• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.10a
• /
• pp.181-182
• /
• 2006

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.2
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2002.05b
• /
• pp.172-173
• /
• 2002

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1202-1206
• /
• 2004

In the future, a machine-tool will be more improved in the form of a knowledge evolution based device. In order to develop the knowledge evolution based machine-tool, this paper proposes the structure of knowledge evolution and the scheme of a dialogue agent among agent-based modules such as a sensory module, a dialogue module, and an expert system. The dialogue agent has a role of interfacing with another machine for cooperation. To design of the dialogue agent module in M2M(Machine To Machine) environment, FIPA-OS and ping agent based on FIPA-OS are analyzed in this study. Through this, it is expected that the dialogue agent module can be more efficiently designed and the knowledge evolution based machine-tool can be hereafter more easily implemented.

• 유체기계공업학회:학술대회논문집
• /
• 2005.12a
• /
• pp.491-496
• /
• 2005

A pump design system was constructed by several integrating in-house programs and commercial softwares to design and evaluate centrifugal pumps. An agent-based prototype framework has been developed for collaborative design and optimization of a centrifugal pump. This paper introduces the feasible technology needed to construct a pump design system based on software agents. The integrated design system, developed in the present study, was used in designing a centrifugal pump and modifying its impeller shape by using optimization processes to increase the pump performance.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2005.05a
• /
• pp.338-339
• /
• 2005

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1357-1360
• /
• 2004

In this paper, a prototype of agent-based engineering system is developed based on the AADE (autonomous agent development environment), a FIPA compliant agent platform. By applying several advanced technologies including software agents, Internet/Web, workflow and database, the developed prototype system is able to successfully fulfill our target of integrating personnel, design activities and engineering resources along a predefined engineering design project (workflow). A software prototype is implemented to integrate various engineering software tools including CAD, structural analysis (FEA), dynamic analysis, fatigue analysis. A wheel-axle-assembly (part of a bogie system) is chosen as a test case for the validation of the prototype system.

• International Journal of Highway Engineering
• /
• v.19 no.1
• /
• pp.1-9
• /
• 2017

PURPOSES : The objective of this study is to develop an optimized method of mix design for rapid-set lightweight-formed mortar mix. To achieve this objective, the workability, setting time, and compressive strength of mixes under various conditions of mix design were evaluated. METHODS : The water-bonder ratio, fly-ash substitution ratio, and forming agent injection amount were selected as design variables in the study. The fluidity, setting time, density, and strength of the mortar mix were considered as major evaluation criteria of the mixture, and were subsequently utilized to evaluate the characteristics of the mortar mix under various conditions. RESULTS : The observations made from the mix design process are as follows: 1) the air content and fluidity increase as the forming agent ratio and forming agent ratio increase, respectively; 2) the maximum air content is approximately 20%; 3) the accelerating agent decreases the fluidity of the mortar mix by 15% on average; 4) the forming agent injection ratio and fly-ash substitution ratio yield significant effects on the initial and final set times of the mortar mix; 5) as the forming agent injection ratio and fly-ash substitution ratio increase, the compressive strength of the mortar mix decreases; and 6) the 28-day compressive strengths of the forming agent injection ratio and fly-ash substitution ratio yield the most significant effects. CONCLUSIONS : It is concluded that the governing design variables for the rapid-set lightweight-formed mortar mix are the forming agent injection ratio and fly-ash substitution ratio.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.862-870
• /
• 2000

Recently, according to the rapid development of internet and communication technologies, a lot of works based on network techniques have been developed. In relation to this trend, the agent systems that had been studied in the early AI have been being studied greatly in association with the network techniques. This paper present a design model of a secretary agent system in which each secretary agent can manage the schedules of her/his superior, and the descriptions about the implementation of the secretary agent system. In the presented secretary agent system, a database system and a knowledge-based systems are included and cooperated with each secretary agent to provide the ability of manipulating lots of schedule data and making decisions on them. This paper also shows that the presented secretary agent system can behavior like a real secretary through the various superior-secretary-meeting-requester interactions, which is different from the roup scheduling programs or personal scheduling programs.

• 연구논문집
• /
• s.34
• /
• pp.113-119
• /
• 2004

Recently, the conventional concept of a machine-tool in manufacturing systems is changing from the target of integration to the autonomous manufacturing device based on a knowledge evolution. Subsequently, a machine-tool has been the subject of a cooperation through an advanced environment where an open architecture controller, high speed network and internet technology are contained In the future, a machine-tool will be more improved in the form of a knowledge evolution based device. In order to develop the knowledge evolution based machine-tool, this paper proposes the structure of knowledge evolution and the scheme of a dialogue agent among agent-based modules such as a sensory module, a dialogue module, and an expert system. The dialogue agent has a role of interfacing with another machine for cooperation. To design of the dialogue agent module in M2M(Machine To Machine)environment, FIPA-OS and ping agent based on FIPA-OS are analyzed in this study. Through this, it is expected that the dialogue agent module can be more efficiently designed and the knowledge evolution based machine-tool can be hereafter more easily implemented.