• 전자공학회논문지B
• /
• 제29B권1호
• /
• pp.58-66
• /
• 1992

This paper proposes a neuro-controller for position control of one-link flexible robot arm. Basically the controller consists of a multi-layer neural network and a conventional PD controller. Two controller are parallelly connected. Neural network is traind by the conventional error back propagation learning rules. During learning period, the weights of neural network are adjusted to minimize the position error between the desired hub angle and the actual one. Finally the effectiveness of the proposed approach will be demonstrated by computer simulation.

• 전기학회논문지
• /
• 제61권5호
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권8호
• /
• pp.352-359
• /
• 2002

A neuro-fuzzy controller has some problems that he difficulty of tuning up the membership function and fuzzy rules, long time of inferencing and defuzzifying compare to PID. Also, the fuzzy controller's own defect as a PD controller has. In this study, it is proposed two methods to solve these problems. The first method is that inner fuzzy rules are tuned up automatically by the back propagation learning according to error patterns. And the second method is a new type defuzzification method that shorten the calculation time of an inferencing and a defuzzifying. In this study, it is designed the new type neuro-fuzzy controller that improves the fast response and the stability of a system by using the proposed methods. And, the designed controller is named EPLNFC(Error pattern Learning Neuro-Fuzzy Controller). To evaluate the fast response and the stability of EPLNFC designed in this study, EPLNFC is applied to a speed control of a DC motor and AC motor.

• 인지과학
• /
• 제4권1호
• /
• pp.261-294
• /
• 1993

대부분의 규칙 기반 전문가 시스템에서 규칙의 갱신과 새로운 규칙의 추가가 다른 규칙에 영향을 주어서는 안된다. 이러한 원리를 규칙의 모듈성이라고 한다. 전문가 시스템에서 증거간의 관계를 알려고 할때, 기존의 전문가 시스템은 정보의 근원이 다른것으로 가정하고 믿음값을 갱신한다. 이러한 가정은 규칙의 모듈성을 위반하게 된다. 본 논문에서는 이러한 문제점을 해결하기 위해 규칙의 모듈성을 보장하는 베이지안 네트워크에 기반을 둔 Fuzzy Belief Network 를 제안한다. Fuzzy Belief Network을 구축하기 위해 노드와 링크 등을 정의하고, 각 노드에서 발생하는 자료의 융합 알고리즘과 자료를 융합한 결과인 믿음값을 모든 노드에 전달하는 확산 알고리즘을 제안한다.

• International Journal of Korean Welding Society
• /
• 제1권1호
• /
• pp.17-22
• /
• 2001

Because the quantitative relationships between welding parameters and welding result are not yet blown, optimal values of welding parameters for $CO_2$ robotic arc welding is a difficult task. Using the various artificial data processing methods may solve this difficulty. This research aims to develop an expert system for $CO_2$ robotic arc welding to recommend the optimal values of welding parameters. This system has three main functions. First is the recommendation of reasonable values of welding parameters. For such work, the relationships in between the welding parameters are investigated by the use of regression analysis and fuzzy system. The second is the estimation of bead shape by a neural network system. In this study the welding current voltage, speed, weaving width, and root gap are considered as the main parameters influencing a bead shape. The neural network system uses the 3-layer back-propagation model and a generalized delta rule as teaming algorithm. The last is the optimization of the parameters for the correction of undesirable weld bead. The causalities of undesirable weld bead are represented in the form of rules. The inference engine derives conclusions from these rules. The conclusions give the corrected values of the welding parameters. This expert system was developed as a PC-based system of which can be used for the automatic or semi-automatic $CO_2$ fillet welding with 1.2, 1.4, and 1.6mm diameter the solid wires or flux-cored wires.

• 대한전자공학회논문지SD
• /
• 제38권11호
• /
• pp.810-820
• /
• 2001

전통적인 이진 가산기는 최상위 비트까지 올림수 전달이 발생하고 직렬가산을 수행한다. 그러나, 변형부호화자리수 체계를 이용한 광가산기는 이진 가산기에서 발생하는 연속적인 올림수 전달을 제한하도록 제안되었다. 본 논문에서는 9가지 부호화된 입력 패턴 중에서 동일한 가산 결과를 가지는 패턴을 동일군으로 하여 5개의 기준패턴으로 만들어 기호치환 규칙수를 줄였다. 또한 결합공간부호화된 입력 패턴과 마스크의 직렬연결로 기존의 기호치환 가산기의 인식 단계에서 필요한 어떤 공간적인 연산없이 인식하여 시스템의 크기를 줄였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권1호
• /
• pp.27-35
• /
• 2016

Black-box classifiers, such as artificial neural network and support vector machine, are a popular classifier because of its remarkable performance. They are applied in various fields such as inductive inferences, classifications, or regressions. However, by its characteristics, they cannot provide appropriate explanations how the classification results are derived. Therefore, there are plenty of actively discussed researches about interpreting trained black-box classifiers. In this paper, we propose a method to make a fuzzy logic-based classifier using extracted rules from the artificial neural network and support vector machine in order to interpret internal structures. As an object of classification, an anomalous propagation echo is selected which occurs frequently in radar data and becomes the problem in a precipitation estimation process. After applying a clustering method, learning dataset is generated from clusters. Using the learning dataset, artificial neural network and support vector machine are implemented. After that, decision trees for each classifier are generated. And they are used to implement simplified fuzzy logic-based classifiers by rule extraction and input selection. Finally, we can verify and compare performances. With actual occurrence cased of the anomalous propagation echo, we can determine the inner structures of the black-box classifiers.

• Computers and Concrete
• /
• 제18권2호
• /
• pp.267-278
• /
• 2016

In order to observe the internal damage of concrete in real time, we introduced acoustic emission nondestructive detecting technology into a series of fracture tests; the test results revealed the whole process that concrete undergoes when it sustains damage that leads to failure, according to the change rules of the acoustic emission parameters. The results showed that both the initiation and unstable loads can be accurately determined using the abrupt change of the acoustic emission rate curves and the turning point of the acoustic emission parameters' accumulative curves. The whole process, from damage to failure, includes five phases, beginning with damage, such as cracking, a stable crack growth process, a critical unstable stage, and unstable propagation. The brittle fracture characteristics of concrete change when steel bars are joined, because the steel bars and the concrete structure bond, which causes an increase in the acoustic emission signals within the fracture process of the reinforced concrete. The unstable propagation stage is also extended. Our research results provide a valid methodology and technical explanations, which can help researchers to monitor the cracking process of concrete structures, in real time, during actual projects.

• 전기학회논문지
• /
• 제62권4호
• /
• pp.554-561
• /
• 2013

In this paper, we introduce a modeling and a process simulator developed with the aid of pRBFNNs for activated sludge process in the sewage treatment system. Activated sludge process(ASP) of sewage treatment system facilities is a process that handles biological treatment reaction and is a very complex system with non-linear characteristics. In this paper, we carry out modeling by using essential ASP factors such as water effluent quality, the manipulated value of various pumps, and water inflow quality, and so on. Intelligent algorithms used for constructing process simulator are developed by considering multi-output polynomial radial basis function Neural Networks(pRBFNNs) as well as Fuzzy C-Means clustering and Particle Swarm Optimization. Here, the apexes of the antecedent gaussian functions of fuzzy rules are decided by C-means clustering algorithm and the apexes of the consequent part of fuzzy rules are learned by using back-propagation based on gradient decent method. Also, the parameters related to the fuzzy model are optimized by means of particle swarm optimization. The coefficients of the consequent polynomial of fuzzy rules and performance index are considered by the Least Square Estimation and Mean Squared Error. The descriptions of developed process simulator architecture and ensuing operation method are handled.

• 한국지능시스템학회논문지
• /
• 제18권6호
• /
• pp.842-848
• /
• 2008

본 논문에서는 비선형 모델의 설계를 위해 Type-2 퍼지 논리 집합을 이용하여 불확실성 문제를 다룬다. 제안된 모델은 규칙의 전 후반부가 Type-2 퍼지 집합으로 주어진 Type-2 퍼지 논리 시스템을 설계하고 불확실성의 변화에 대한 비선형 모델의 성능을 해석한다 여기서 규칙 전반부 멤버쉽 함수의 정점 선택은 C-means 클러스터링 알고리즘을 이용하고, 규칙 무반부 퍼지 집합의 정점 결정에는 경사 하강법(Gradient descent method)을 이용한 오류 역전파 알고리즘을 사용하여 학습한다. 또한, 제안된 모델에 관련된 파라미터는 입자 군집 최적화(Particle Swarm Optimization; PSO) 알고리즘으로 동조한다. 제안된 모델은 모의 데이터집합(Synthetic dadaset), Mackey-Glass 시계열 공정 데이터를 적용하여 논증되고, 기존 Type-1 퍼지 논리 시스템과의 근사화 및 일반화 능력에 대하여 비교 토의한다.