• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.451-458
• /
• 2006

The goal of many researchers in the field of structural engineering is to reduce both damage to building structures and discomfort of their inhabitants during strong motion seismic events. The present paper reports on analytical work conducted with this aim in mind as a prior research of experimental study. A four-story, 6.4 m tall, laboratory model of a building is employed as a example structure. The laboratory structure has graphite epoxy columns and each floor is equipped with a chevron brace that serves to resist inter-story drift with the installation of a magnetorheological (MR) damper. An artificial excitation has been generated with a robust range of seismic characteristics. A series of numerical simulations demonstrates that an optimized fuzzy controller is capable of robust performance for a variety of seismic base motions. Optimization of the fuzzy controller is achieved using multi-objective genetic algorithm(MOGA), i.e. NSGA-II. Multiple objective functions are used in order to reduce both peak and root-means-squared displacement and accelerations at the floor levels of the building.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.317-320
• /
• 2008

본 논문에서는 Type-1 퍼지 논리 시스템과 Type-2 퍼지 논리 시스템을 설계하고, 불확실한 정보를 갖는 입력 데이터에 대하여 각각의 성능을 비교한다. Type-1 퍼지 논리 시스템은 외부잡음에 민감한 단점을 가지고 있는 반면, Type-2 퍼지 논리 시스템은 불확실한 정보를 잘 표현할 수 있으며 효율적으로 취급한다. 따라서 Type-2 퍼지 논리 시스템을 이용하여 이러한 단점을 극복하고자 2가지의 모델을 설계한다. 첫 번째 모델은 규칙의 전 ${\cdot}$ 후반부가 불확실성을 표현 할 수 없는 Type-1 퍼지 집합으로 구성된 Type-1 퍼지 논리 시스템을 설계한다. 두 번째는 규칙 후반부만 Type-2 퍼지 집합으로 구성한 두가지의 Type-2 퍼지 논리 시스템을 설계한다. 여기서 규칙 전반부의 입력 공간 분할에는 Min-Max 방법의 균등분할을 사용하고, 규칙 후반부 멤버쉽 함수의 중심 결정에는 입자 군집 최적화(Particle Swarm Optimization) 알고리즘을 사용하여 동정한다. 또한 입력 데이터에 인위적으로 가하는 노이즈의 정도에 따른 각각 모델의 성능을 비교한다. 마지막으로 비선형 모델 평가에 주로 사용되는 가스로 시계열 데이터를 제안된 모델에 적용하고, 실험을 통하여 불확실한 정보를 다루기에 Type-1 퍼지 논리 시스템 보다 Type-2 퍼지 논리 시스템이 효율적이라는 것을 보인다.

• Environmental Engineering Research
• /
• v.25 no.4
• /
• pp.545-553
• /
• 2020

Rainfall-Runoff modeling plays a crucial role in various aspects of water resource management. It helps significantly in resolving the issues related to flood control, protection of agricultural lands, etc. Various Machine learning and statistical-based algorithms have been used for this purpose. These techniques resulted in outcomes with an acceptable rate of success. One of the pertinent machine learning algorithms namely Adaptive Neuro Fuzzy Inference System (ANFIS) has been reported to be a very effective tool for the purpose. However, the computational complexity of ANFIS is a major hindrance in its application. In this paper, we resolved this problem of ANFIS by incorporating one of the evolutionary algorithms known as Particle Swarm Optimization (PSO) which was used in estimating the parameters pertaining to ANFIS. The results of the modified ANFIS were found to be satisfactory. The performance of this modified ANFIS is then compared with conventional ANFIS and another popular statistical modeling technique namely ARIMA model with respect to the forecasting of runoff. In the present investigation, it was found that proposed PSO-ANFIS performed better than ARIMA and conventional ANFIS with respect to the prediction accuracy of runoff.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.188-193
• /
• 2000

This paper presents an approach to obtain a reduced neuro-fuzzy model for a plant. The Neuro-Fuzzy Network are compose of the Radial Basis Function Networks with Gausis membership and learned by using temporal back propagation. The dependency in rough set theory is used to eliminate rules. Dependency between the condition membership value of each rule in a model and the output of the plant can allow us to see how much contribution the rule is to identify the plant. While the reduced model maintains the same performance as the original one, the selection algorithm can minimize its complexity and redundancy of the structure.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.4 s.304
• /
• pp.25-34
• /
• 2005

We had research to conduct interrelationships between sensors using postprocessing analysis with the Fuzzy-Kalman Filtering Auto-Correlation about Real Time Simulator data of the NaroSC LCS in case of a fully blind situation scenario. The conducted interrelations are same harmony with relations in scenario. We had analyzed signals of sensors reverse-using a optimization character of Fuzzy-Kalman Filter. As our research conclusion, We had recognized possibilities of signal processing about the KSLV-1, on-board payloads, general equipments of ground support which apply to multi sensor systems.

• The Journal of Information Technology
• /
• v.5 no.4
• /
• pp.73-79
• /
• 2002

In this paper, I will propose the Niche-Meta Genetic Algorithm that has a multi-mutation operator for design of fuzzy controller. The gene in the proposed algorithm is formed by several parameters that represent the crossover rate, mutation rate and input-output membership functions. The optimization of fuzzy membership function is performed with local search on sub-population and the optimal structure is constructed with global search on total-population. The multi-mutation is selected under basis of the result of local evolution. A simulation for 2 D.O.F wheeled-mobile robot is showed to prove the efficiency of the proposed algorithm

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.419-424
• /
• 2019

The FCM algorithm finds the optimal solution through iterative optimization technique. In particular, there is a difference in execution time depending on the initial center of clustering, the location of noise, the location and number of crowded densities. However, this method gradually updates the center point, and the center of the initial cluster is shifted to one side. In this paper, we propose a TI-FCM(Triangular Inequality-Fuzzy C-Means) clustering algorithm that determines the cluster center density by maximizing the distance between clusters using triangular inequality. The proposed method is an effective method to converge to real clusters compared to FCM even in large data sets. Experiments show that execution time is reduced compared to existing FCM.

• Smart Structures and Systems
• /
• v.23 no.2
• /
• pp.155-171
• /
• 2019

In this study, Semi-active Tuned Mass Dampers (STMDs) are employed in order to cover the prevailing uncertainties and promote the efficiency of the Tuned Mass Dampers (TMDs) to mitigate undesirable structural vibrations. The damping ratio is determined using type-1 and type-2 Fuzzy Logic Controllers (T1 and T2 FLC) based on the response of the structure. In order to increase the efficiency of the FLC, the output membership functions are optimized using genetic algorithm. The results show that the proposed FLC can reduce the sensitivity of STMD to excitation records. The obtained results indicate the best operation for T1 FLC among the other control systems when the uncertainties are neglected. According to the irrefutable uncertainties, three supplies for these uncertainties such as time delay, sensors measurement noises and the differences between real and software model, are investigated. Considering these uncertainties, the efficiencies of T1 FLC, ground-hook velocity-based, displacement-based and TMD reduce significantly. The reduction rates for these algorithms are 12.66%, 26.43%, 20.98% and 21.77%, respectively. However, due to nonlinear behavior and considering a range of uncertainties in membership functions, T2 FLC with 7.2% reduction has robust performance against uncertainties compared to other controlling systems. Therefore, it can be used in actual applications more confidently.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.97-98
• /
• 2008

본 논문에서는 다중 출력을 가지는 퍼지 관계 기반 퍼지뉴럴네트워크를 설계한다. 퍼지 관계 기반 퍼지뉴럴네트워크는 선체 인력 변수에 따른 입력 공간을 분할함으로서 네트워크를 구성한다. 규칙의 전반부는 앞서 언급한 전체 입력 공간을 분할하여 표현하고, 규칙의 후반부는 다항식으로서 표현되며 오류역전파 알고리즘을 이용하여 연결가중치인 후반부 다항식을 학습한다. 또한, 각 입력에 대만 전반부 멤버쉽함수의 정점과 학습률 및 모멤텀 계수를 유전자 알고리즘을 이용하여 최적 동조한다. 따라서 유전자 알고리즘을 이용하여 퍼지뉴럴네트워크를 최적 설계한다. 마지막으로 제안된 모델은 표준 모델로서 널리 사용되는 수치적인 예를 통하여 평가한다.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.95-96
• /
• 2008

본 논문에서는 시계열 예측 공정의 모델링을 위해 Type-2 퍼지 논리 집합을 이용하여 불확실성 문제를 다룬다. 기존의 Type-1 퍼지 논리 시스템(Fuzzy Logic System, FLS)은 외부의 노이즈와 같은 불확실성에 민감한 단점이 있다. 그러나 Type 퍼지 논기 시스템은 불확실한 정보까지 멤버쉽 함수로 표현함으로서 효과적으로 취급할 수 있다. 여기서 불확실한 정보를 표현하기 위해 규칙의 전 후반부 멤버쉽 함수로 삼각형 형태의 Type-2 퍼지 집합을 사용한다. 전반부의 경우 HCM 클러스터링을 사용하여 입력 데이터들 간의 거리를 중심으로 멤버쉽 함수를 정의하고, 후반부는 입자 군집 최적화(Particle Swarm Optimization) 알고리즘으로 멤버쉽 함수의 정점을 동조한다. 제안된 모델은 표준 모델 평가에 주로 사용되는 가스로 시계열 데이터를 적용하고, 특정 데이터로 노이즈에 영향 받은 데이터를 사용하여 수치 석인 예를 보인다.