• Title/Summary/Keyword: Transition prediction

Search Result 243, Processing Time 0.025 seconds

Task Planning Algorithm with Graph-based State Representation (그래프 기반 상태 표현을 활용한 작업 계획 알고리즘 개발)

  • Seongwan Byeon;Yoonseon Oh
    • The Journal of Korea Robotics Society
    • /
    • v.19 no.2
    • /
    • pp.196-202
    • /
    • 2024
  • The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

Prediction of Urban Land Cover Change Using Multilayer Perceptron and Markov Chain Analysis (다층 퍼셉트론(MLP)과 마코프 체인 분석(MCA)을 이용한 도심지 피복 변화 예측)

  • Bhang, Kon Joon;Sarker, Tanni;Lee, Jin-Duk
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.36 no.2
    • /
    • pp.85-94
    • /
    • 2018
  • The change of land covers in 2026 was prediceted based on the change of urbanization in 1996, 2006 and 2016 in Seoul and surrounding areas in this study. Landsat images were used as the basic data, and MLP (Multilayer Perceptron) and MCA (Markov Chain Analysis) were integrated for future prediction for the study area. The land cover transition potentials were calculated by setting up sub-models in MLP and the driving factors of land cover transition from 1996 to 2006 and transition probabilities were calculated using MCA to generate the land cover map of 2016. This was compared to the land cover map of 2016 from Landsat. MLP and MCA were verified and the future land covers of 2026 were predicted using the land cover map from Landsat in 2006 and 2016. As a result, it was predicted that the major land cover changes from 1996 to 2006 were from Barren Land and Grass Land to Builtup Area, and the same trend of transition will be remained for 2026. This study is meaningful in that it is applied for the first time to predict the future coating change in Seoul and surrounding areas by the MLP-MCA method.

Implementation of Roughness-Induced Turbulent Transition Model on Inflight Icing Code (표면 조도를 고려한 난류 천이 모델의 항공기 결빙 해석자에 대한 적용 연구)

  • Min, Seungin;Yee, Kwanjung
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.48 no.1
    • /
    • pp.23-33
    • /
    • 2020
  • In this study, the effect of surface roughness distribution and its influence on the inflight icing code was investigated. Previous numerical studies focused on the magnitude of surface roughness, and the effects were only addressed in terms of changes in thermal boundary layers with fully turbulent assumption. In addition, the empirical formula was used to take account the turbulent transition due to surface roughness, which was regarded as reducing the accuracy of ice shape prediction. Therefore, in this study, the turbulent transition model based on the two-equation turbulence model was applied to consider the effects of surface roughness. In order to consider the effect of surface roughness, the transport equation for roughness amplification parameter was applied, and the surface roughness distribution model was implemented to consider the physical properties. For validation, the surface roughness, convective heat transfer coefficient, and ice shape were compared with experimental results and other numerical methodology. As a result, it was confirmed that the excessive prediction of the heat transfer coefficient at the leading edge and the ice horn shape at the bottom of the airfoil were improved accordingly.

Validation of Modified Two-Surface Model (수정이중면 모델의 타당성 분석)

  • Kim, Dae-Kyu
    • Proceedings of the KAIS Fall Conference
    • /
    • 2007.05a
    • /
    • pp.276-278
    • /
    • 2007
  • In this study the modified Two-Surface model was validated by comparing the model prediction with the results of the experiments carefully performed. It was seen that the modified Two-Surface model was capable of more realistically simulating the behaviors of clayey specimens, specially over-consolidated specimens. This is attributed mainly to the smooth transition rule from the elastic to elastoplastic regions.

  • PDF

Soil Moisture and Moisture Stress Prediction for Corn in a Western Corn Belt State (미국 옥수수 서부주산지대에서의 토양수분과 작물수분장해 예측연구)

  • Shaw, R.H.
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.28 no.1
    • /
    • pp.1-11
    • /
    • 1983
  • Iowa is in a very interesting position for a climatologist with respect to soil moisture, It is located in a transition zone between humid climates to the east, and dry climates to the west, As a result of this, soil moisture reserves may vary widely from year to year, and even from place to place within a year. A wet situation may prevail where free water can be found in the 5-foot profile and the tile are running.(omitted)

  • PDF

Methodology of a Probabilistic Pavement Performance Prediction Model Based on the Markov Process (확률적 포장 공용성 예측모델 개발 방법론)

  • Yoo, Pyeong-Jun;Lee, Dong-Hyun
    • International Journal of Highway Engineering
    • /
    • v.4 no.4 s.14
    • /
    • pp.1-12
    • /
    • 2002
  • Pavement Management System has a special purpose that the rehabilitation strategy applied on pavement should be executable in view of technical and economical point after new pavement open to the traffic. To achieve that purpose, a reliable pavement performance prediction model should be embeded in the system. The object of this study is to develop a probabilistic pavement performance prediction model for evaluating asphalt pavements based on the Markov chain concept. In this paper, methodology of the Markov chain modeling principle is explained, and the application of this model to asphalt pavement is described. As the results, transition matrics for predicting asphalt pavement performance are obtained, and also performance life is estimated quantitatively by this system.

  • PDF

CFD Analysis of Aerodynamic Characteristics of a BWB UCAV configuration with Transition effect (천이효과를 고려한 BWB UCAV 형상의 공력 특성 전산해석)

  • Jo, Young-Hee;Chang, Kyoungsik;Sheen, Dong-Jin;Park, Soo Hyung
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.42 no.7
    • /
    • pp.535-543
    • /
    • 2014
  • A computational simulation for a nonslender BWB UCAV configuration with rounded leading edge and span of 1.0m was performed to analyze its aerodynamic characteristics. The freestream is 50m/s over -4 to 26 degree A.o.A.s. Reynolds number based on the mean chord length is $1.25{\times}10^6$. 3D multi block hexahedral grids are used which allow good grid quality and ease to capture boundary layer. ${\gamma}-Re_{\theta}$ model as well as $k-{\omega}$ SST model is employed to assess the effect of transition for flow behavior. Drag and lift of the UCAV were well predicted while $C_M$ is under predicted at high angle of attacks and influenced by the turbulence models strongly. After assessing pressure distribution, skin friction lines and velocity field around the UCAV configuration, it was found that transition effect should be considered to enhance the prediction of aerodynamic behavior by a vortical flowfield.

Prediction models of compressive strength and UPV of recycled material cement mortar

  • Wang, Chien-Chih;Wang, Her-Yung;Chang, Shu-Chuan
    • Computers and Concrete
    • /
    • v.19 no.4
    • /
    • pp.419-427
    • /
    • 2017
  • With the rising global environmental awareness on energy saving and carbon reduction, as well as the environmental transition and natural disasters resulted from the greenhouse effect, waste resources should be efficiently used to save environmental space and achieve environmental protection principle of "sustainable development and recycling". This study used recycled cement mortar and adopted the volumetric method for experimental design, which replaced cement (0%, 10%, 20%, 30%) with recycled materials (fly ash, slag, glass powder) to test compressive strength and ultrasonic pulse velocity (UPV). The hyperbolic function for nonlinear multivariate regression analysis was used to build prediction models, in order to study the effect of different recycled material addition levels (the function of $R_m$(F, S, G) was used and be a representative of the content of recycled materials, such as fly ash, slag and glass) on the compressive strength and UPV of cement mortar. The calculated results are in accordance with laboratory-measured data, which are the mortar compressive strength and UPV of various mix proportions. From the comparison between the prediction analysis values and test results, the coefficient of determination $R^2$ and MAPE (mean absolute percentage error) value of compressive strength are 0.970-0.988 and 5.57-8.84%, respectively. Furthermore, the $R^2$ and MAPE values for UPV are 0.960-0.987 and 1.52-1.74%, respectively. All of the $R^2$ and MAPE values are closely to 1.0 and less than 10%, respectively. Thus, the prediction models established in this study have excellent predictive ability of compressive strength and UPV for recycled materials applied in cement mortar.

Statistical analysis on the fluence factor of surveillance test data of Korean nuclear power plants

  • Lee, Gyeong-Geun;Kim, Min-Chul;Yoon, Ji-Hyun;Lee, Bong-Sang;Lim, Sangyeob;Kwon, Junhyun
    • Nuclear Engineering and Technology
    • /
    • v.49 no.4
    • /
    • pp.760-768
    • /
    • 2017
  • The transition temperature shift (TTS) of the reactor pressure vessel materials is an important factor that determines the lifetime of a nuclear power plant. The prediction of the TTS at the end of a plant's lifespan is calculated based on the equation of Regulatory Guide 1.99 revision 2 (RG1.99/2) from the US. The fluence factor in the equation was expressed as a power function, and the exponent value was determined by the early surveillance data in the US. Recently, an advanced approach to estimate the TTS was proposed in various countries for nuclear power plants, and Korea is considering the development of a new TTS model. In this study, the TTS trend of the Korean surveillance test results was analyzed using a nonlinear regression model and a mixed-effect model based on the power function. The nonlinear regression model yielded a similar exponent as the power function in the fluence compared with RG1.99/2. The mixed-effect model had a higher value of the exponent and showed superior goodness of fit compared with the nonlinear regression model. Compared with RG1.99/2 and RG1.99/3, the mixed-effect model provided a more accurate prediction of the TTS.

An Experimental Study on the Transition of Momentum Controlling Hydrogen Jet to Buoyant Jet (운동량제어 수소제트가 부양제트로 천이되는 현상에 대한 실험적 연구)

  • Won, S.H.;Chung, S.H.;Kim, J.S.
    • Transactions of the Korean hydrogen and new energy society
    • /
    • v.16 no.1
    • /
    • pp.1-8
    • /
    • 2005
  • Transition of momentum-controlling hydrogen jet to buoyant jet is experimentally investigated in order to develop a prediction model for the moving trajectory of hydrogen leaked from hydrogen devices. In the experiments, room-temperature helium, that has a similar density to the hydrogen leaked from high pressure tank, is horizontally injected through a 4mm tube and its moving trajectory is visualized by the shadowgraph method. The moving trajectories are found to be parabolic, thereby exhibiting increasing influence of the buoyancy. In analyzing the experimental results, the vertical movement is assumed to be controlled by the buoyancy while the horizontal movement is controlled by the air entrainment caused by the initial momentum. The resealing based on this assumption yields a single curve fitting to the all experimental results.