.80-85
• /
• 2008

The prediction of the separation trajectories of external stores released from a military aircraft is an important task in the aircraft design area having the objective to define the operational and release envelopes. This paper presents the results obtained for store separation by employing commercial softwares, FLUENT and CFD-FASTRAN. FLUENT treats the rigid body motion by employing a remeshing scheme. CFD-FASTRAN uses Chimera(overset) grid and interpolations. It was found that, for the prediction of the trajectories and behavior of the stores separated from the wing, both codes show the good agreement with the experimental results.