• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.5904-5927
• /
• 2019

Many artificial intelligence (AI) techniques have been embedded into various engineering technologies to assist them in achieving different goals. The integration of modern technologies with energy consumption management system and occupant's comfort inside buildings results in the introduction of intelligent building concept. The major aim of this integration is to manage the energy consumption effectively and keeping the occupant satisfied with the internal environment of the building. The last few couple of years have seen many applications of AI techniques for optimizing the energy consumption with maximizing the user comfort in smart buildings but still there is much room for improvement in this area. In this paper, a hybrid of two AI algorithms called firefly algorithm (FA) and genetic algorithm (GA) has been used for user comfort maximization with minimum energy consumption inside smart building. A complete user friendly system with data from various sensors, user, processes, power control system and different actuators is developed in this work for reducing power consumption and increase the user comfort. The inputs of optimization algorithms are illumination, temperature and air quality sensors' data and the user set parameters whereas the outputs of the optimization algorithms are optimized parameters. These optimized parameters are the inputs of different fuzzy controllers which change the status of different actuators according to user satisfaction.

• Smart Structures and Systems
• /
• v.23 no.1
• /
• pp.91-106
• /
• 2019

Adopting sloped rolling-type isolation devices underneath a raised floor system has been proved as one of the most effective approaches to mitigate seismic responses of the protected equipment installed above. However, pounding against surrounding walls or other obstructions may occur if such a base-isolated raised floor system is subjected to long-period excitation, leading to adverse effects or even more severe damage. In this study, real-time hybrid simulation (RTHS) is adopted to assess the control performance of a smart base-isolated raised floor system as it is an efficient and cost-effective experimental method. It is composed of multiple sloped rolling-type isolation devices, a rigid steel platen, four magnetorheological (MR) dampers, and protected high-tech equipment. One of the MR dampers is physically tested in the laboratory while the remainders are numerically simulated. In order to consider the effect of input excitation characteristics on the isolation performance, the smart base-isolated raised floor system is assumed to be located at the roof of a building and the ground level. Four control algorithms are designed for the MR dampers including passive-on, switching, modified switching, and fuzzy logic control. Six artificial spectrum-compatible input excitations and three slope angles of the isolation devices are considered in the RTHS. Experimental results demonstrate that the incorporation of semi-active control into a base-isolated raised floor system is effective and feasible in practice for high-tech industry.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.819-826
• /
• 2001

Genetic algorithms are becoming more popular because of their relative simplicity and robustness. Genetic algorithms are global search techniques for nonlinear optimization. However, traditional genetic algorithms, though robust, are generally not the most successful optimization algorithm on any particular domain because they are poor at hill-climbing, whereas simulated annealing has the ability of probabilistic hill-climbing. Therefore, hybridizing a genetic algorithm with other algorithms can produce better performance than using the genetic algorithm or other algorithms independently. In this paper, we propose an efficient hybrid optimization algorithm named the adaptive random signal-based learning. Random signal-based learning is similar to the reinforcement learning of neural networks. This paper describes the application of genetic algorithms and simulated annealing to a random signal-based learning in order to generate the parameters and reinforcement signal of the random signal-based learning, respectively. The validity of the proposed algorithm is confirmed by applying it to two different examples.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2009.04a
• /
• pp.433-436
• /
• 2009

본 연구에서는 준능동 TMD(STMD)가 설치된 초고층건물의 풍응답을 효과적으로 저감시키기 위한 퍼지 하이브리드제어기법을 제안하였다. 이를 위하여 STMD의 응답저감에 우수한 성능을 보이는 스카이훅(skyhook) 제어기와 구조물의 응답저감에 뛰어난 그라운드훅(groundhook) 제어알고리즘을 사용하였다. 본 연구에서는 두 제어기를 적절히 조합하기 위하여 최적의 가중치를 실시간으로 결정하는 퍼지 하이브리드제어기를 개발함으로써 일반적인 가중합방식의 하이브리드 제어기법의 성능을 개선하였다. 제안된 제어기의 성능을 검토하기 위하여 풍하중을 받는 76층 사무소 건물을 예제구조물로 사용하였다. MR 감쇠기를 이용하여 STMD를 구성하였고 STMD의 제어성능을 평가하기 위하여 TMD 및 ATMD의 성능과 비교하였다. 수치해석을 통하여 STMD의 제어성능이 TMD에 비하여 월등히 뛰어남을 확인할 수 있었다. 또한 퍼지 하이브리드 제어기법을 사용하면 스카이훅 및 그라운드훅 제어기를 효과적으로 조합하여 STMD와 건물의 응답을 동시에 줄일 수 있음을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.650-652
• /
• 2004

본 논문에서는 간접 벡터 제어 방식의 유도전동기를 위한 하이브리드 퍼지 속도제어기를 설계한다. 제안한 하이브리드 퍼지 속도제어기는 유도 전동기의 속도 응답 성능을 향상시키기 위하여 응답 상태에 따라 PI(비계적분) 제어기와 퍼지 제어기를 선택하여 사용하는 형태이다. 정상상태에서는 PI 제어기를 사용하고 속도 오차값이 크면 퍼지 제어기를 사용한다. 또한 사용된 퍼지 제어기는 퍼지 입력의 파라미터를 튜닝하여 응답 성능을 높였다. 본 논문에서 제안한 하이브리드 퍼지속도 제어기와 기존의 PI 제어기의 성능을 실험을 통하여 비교 검증한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.185-188
• /
• 2007

본 논문은 하이브리드용 자동차의 리튬 이온 전지의 사이클 라이프에 따른 용량의 감소를 예측하고 잔량을 예측하기 위한 지능형 스마트 모듈의 설계를 제안한다. 리튬 이온 전지는 충 방전 횟수에 따라 전하를 담을 수 있는 용량이 감소하고, 방전 전압이 비선형이므로 정확한 잔량 예측이 어렵다. 따라서, 지능형 스마트 모듈은 전압과 전류, 온도의 측정을 위한 데이터 수집 장치를 제작하고 퍼지 로직을 이용한 잔량 측정 알고리즘을 통해 정확도가 높은 리튬 이온 전지의 잔량을 예측하고, 충 방전 실험 값과 퍼지 로직을 이용한 결과 값의 비교를 통해 그 효용성을 보인다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.585-590
• /
• 1998

The purpose of this paper is to develop a neurofuzzy modeling & inference system which can determine principle dimensions and hull factors in an initial ship design. Neurofuzzy modeling & inference for a hull form design (NeFHull) applies the given input-output data to the fuzzy theory. NeFHull also deals the fuzzificated values with neural networks. NeFHull redefines normalized input-output data as membership functions and executes the fuzzficated information with backporpagation-neural -networks. A hybrid learning algorithms utilized in the training of neural networks and examining the usefulness of suggested method through mathematical and mechanical examples.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.1
• /
• pp.73-82
• /
• 2013

In pattern classification, feature selection is an important factor in the performance of classifiers. In particular, when classifying a large number of features or variables, the accuracy and computational time of the classifier can be improved by using the relevant feature subset to remove the irrelevant, redundant, or noisy data. The proposed method consists of two parts: a wrapper part with an improved genetic algorithm(GA) using a new reproduction method and a filter part using mutual information. We also considered feature selection methods based on mutual information(MI) to improve computational complexity. Experimental results show that this method can achieve better performance in pattern recognition problems than other conventional solutions.

• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.489-490
• /
• 2011

본 논문에서는 병렬형 하이브리드 자동차 (PHEV) 파워트레인 구성요소 정격설계와 내연기관의 최적 운전을 위한 퍼지논리제어에 대하여 기술한다. 내연기관, 전동기, Energy Storage System (ESS)과 같은 파워트레인 구성요소들의 정격은 에너지 개념과 Electrical Peaking Hybrid (ELPH)를 이용하여 설계 하였으며 내연기관의 운전효율을 증가시키기 위해 퍼지논리를 사용하여 파워트레인의 전력흐름을 제어하였다. 제안된 퍼지논리는 설계된 구성요소 정격값을 바탕으로 PHEV PSIM 시뮬레이터를 구성하고 시뮬레이션 하여 그 효용성을 분석하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.852-855
• /
• 1995

In modern plant lndustry, dignosis system is an essential implement because a human operator cannot check the state of system all the time. The recent facility needs a computer system which is able to replace and extense the function of the human expert. Checking the state of the plant system, the computer system uses signals form sensors attached to the plant systems. But, It is difficult to predict the cause of the failure from the sensing signals. Because the relationship among the signals cannot be easily represented by mathematical models. So expert system based on a fuzzy rule and Neural network method is sugguested. Expert system decide whether aa state of the system is ordinary of failure by the evaluation of the signals. If the state of the system is unstable, expert system preprocess the signals. When fault is occurred in the machine, the expert system dignoses the state of the system and find the cause as a primary tool. If the expert system dose not find the adequate cause successfully, neural network system uses the preprocessed signals as an input and propose a cause of the failure.