• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.120-125
• /
• 2013

This paper proposes a goal oriented action planning method that plans the behaviors of computer generated forces and a replanning method that replans new actions when the situations are changed in war game. This new method provides good expression because it is flexible and can do more realized description unlike the conventional finite state machines. As a result, proposed method has an advantage that it can describe the behaviors of computer generated forces as those of real soldier. However, since it is not deterministic it has some difficulties in analysing the decision processing of behaviors and making the computer generated forces do some specific actions. We employed combat plane models of air forces in order to verify the feasibility of our method. Finally, we could find that our method produced very similar behaviors to those of a real soldier. This paper describes our planning method, experimental results, and future works.

• Journal of the Society of Naval Architects of Korea
• /
• v.33 no.4
• /
• pp.142-149
• /
• 1996

Pyramid type three roll bending machines are widely used in roll-bending process to produce singly curved plate. In forming singly curved plate, controlling the vertical displacement of the center roller is most important to acquire the shape required and automation system of the process. In this paper roller bending process is modeled as an elastic-plastic phenomenon and analyzed using beam theory and finite element method. In finite element analysis the workpiece is modeled by using beam elements and plane strain elements respectively. Through the analyses vertical center roller displacement is obtained to get constant curvature distribution along arc length. The relationship between center roller displacement and curvature in steady state as well as residual stress and strain along plate thickness direction are calculated through finite element analysis.

• Korean Journal of Cognitive Science
• /
• v.16 no.4
• /
• pp.351-368
• /
• 2005

The manual construction of the knowledge-base takes much time and effort, and it is hard to adjust intelligence systems to dynamic and flexible environment. Thus mental development in those systems has been investigated in recent years. Autonomous mental development is a new paradigm for developing autonomous machines, which are adaptive and flexible to the environment. Learning conversation, a kind of mental development, is an important aspect of conversational agents. In this paper, we propose a learning conversation method for conversational agents which uses several promising techniques; speech-act templates and genetic programming. Knowledge acquisition of conversational agents is implemented by finite state machines and templates, and dynamic sentence generation is implemented by genetic programming Several illustrations and usability tests how the usefulness of the proposed method.

• International Journal of Automotive Technology
• /
• v.4 no.2
• /
• pp.87-94
• /
• 2003

Recent advancements of permanent magnet (PM) materials and solid-state devices have contributed to a substantial performance improvement of permanent magnet machines. Owing to the rare-earth PMs, these motors have higher efficiency, power factor, output power per mass and volume, and better dynamic performance than induction motors without sacrificing reliability. Not surprisingly, they are continuously receiving serious considerations for a variety of automotive and propulsion applications. An electric vehicle (EV) requires a high-effficient propulsion system having a wide operating range and a capability of generating a high peak torque for short durations. The improvement of torque-speed performance for these systems is consequently very important, and researches in various aspects are therefore being actively pursued. A great emphasis has been placed on the efficiency and optimal utilization of PM machines. This requires attention to many aspects related to the machine design and overall performance. In this respect, the prediction of iron losses is particularly indispensable and challenging, especially for drives with a deep field-weakening range. The objective of this paper is to present iron loss estimations of a PM motor over a wide speed range. As aforementioned, in EV applications core losses can be significant during high-speed operation and it is imperative to evaluate these losses accurately and take them into consideration during the motor design stage. In this investigation, the losses are predicted by using an analytical model and a 2D time-stepped finite element method (FEM). The results from different analytical approaches are compared with the FEM computations. The validity of each model is then evaluated by these comparisons.

• The KSFM Journal of Fluid Machinery
• /
• v.11 no.5
• /
• pp.50-56
• /
• 2008

Metal cutting operations involve generation of heat due to friction between the tool and the pieces. This heat needs to be carried away otherwise it creates white spots. To reduce this abnormal heat cutting fluid is used. Cutting fluid also has an important role in the lubrication of the cutting edges of machine tools and the pieces they are shaping, and in sluicing away the resulting swarf. As a cutting fluid, water is a great conductor of heat but is not stable at high temperatures, so to improve stability an emulsion type mixed fluid with water and oil is often used. It is pumped over the cutting site of cutting machines as a state of atomized water droplet coated with oil by using jet. In this paper, to develop cutting fluid supplying nozzle to obtain ultra thin oil film for coating water droplet, a numerical analysis of three dimensional mixed fluid Jet through multi-stage nozzle was carried out by using a finite volume method. Jet flow characteristics such as nozzle exit velocity, development of mixing region, re-entrance and jet intensity were analyzed. Detailed mixing process of fluids such as air, water and oil in the nozzle were also investigated. It is easy to understand complex flow pattern in multi-stage nozzle. Important flow Information for advance design of cutting fluid supplying nozzle was drawn.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.3
• /
• pp.48-54
• /
• 2000

This paper exploits the use of don't cares on software synthesis for embedded systems. Embedded systems have extremely tight real-time and code size constraints. We propose applying BDD minimization techniques in the presence of a don't care set to synthesize code for extended Finite State Machines from a BDD-based representation of the FSM transition function. The don't care set can be derived from local analysis as well as from external information. We show experimental results, discuss their implications, the interactions between BDD-based minimization and dynamic variable reordering, and propose directions for future research.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.7
• /
• pp.356-371
• /
• 2001

본 논문에서는 비동기식 상위수준합성기 제작의 일환으로 효율적인 비동기식 제어부의 자동생성에 관한 방법을 제안한다. 제안된 방법은 목적시스템의 사양으로써 주어진 제어데이터흐름그래프로부터 일련의 체계적인 변환과정을 통하여, 제어부를 구성할 제어회로들에 대응하는 계층적으로 분할된 비동기식 유한상태기들의 집합을 유도한다. 유도된 비동기식 유한상태기들은 현존하는 비동기식 제어회로 합성기를 통하여 해저드 없는 비동기식 제어회로들로 합성되며, 이들은 상호간에 4단계 핸드셰이킹에 기반한 신호교환을 통하여 동작하면서 전체 시스템을 제어하는 계층적으로 분할된 비동기식 제어부를 구성한다. 획득한 제어부는 계층.분산적이며, 면적, 성능 및 합성시간의 측면에서 기존방식을 통하여 생성한 제어부에 비해 우월하다.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.11
• /
• pp.951-956
• /
• 2014

Steady-state thermal analysis was performed on a thermal equivalent circuit to determine the heat generation during operation of an interior permanent magnet synchronous motor (IPMSM). New machines must be compact and light and produce high torque density under extreme environmental conditions. Thermal analysis of an IPMSM is particularly important because excessive heat generated from the core and magnet reduces the IPMSM's output and has adverse effects on the durability. Therefore, steady-state thermal analysis of an IPMSM was performed for changes in the design variables using a thermal equivalent circuit. The changed variables were the axis length and thickness of the housing. The results of this method were compared with those of the finite element method to verify the accuracy and reliability.

• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.165-177
• /
• 2008

An important issue in Multiagent reinforcement learning is how an agent should learn its optimal policy in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for Multiagent reinforcement learning tend to apply single-agent reinforcement learning techniques without any extensions or require some unrealistic assumptions even though they use explicit models of other agents. In this paper, a Naive Bayesian based policy model of the opponent agent is introduced and then the Multiagent reinforcement learning method using this model is explained. Unlike previous works, the proposed Multiagent reinforcement learning method utilizes the Naive Bayesian based policy model, not the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper, the Cat and Mouse game is introduced as an adversarial Multiagent environment. And then effectiveness of the proposed Naive Bayesian based policy model is analyzed through experiments using this game as test-bed.