• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2017.11a
• /
• pp.366-368
• /
• 2017

본 연구는 국내 산사태 발생 데이터를 기반으로 시뮬레이션 모델을 머신러닝 기법을 통해 학습시켜 산사태의 토석류 흐름을 구현하는 알고리즘에 대한 연구이다. 전통적인 프로그래밍을 통한 산사태 시뮬레이션 모델 개발을 해당 시스템에 더 많은 고도의 물리학 법칙을 통합 적용시켜 토석류의 흐름을 공학적으로 재현해내는데 중점을 두고 개발이 진행되지만, 본 연구에서 다루는 머신러닝 기법을 통한 산사태 시뮬레이션 모델 개발의 경우 시스템에 입력되는 데이터를 기반으로한 학습을 통하여 토석류 흐름에 영향을 미치는 변수와 파라메터를 산출하고 정의는데 중점을 두고 개발이 진행된다. 본 연구에서 산사태 시뮬레이션 모델 개발에 활용하는 머신러닝 알고리즘은 강화학습 알고리즘으로 기존 산사태 발생 지점을 기반으로 에이전트를 설정해 시간에 따라 시뮬레이션의 각 스텝에서 토석류의 흐름 즉 액션을 환경에 따른 가중치를 기준으로 산정하게 된다. 여기서 환경에 따른 가중치는 시뮬레이션 모델에 정의된 메서드에 따라 산정된다. 시간이 목표값에 도달하여 결과가 출력되면 출력된 결과와 해당 산사태 발생 지점의 실제 산사태 피해 지역 데이터 즉 시뮬레이션 결과 이상치와의 비교를 통하여 시뮬레이션을 평가하게 된다. 이러한 평가는 시뮬레이션 데이터와 실제 데이터간의 유사도 비교를 통해 손실률을 도출하게 되고 이러한 손실률을 경사하강법등의 최적화 알고리즘을 통해 최소화 하여 입력된 데이터를 기반으로한 최적의 토석류 흐름 구현 알고리즘을 도출한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.443-450
• /
• 2009

In an earlier development phase, the simulation technique is one of the key analysis methods for checking the correctness of system's functional requirements. In general, simulation is manually or randomly performed by executing state machine diagrams according to the requirement scenarios. Therefore, simulation is one of the most effort-consuming tasks. In this paper, an automatic simulation technique of state machine diagrams is provided according to the scenarios of the sequence diagrams. It is not easy to generate detailed simulation traces from sequence diagrams due to different abstraction levels between sequence diagrams and state machine diagrams. In order to adjust for different abstraction levels, state machine diagrams and sequence diagrams are transformed into LTS models and compositional analysis and transition reduction are performed. After checking behavior conformance between them, detailed simulation traces for the state machine diagrams are generated. These simulation traces are used not only for performing automatic simulation but also for assisting analyzers to reach a specific system state in order to guide further efficient simulation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.785-788
• /
• 2019

최근 계산과학 분야에서 시뮬레이션을 활발하게 이용하고 있다. 그리고 IT 기술의 발전에 힘입어 이제는 시뮬레이션을 별도의 복잡한 절차 없이 온라인으로 할 수 있게 되었다. LCAODFTLab은 EDISON 플랫폼에서 제공하는 나노물리 분야의 시뮬레이션 프로그램이다. LCAODFTLab은 온라인 환경에서 사용자에 의해 주어진 원자구조에 대한 전자구조 시뮬레이션을 제공한다. 이처럼 실제로 실행하기 어려운 실험을 간단히 행하는 시뮬레이션은 얼마나 정밀하고 복잡한가에 따라 비용이 발생한다. 이러한 비용은 대체로 사용자에게 부담이 되고, 따라서 시뮬레이션의 수행비용을 줄이는 것은 아주 중요한 요소이다. 따라서 본 논문에서는 EDISON 플랫폼 사용자의 데이터와 머신러닝을 활용하여 시뮬레이션 비용을 줄이는 방법을 소개한다. 이를 통해 사용자는 큰 비용을 지불하지 않고 결과를 예측할 수 있고, 대략적인 수행시간을 알 수 있다.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.8 no.4
• /
• pp.41-47
• /
• 2009

This research deals with evaluation of machining accuracy for Parallel Kinematic Machine Tool(PKMT) applied parallel type robot system with high precision and stiffness. For this purpose, machine simulation is carried out to foreknow collision and interference between workpiece and tool. Furthermore, on the basis of machine simulation data, PKMT is manufactured. Machining accuracy such as cylindricity straightness, squareness, parallelism circularity, concentricity pitch error and yaw error, is measured by using coordinate measuring machine. Test piece for evaluation of machining accuracy is designed and manufactured under the standard of ISO 10791-7.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.367-372
• /
• 2003

This paper shows about the machine simulation embodiment when it happened NC equipment and between workpiece and interference collision at 5 axises processing of aircraft parts. And this research has been chosen because of the highest equipment interference occurrence rate at aircraft parts processing of 5 axises horizontal machine. It can verify simulation and machining process through correlation about their dynamic relations. interference, collision as embodied virtual manufacturing system of machining tool, workpiece, and holder etc. that is necessary element in shape of machine tool and function and processing in imagination ball. Also. it verified about interference and collision between NC equipment parts and workpiece, for applied machine simulation to NC Data of actuality aircraft parts of BULKHEAD and FRAME.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.11
• /
• pp.30-35
• /
• 2021

In this study, a machine simulation system was built using the actual scale of an AC-type 5-axis machine tool for mold surface machining that can be used in applications, such as, modeling and machine building, stroke, and collision detection. The validity of the 5-axis machine simulation system was verified by performing tool path generation, post-processing, machine simulation, prototype motion simulation, and an actual cutting experiment. This entire process was intended to activate the 5-axis machining in mold surface machining.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.12
• /
• pp.52-59
• /
• 2004

This paper shows about the machine simulation embodiment when it happens NC equipment and between workpiece and interference in 5 axises machining of aluminium alloy a vehicles parts. And this research has been chosen because of the highest equipment interference occurrence rate at a vehicles parts processing of 5 axises horizontal machine. It can verify simulation and machining process through correlation of their dynamic relations, interference, collision as embodied virtual manufacturing system of machine, workpiece, and holder etc. That is necessary element in shape of machine tool, function and processing in imagination ball. Also, it verifies about interference and collision between NC equipment and workpiece, as it applied machine simulation to NC Data of actuality aircraft parts of BULKHEAD and FRAME. As the result of this study, by removing the equipment interference and collision element which creates NC data, the virtual machine tool it the efficiency of machine process has increased.

• Journal of the Korea Society for Simulation
• /
• v.22 no.1
• /
• pp.77-86
• /
• 2013

Cloud computing is one of the distributed computing environments and utilizes several computing resources. Cloud environment uses a virtual machine to process a requested job. To balance a workload and process a job rapidly, cloud environment uses a provisioning technique and assigns a task with a status of virtual machine. However, a scheduling method for cloud computing requires a definition of virtual machine availabilities, which have an obscure meaning. In this paper, we propose Fuzzy logic driven Virtual machine Provisioning scheduling using Resource Evaluation(FVPRE). FVPRE analyzes a state of every virtual machine and actualizes a value of resource availability. Thus FVPRE provides an efficient provisioning scheduling with a precise evaluation of resource availability. FVPRE shows a high throughput and utilization for job processing on cloud environments.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.47-54
• /
• 2024

The global decrease in traditional energy resources has prompted increasing energy demand, necessitating efforts to replace and optimize energy sources. This study focuses on enhancing energy efficiency in manufacturing plants, known for their high energy consumption. Through simulations and analyses, the study proposes a temperature-based control system for HVAC (Heating, Ventilating, and Air Conditioning) operations, utilizing machine learning algorithms to predict and optimize factory temperatures. The results indicate that this approach, particularly the prediction-based free cooling algorithm, can achieve over 10% energy savings compared to existing systems. This paper presents that implementing an efficient HVAC control system can significantly reduce overall factory energy consumption, with plans to apply it to real factories in the future.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.06a
• /
• pp.153-154
• /
• 2007