• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1401-1408
• /
• 2000

Critical prediction models that determine whether a design entity is fault-prone or non fault-prone play an important role in reducing system development cost because the problems in early phases largely affected the quality of the late products. Real-time systems such as telecommunication system are so large that criticality prediction is more important in real-time system design. The current models are based on the technique such as discriminant analysis, neural net and classification trees. These models have some problems with analyzing cause of the prediction results and low extendability. In this paper, we propose a criticality prediction model using fuzzy rulebase constructed by genetic algorithm. This model makes it easy to analyze the cause of the result and also provides high extendability, high applicability, and no limit on the number of rules to be found.

• Journal of Sensor Science and Technology
• /
• v.12 no.2
• /
• pp.79-87
• /
• 2003

In this paper, we propose a method to obtain a linear characteristic using soft computing for systems which have array sensors of nonlinear characteristics. Also a procedure utilizing the pattern information of array sensors without additional sensors is proposed to reduce disturbance effects. For a typical example, even a single CdS cell for CdS array has nonlinear characteristics. Overall linear characteristic for CdS array is obtained using fuzzy logic for each cell and overlapped portion. In addition, further improvement for linearization is obtained applying genetic algorithms for the parameters of membership functions. Also the effect of disturbing external light changes to the CdS array can be reduced without using any additional sensors for calibration. The proposed method based on fuzzy logic shows improvements for position measurements and disturbance reduction to external light changes due to the fuzziness of the shadow boundary as well as the inherent nonlinearity of the CdS array. This improvement is shown by applying the proposed method to the ball position measurements of a magnetic levitation system.

• Journal of Korean Association for Spatial Structures
• /
• v.22 no.3
• /
• pp.49-56
• /
• 2022

Tuned mass damper (TMD) is widely used to reduce dynamic responses of structures subjected to earthquake loads. A smart tuned mass damper (STMD) was proposed to increase control performance of a traditional passive TMD. A lot of research was conducted to investigate the control performance of a STMD based on analytical method. Experimental study of evaluation of control performance of a STMD was not widely conducted to date. Therefore, seismic response reduction capacity of a STMD was experimentally investigated in this study. For this purpose, a STMD was manufactured using an MR (magnetorheological) damper. A simple structure presenting dynamic characteristics of spacial roof structure was made as a test structure. A STMD was made to control vertical responses of the test structure. Two artificial ground motions and a resonance harmonic load were selected as experimental seismic excitations. Shaking table test was conducted to evaluate control performance of a STMD. Control algorithms are one of main factors affect control performance of a STMD. In this study, a groundhook algorithm that is a traditional semi-active control algorithm was selected. And fuzzy logic controller (FLC) was used to control a STMD. The FLC was optimized by multi-objective genetic algorithm. The experimental results presented that the TMD can effectively reduce seismic responses of the example structures subjected to various excitations. It was also experimentally shown that the STMD can more effectively reduce seismic responses of the example structures conpared to the passive TMD.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.70-77
• /
• 2008

This paper proposes a new text candidate region detection method that uses genetic algorithm based on information of the segmented regions. In image segmentation, a classification of the pixels at each color channel and a reclassification of the region-unit for reducing inhomogeneous clusters are performed. EWFCM(Entropy-based Weighted C-Means) algorithm to classify the pixels at each color channel is an improved FCM algorithm added with spatial information, and therefore it removes the meaningless regions like noise. A region-based reclassification based on a similarity between each segmented region of the most inhomogeneous cluster and the other clusters reduces the inhomogeneous clusters more efficiently than pixel- and cluster-based reclassifications. And detecting text candidate regions is performed by genetic algorithm based on energy and variance of the directional edge components, the number, and a size of the segmented regions. The region information-based detection method can singles out semantic text candidate regions more accurately than pixel-based detection method and the detection results will be more useful in recognizing the text regions hereafter. Experiments showed the results of the segmentation and the detection. And it confirmed that the proposed method was superior to the existing methods.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.2
• /
• pp.137-148
• /
• 2000

This paper is based on the 9 goat colonies along the middle and lower Yellow River valley and 7 local goat colonies in the Northeast, Tibet and the Yangtze valley. After collecting the same data about the 22 goat colonies in China and other countries, it establishes and composes the matrix of fuzzy similarity relation describing the genetic similarities of different colonies. It also clusters 38 colonies according to their phylogenetic relationship. The establishment of the matrix and the cluster are effected in terms of the frequency of 18 loci and 43 allelomorphs in blood enzyme and other protein variations. The study proves that the middle Yellow River valley is one of the taming and disseminating centers of domestic goats in the South and East of Central Asia. Compared with other goat populations in this vast area, the native goat populations in the west of Mongolian Plateau, the Qinghai-Tibet Plateau and the middle Yellow River valley share the same origin. The colonies in the lower Yellow River valley and those in the middle valley, however, are relatively remote in their phylogenetic relationship. The native goat colonies in the southeast of Central Asia can be classified into two genetic groups: "East Asia" and "South Asia" and the colonies in Southeast Asia belong to either group.

• Smart Structures and Systems
• /
• v.19 no.4
• /
• pp.341-350
• /
• 2017

Based on the super elastic properties of the shape memory alloy (SMA) and the inverse piezoelectric effect of piezoelectric (PZT) ceramics, a kind of hybrid semi-active control device was designed and made, its mechanical properties test was done under different frequency and different voltage. The local search ability of genetic algorithm is poor, which would fall into the defect of prematurity easily. A kind of adaptive immune memory cloning algorithm(AIMCA) was proposed based on the simulation of clone selection and immune memory process. It can adjust the mutation probability and clone scale adaptively through the way of introducing memory cell and antibody incentive degrees. And performance indicator based on the modal controllable degree was taken as antigen-antibody affinity function, the optimization analysis of damper layout in a space truss structure was done. The structural seismic response was analyzed by applying the neural network prediction model and T-S fuzzy logic. Results show that SMA and PZT friction composite damper has a good energy dissipation capacity and stable performance, the bigger voltage, the better energy dissipation ability. Compared with genetic algorithm, the adaptive immune memory clone algorithm overcomes the problem of prematurity effectively. Besides, it has stronger global searching ability, better population diversity and faster convergence speed, makes the damper has a better arrangement position in structural dampers optimization leading to the better damping effect.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2000.10a
• /
• pp.496-500
• /
• 2000

대형 구조물의 진동제어를 위하여 MR 유체 댐퍼를 사용한 반능동 제어기법에 대하여 연구하였다. 기존에 많이 사용되고 있는 수동제어기법은 일단 제어장치를 설치한 후에는 구조물에 실제로 작용하고 있는 외부 하중의 현재 특성에 대해서 적절히 반응할 수 없다는 제한을 가지고 있으며, 이를 극복하기 위하여 연구되어온 능동제어기법은 구조물이 진동을 감소시키기 위하여 구조물에 직접적으로 가해지는 커다란 제어력을 요구하며, 이로 인해 경우에 따라서는 불안정한 상태가 유발될 수도 있다는 점이 단점으로 지적되고 있다. 최근에 Spencer 등은 반능동 제어기법을 제안하였는데, 이는 수동제어장치의 제어특성을 On-Line 으로 조절하는 방식으로서 제어 가능한 수동제어기법으로도 불리운다. 구조물의 진동제어에 필요한 제어력이, 특수한 제어기구에서 발생되는 인위적인 힘이 아니라, 적절한 구조부재에서 발생되는 자연적인 부재력이므로, 무엇보다 강인하고 신뢰할 수 있는 제어기법이며, 이때 제어장치의 구조적 특성을, 측정된 구조물의 응답에 맞추어 적절히 조절함으로써 다양한 외부하중에 대해 보다 효율적인 제어가 이루어질 수 있도록 한 방법이다. 반능동제어를 위한 제어기로서는 Variable Orifice Dampers, Friction Controllable Isolators, Variable Stiffness Devices, Electro-Rheological (ER) Fluid Damper, Magneto-Rheological(MR) Fluid Damper등이 제안되고 있으며, 본 논문에서는 반응속도가 빠르고, 적은 파워만을 요구하며, 커다란 제어력을 낼 수 있는 MR Damper를 사용하여 지진하중을 받는 구조물의 반능동 제어게 대하여 연구하였다. MR Damper의 특성이 비선형이므로 이에 적합한 Sliding Mode Fuzzy Control(SMFC)기법을 사용하였으며 이때 SMFC 의 최적 설계를 위하여 Genetic Algorithm을 적용하였다. 제안된 제어기법의 실제 적용성을 검증하기 위하여 기존이 제어결과와 비교 검토하였으며, 그 결과로부터 MR Damper를 사용한 반능동 제어기법이 구조물의 진동제어에 매우 효과적임을 확인할 수 있었다.

• Structural Engineering and Mechanics
• /
• v.11 no.5
• /
• pp.485-502
• /
• 2001

Modem soft computing methods, such as neural networks, evolutionary models and fuzzy logic, are mainly inspired by the problem solving strategies the biological systems use in nature. As such, the soft computing methods are fundamentally different from the conventional engineering problem solving methods, which are based on mathematics. In the author's opinion, these fundamental differences are the key to the full understanding of the soft computing methods and in the realization of their full potential in engineering applications. The main theme of this paper is to discuss the fundamental differences between the soft computing methods and the mathematically based conventional methods in engineering problems, and to explore the potential of soft computing methods in new ways of formulating and solving the otherwise intractable engineering problems. Inverse problems are identified as a class of particularly difficult engineering problems, and the special capabilities of the soft computing methods in inverse problems are discussed. Soft computing methods are especially suited for engineering design, which can be considered as a special class of inverse problems. Several examples from the research work of the author and his co-workers are presented and discussed to illustrate the main points raised in this paper.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.475-478
• /
• 2005

본 논문에서는 자기구성 퍼지다항식 뉴럴 네트워크(SOFPNN)를 구성하고 있는 퍼지 다항식뉴론(FPM)의 구조와 파라미터를 유전자 알고리즘을 이용하여 최적화시킨 새로운 개념의 진화론적 최적 고급 자기구성 퍼지 다항식 뉴릴 네트워크를 소개한다. 기존의 자기구성 퍼지 다항식 뉴럴 네트워크에서 모델을 설계할 때에는 설계자의 주관적인 특징과 시행착오에 의해서 모델을 구축하였다. 이러한 설계자의 경험을 배제하고 객관적이고 효율적인 모델을 구축하기 위해서 본 논문에서는 FPH의 파라미터들을 최적화 알고리즘인 유전자 알고리즘을 이용하여 동조하였다. 즉, 모델을 구축하는데 기본이 되는 FPN의 각각의 파라미터들-입력변수의 수, 다항식 차수, 입력변수, 멤버쉽 함수의 수, 그리고 멤버쉽 함수의 정점-을 동조함으로써 기존의 모델에 비해서 구조적으로 그리고 파라미터적으로 최적화된 네트워크를 생성할 수 있다. 뿐만 아니라 주어진 데이터의 특성을 모델 구축에 반영하고자 멤버쉽 함수의 정점 역시 유전자 알고리즘으로 동조하였다. 실험적 예제를 통하여 제안된 모델의 성능을 확인한 결과 기존의 퍼지모델 및 신경망 모델에 비해서 아주 우수한 근사화 능력과 일반화 능력을 가짐을 알 수 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1181-1185
• /
• 2009

Adaptive Nuero-Fuzzy Inference System(ANFIS) 모형은 인공신경망과 퍼지모형의 특징을 가지는 모형으로 자료간의 관계가 선형이 아닌 비선형관계를 가질 경우 매우 정확한 예측 모형을 구축할 수 있는 특징이 있다. 월강수량 예측이 관측된 기상자료들과 비선형 관계에 있다고 생각되어 ANFIS 모형을 이용하여 월강수량을 예측하였다. 본 연구의 대상 지점으로는 금강유역의 대전 지점으로 선정하였다. 금강유역은 우리나라의 한가운데 위치하여 평균적인 강수형태 및 특징을 보여 좋은 실험유역으로 생각되어 선정하였다. 금강유역의 기상청에서 운영하는 지상 유인관측소 중 비교적 금강유역을 대표하고 양질의 자료가 기록되어 있다고 판단되는 대전지점을 실험지점으로 생각되어 선정하였다. 기상청 대전 유인 관측소에는 총 39년치 기상 자료가 기록되어 있다. 기상청에서는 전국 주요 도시들을 대상으로 2003년부터 월간 예보를 하고 있다. 본 연구에서는 기상청 월간예보와 기상청 대전 유인관측소에서 관측된 5년 치 기상자료를 모델의 입력자료로 구성하였다. 적절한 입력변수 조합을 구성하기 위하여 반복해법을 적용하였다. 5년 치 자료 중 절반은 학습을 시키는데 사용하였고 나머지 절반을 이용하여 모형을 검증하였다. 여러 입력변수를 이용하여 모형의 학습시킨 결과 입력변수가 3개 일 경우 가장 높은 정확도를 보였다. 입력변수가 3개로 학습 시킨 ANFIS 모형과 기상청에서 제공하는 월간예보를 비교해본 결과 ANFIS 모형을 적용하여 월 강수량을 예측하는 것이 기상청에서 제공하는 월간예보보다 높은 정확도를 보이는 것을 확인할 수 있었다.