DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Doo Yong | - |
dc.contributor.advisor | 이두용 | - |
dc.contributor.author | Park, Joon-Hyuk | - |
dc.date.accessioned | 2022-04-15T07:57:52Z | - |
dc.date.available | 2022-04-15T07:57:52Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=949073&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295045 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 기계공학과, 2021.2,[vi, 66 p. :] | - |
dc.description.abstract | Real-time interactive simulation including deformable object has been researched for various engineering applications in the field of medical simulations or computer graphics for instance. Finite element method is a representative method to simulate the behavior of the deformable model accurately. Improvement of accuracy and quality for the simulation is expected with the model composed of dense elements, however, this results in greatly increased computational load and therefore appropriate compromise on the number of elements is required for real-time simulation. Several efficient computational methods, although, using the model or the subspace with smaller DOFs have been proposed, dynamic simulation of model with arbitrary constitutive law including accurate local deformation induced by interaction have not been considered. We, in this paper, propose a method to enhance precision for deformation of dynamic real-time interactive simulation with low-resolution model, through machine learning using a high-resolution model. High-resolution nodal displacements corresponding to low-resolution nodal displacements and velocities are stored in dataset, by applying a series of training external forces to both resolution model with arbitrary constitutive law. Fully connected network is designed, and learns the function to produce the deformation with improved precision from the motion of low-resolution model. Higher resolution deformation is visually rendered with small additional computation time, by applying the learned function to the low-resolution model with less computational load. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Real-time simulation▼aDynamic simulation▼aFinite element method▼aMachine learning▼aDeep learning | - |
dc.subject | 실시간 시뮬레이션▼a동적 시뮬레이션▼a유한요소법▼a기계학습▼a심층학습 | - |
dc.title | Enhancing precision of deformation in real-time interactive simulation using machine learning | - |
dc.title.alternative | 기계학습을 이용하여 실시간 상호작용 시뮬레이션의 변형 정밀도를 증대하는 방법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :기계공학과, | - |
dc.contributor.alternativeauthor | 박준혁 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.