• 한국신뢰성학회지:신뢰성응용연구
• /
• 제10권1호
• /
• pp.39-56
• /
• 2010

Statistical process control (SPC) is a powerful technique for monitoring, managing, analysing and improving the process performance. However, its has limitations such as lack of engineering, statistical skill and training, and lesser importance of activity. To solve the problems, this study proposes an intelligent SPC system using specified agents which are derived through analysis and evaluation of the SPC activities. The activities investigated by the relevant researches are categorized as collection, process analysis, diagnosis, detection, cause analysis and rule generation. Also, the evaluation criteria are established as feasibility of automation, frequency, level and time. The requirements of the agent functions are derived by the evaluation, and the types of customized agents are as data collection, store, analysis, diagnosis, monitoring, alarm and reporting. A prototype SPC system represents that the functions of the proposed agents are successfully validated.

• 자원리싸이클링
• /
• 제25권5호
• /
• pp.44-49
• /
• 2016

배연탈황기술은 화력발전소에 발생하는 $SO_2$ 가스를 제거하기 위한 효과적인 방법이며, 흡수제로 석회석을 사용하고 있다. 본 연구에서는 천연자원인 석회석의 사용량을 저감하고 산업 폐기물의 재활용을 위해, 제철소에서 발생하는 석회석 슬러지를 흡수제로 사용하고자 하였다. 흡수제 원료의 물리 화학적 특성분석을 실시하였으며, 전처리 설비를 구축하여 석회석 슬러지를 사용한 흡수제를 제조한 후 배연탈황 공정에 적용하였다. 제조 흡수제 적용 결과, $SO_2$ 농도 변화상에서의 경향성은 나타나지 않았으며, 흡수탑에서의 운전 제어를 통해 석회석 슬러지를 흡수제로 사용 가능할 것으로 사료되었다.

• 제어로봇시스템학회논문지
• /
• 제5권7호
• /
• pp.848-854
• /
• 1999

In this paper, we designed and implemented a precise pulse motor controller chip that generates the pulse needed to control step motor, DC servo and AC servo motors. This chip generates maximum pulse output rate of 5Mpps and has the quasi-S driving capability and speed and moving distance override capability during driving. We designed this chip with VHDL and executed a logic simulation and synthesis using Synopsys tool. The pre-layout simulation and post-layout simulation was executed by Compass tool. This chip was produced with 100 pins, PQFP package by 0.8${\mu}{\textrm}{m}$ gate array process and implemented by completely digital logic. We developed the test hardware board of performance and the CAMC(Computer Aided Motor Controller) Agent softwate to test the performance of the pulse motor controller chip produced. CAMC Agent enables user to set parameters needed to control motor with easy GUI(Graphic User Interface) environment and to display the output response of motor graphically.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.328-331
• /
• 1995

A successful, computer-aided design support system can help a process designer focus on making effective design decisions, not merely tedious routine calculations. Such a system is essential to enhance quality of design in terms of economics, environmental benignity, reliability, robustness, and operability. Such a statement is even more accepted when applied to conceptual design problems, where gross design specifications are given while a combinatorial number of design alternatives exists. This paper presents an agent-based approach as a systematic and efficient way to design a design support system for the synthesis of conceptual chemical processes. An agent-based approach allows us to handle design knowledge as an object and thus greatly improve the modularity and reusability of that knowledge. Such modularity and reusability lead to the increased productivity in the development of a design support system and the increased ease in the relaxation of design decisions and the generation of design alternatives, both of which functions are critically important in dealing with the complexity and uncertainty of conceptual design problems.

• 환경위생공학
• /
• 제15권3호
• /
• pp.24-30
• /
• 2000

In this study, to determine the optimum fermentation process for the feed production of food wastes and estimate the practical value of fermented feed using kudzu creeper and sawdust as bulking agent. This study considered initial C/N ratio control as the fermentation process variables. The result are summarized as follows. Minimum water contents of byproducts in the fermentation feed production showed 39%(kudzu), 37%(sawdust) at the C/N ratio 25 and 45%(kudzu, sawdust) at the C/N ratio 35. Temperature variations in the fermentation feed production at the C/N ratio 25 indicated $68^{\circ}C$(kudzu), $70^{\circ}C$(sawdust). Optimum condition of fermentation process of water content, C/N ratio and permeability (porous structure of the mixture). For optimum fermentation gravitationally dewatered garbage, the proper mixing ratios of kudzu(moisture contents : 17.3%) and sawdust(moisture contents : 13.2%) were 41% and 39%, respectively. Major biological reaction in the aerobic fermentation feed production occurred during 12~24hrs.

• 한국공간구조학회논문집
• /
• 제21권2호
• /
• pp.41-48
• /
• 2021

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권11호
• /
• pp.1047-1058
• /
• 2005

본 논문에서는 에이전트 지식 기반 화상회의 시스템의 유연성(flexibility)을 개선하기 위해서 기존의 서비스 조정 부분을 새롭게 설계한 전략적 지식 에이전트 아키텍처(Strategic-INTER Knowledge Architecture)를 제안한다. 제안한 아키텍처는 서비스 품질에 관한 문제에 있어서 발생한 문제의 성질이나 문제해결의 진행상황을 고려하면서 해결전략을 동적으로 변환하여 유연성 있게 해결한다 여기에서 유연성이란 시스템 내부에서 발생한 변동의 대응 및 이용자가 사용하기 편리한 서비스 제공 능력을 말한다. 한편, 제안 아키텍처를 화상회의 시스템에 적용한다. 본 아키텍처 적용에 의해서 화상회의 시스템의 에이전트 간 협조가 효과적으로 실행되었으며, 이전의 화상회의 시스템에 비해서 제약조건이 강화 된 경우에도 시스템의 유연한 대응이 가능하게 되었음을 제시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.35.3-35
• /
• 2002

Reinforcement Learning (RL) is one of machine learning methods and an RL agent autonomously learns the action selection policy by interactions with its environment. At the beginning of RL research, it was limited to problems in environments assumed to be Markovian Decision Process (MDP). However in practical problems, the agent suffers from the incomplete perception, i.e., the agent observes the state of the environments, but these observations include incomplete information of the state. This problem is formally modeled by Partially Observable MDP (POMDP). One of the possible approaches to POMDPS is to use historical nformation to estimate states. The problem of these approaches is how t..

• 한국산업융합학회 논문집
• /
• 제25권2_2호
• /
• pp.199-208
• /
• 2022

The steel wire or steel bar processing process applied to the manufacture of various bolts and power transmission shafts was improved by applying in-line phosphate film treatment technology. By applying a polymer lubricant for a non-reactive metal forming process and a non-reactive non-phosphorus lubricating coating agent, the film formation for each process time was comparatively analyzed and reviewed. Compared to the nine processes applied previously, the in-line phosphate film treatment technology applied with only two processes has been effectively improved in terms of reduction of treatment time, reduction of facility installation area, prevention of water pollution due to wastewater, and non-use of ozone-depleting substances. In addition, it was found that it can have an important effect on productivity improvement and price competitiveness from the simplification of quality control and process control as well as improvement of the working environment.

• 로봇학회논문지
• /
• 제17권1호
• /
• pp.76-85
• /
• 2022

One of the most fundamental challenges when designing controllers for dynamic systems is the adjustment of controller parameters. Usually the system model is used to get the initial controller, but eventually the controller parameters must be manually adjusted in the real system to achieve the best performance. To avoid this manual tuning step, data-driven methods such as machine learning were used. Recently, reinforcement learning became one alternative of this problem to be considered as an agent learns policies in large state space with trial-and-error Markov Decision Process (MDP) which is widely used in the field of robotics. However, on initial training step, as an agent tries to explore to the new state space with random action and acts directly on the controller parameters in real systems, MDP can lead the system safety-critical system failures. Therefore, the issue of 'safe exploration' became important. In this paper we meet 'safe exploration' condition with Control Barrier Function (CBF) which converts direct constraints on the state space to the implicit constraint of the control inputs. Given an initial low-performance controller, it automatically optimizes the parameters of the control law while ensuring safety by the CBF so that the agent can learn how to predict and control unknown and often stochastic environments. Simulation results on a quadrotor UAV indicate that the proposed method can safely optimize controller parameters quickly and automatically.