• Title/Summary/Keyword: 단조시뮬레이션

Search Result 65, Processing Time 0.025 seconds

Design of Non-monotonic Deterministic Bolzmann Machine Using FPGA (FPGA를 이용한 비단조 DBM 네트워크 설계)

  • 강형원;박철영
    • Proceedings of the Korea Society for Industrial Systems Conference
    • /
    • 2004.06a
    • /
    • pp.3-7
    • /
    • 2004
  • 본 연구에서는 학습기능을 갖는 결정론적 볼츠만 머신에 비단조 뉴런을 이용하여 학습 성능을 수치 시뮬레이션을 통하여 분석한다. 먼저 네트워크의 은닉층에 비단조 및 단조뉴런을 이용한 경우에 대하여 각각 활성화 함수로 시그모이드 함수와 end-cut-off 타입의 비단조함수를 사용한 경우에 대하여 성능을 비교한다. 또한, VHDL을 이용해 설계한 DBM 네트워크에 시그모이드 함수와 end-cut-off 타입의 비단조함수를 사용한 경우에 대하여 시뮬레이션을 통해 수치 시뮬레이션과 성능이 같은지 비교하고 그 유용성을 입증한다.

  • PDF

Finite Element Analysis of Compound Forging Processes (복합단조 공정의 유한요소해석)

  • 전만수;문호근;이민철;서대윤
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 1996.04a
    • /
    • pp.546-550
    • /
    • 1996
  • A fully automatic computer simulation technique of axisymmetric multi-stage compound forging processes was presented in this paper. A penalty rigid-viscoplastic finite element method was employed together with an improved looping method for automatically remeshing with quadrilateral finite-elements only. An application example of six-stage axisymmetric forging processes involving one cold and two hot forging processes, two piercing processes and a sizing process was given with emphasis on automatically tracing the metal flow lines through the whole simulation.

  • PDF

Finite Element Analysis of a Cold forging Process Having a Floating Die (부유금형을 가진 냉간단조 공정의 유한요소해석)

  • 전만수
    • Proceedings of the Korean Society for Technology of Plasticity Conference
    • /
    • 1999.03b
    • /
    • pp.103-107
    • /
    • 1999
  • In this paper, a computer simulation technique for the forging process having a floating die is presented. The penalty rigid-plastic finite element method is employed together with an iteratively force-balancing method, in which the convergence is achieved when the floating die part is in force equilibrium within the user-specified tolerance. The force balance is controled by adjusting the velocity of the floating die in an automatic manner. An application example of a three-stage cold forging process is given.

  • PDF

Simulation of Spider forging Processes and Verification of the Results (스파이더 단조공정의 시뮬레이션 및 결과의 검증)

  • Kim, H.T.;Lee, M.C.;Eom, J.G.;Jun, B.Y.;Joun, M.S.
    • Proceedings of the Korean Society for Technology of Plasticity Conference
    • /
    • 2007.10a
    • /
    • pp.183-188
    • /
    • 2007
  • We simulated a hot forging process for the spider with four legs and an enclosed die forging process for the spider with three legs using an intelligent forging simulator AFDEX 3D and compared the predictions with the experiments in terms of the deformed shape. The formation of characteristic lines was emphasized in the simulation to simulate the extruded legs with higher accuracy.

  • PDF

Model-Based Scheduling Optimization of Hot Press Forging Process for Energy Efficiency (열간 자유 단조 공정의 에너지 효율화를 위한 모형 기반 작업 계획 최적화)

  • Lee, Jeongmi;Kim, Seyoung;Ryu, Kwang Ryel
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2018.10a
    • /
    • pp.641-644
    • /
    • 2018
  • 열간 자유 단조는 고온으로 가열한 강피에 압력을 가하여 원하는 형상을 빚는 공정이다. 가열로에서 여러 개의 강피를 동시에 가열하며 목표 온도에 도달하면 꺼내어 다음 공정을 진행한다. 이때 가열로에 투입하는 소재의 조합과 후단 공정을 위해 소재를 꺼내는 순서가 가열로의 에너지 효율에 영향을 끼친다. 본 논문에서는 열간 자유 단조의 에너지 효율을 높이기 위한 비용 예측 모형 기반 작업 계획 최적화 방안을 제안한다. 유전 알고리즘을 이용하여 가열로 강피 조합을 최적화하며 각 설비별 작업 할당 규칙에 따라 전체 작업 계획을 수립한다. 시뮬레이션 기반으로 후보 작업 계획을 평가하여 계획을 최적화 하며 이를 위해 각 설비별 공정 소요 시간 및 에너지 사용량 예측 모형을 이용한다. 예측 모형은 공정 데이터를 기반으로 기계 학습 알고리즘을 적용하여 학습한다. 또한 주기적인 재계획을 통해 예측의 불확실성으로 인해 작업의 진행이 계획대로 이루어지지 않는 문제점을 해결하고자 한다.

Experimental and Numerical Study on Closed Die Hot Forging of a Large Crankshaft (대형 크랭크샤프트의 형단조에 관한 실험적 및 수치적 연구)

  • Cho, B.J.;Lee, M.C.;Kim, H.T.;Park, T.H.;JeGal, Y.J.;Choi, I.S.;Joun, M.S.
    • Proceedings of the Korean Society for Technology of Plasticity Conference
    • /
    • 2008.05a
    • /
    • pp.263-266
    • /
    • 2008
  • We apply a closed die forging technology to a large crankshaft of which forging weight amounts to 850kg. 40ton counter-blow hammer forging machine is used. The forging process is optimized to reduce the forming load using finite element simulation. AFDEX 3D is used for forging simulation. The experiment is compared with finite element prediction and a good agreement is observed. The successful development of a large crankshaft by the closed die forging technology will contribute to opening a new area of closed-die forging application and to enhancing competitiveness of national machinery industries especially including ship part and power generation industries.

  • PDF

Analysis of Mateiral Flow in Metal Forming Processes by Using Computer Simulation and Experiment with Model Material (소성가공시 재료유동에 대한 수치해석 및 모델실험)

  • 김헌영;김동원
    • Transactions of the Korean Society of Mechanical Engineers
    • /
    • v.17 no.2
    • /
    • pp.285-299
    • /
    • 1993
  • The objective of the present study is to analyze material flow in the metal forming processes by using computer simulation and experiment with model material, plasticine. A UBET program is developed to analyze the bulk flow behaviour of various metal forming problems. The elemental strain-hardening effect is considered in an incremental manner and the element system is automatically regenerated at every deforming step in the program. The material flow behavior in closed-die forging process with rib-web type cavity are analyzed by UBET and elastic-plastic finite element method, and verified by experiments with plasticine. There were good agreements between simulation and experiment. The effect of corner rounding on material flow behavior is investigated in the analysis of backward extrusion with square die. Flat punch indentation process is simulated by UBET, and the results are compared with that of elastic-plastic finite element method.

Prediction of Sink Phenomenon during Forging Process and Improvement of LPI Fuel Filter Housing Forging Product (LPI 차량용 연료필터 상부 하우징 냉간 단조 성형 공정에서 sink 현상 예측 및 개선)

  • Kim, Jun-Young;Park, Sang-Min;Hong, Seokmoo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.6
    • /
    • pp.395-399
    • /
    • 2017
  • The LPI fuel filter housings used in automobiles were made from conventional die castings but have recently been developed by cold forging to improve the weight and durability. On the other hand, a sink may develop at the core of the forged product due to the resulting T-shape, which not only reduces the aesthetics, but also increases the post-processing cost of the product. Therefore, this research focused on methods to predict and mitigate sink development and progression during the T-shape forging process. Finite element analysis of the forging process was first performed to determine the optimal initial workpiece devoid of burrs and underfills. An accurate sink prediction was then obtained via metal flow analysis, which was a result of the finite element simulation. Through finite element analysis, it was confirmed that sink development is a product of the differences in nodal velocities arising from the T-shaped forging process. Consequently, a pad was inserted beneath the sink to minimize these velocity differences. The results yielded significant improvement with regard to the sink defect. This method was practically applied to an industrial site to validate the sink improvement.