• 전자공학회논문지SC
• /
• 제41권3호
• /
• pp.39-46
• /
• 2004

본 논문은 IPMSM 드라이브의 고성능 속도 제어를 위하여 퍼지제어와 신경회로망을 혼합 구성한 적응 FNN 제어기를 제시한다. 적응 FNN 제어기는 기준 모델에 기초한 적응 메카니즘을 적용하여 신경회로망의 고도의 적응제어와 퍼지제어기의 강인성 제어의 장점들을 접목한다. 적응 FNN 제어기의 출력은 FNN 제어기의 출력과 적응 퍼지제어의 출력을 합하여 출력을 얻는다. 적응 FNN 제어기는 다양한 동작조건에서 응답특성을 분석하고 평가한다. 제시한 적응 FNN 제어기의 타당성은 IPMSM 드라이브 시스템에 적용하여 성능 결과로 입증한다.

• 전기학회논문지
• /
• 제61권2호
• /
• pp.312-320
• /
• 2012

In this study, we introduce a new design methodology of a granular-oriented self-organizing polynomial neural networks (GoSOPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). In contrast to the typical architectures encountered in polynomial neural networks (PNN), our main objective is to develop a methodological design strategy of GoSOPNNs as follows : (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context-based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets (so-called contexts) defined in the output space. (b) The proposed design procedure being applied at each layer of GoSOPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics (such as the number of contexts, the number of clusters, a collection of the specific subset of input variables, and the order of the polynomial) can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed GoSOPNN network, we describe a detailed characteristic of the proposed model using a well-known learning machine data(Automobile Miles Per Gallon Data, Boston Housing Data, Medical Image System Data).

• 한국지능시스템학회논문지
• /
• 제11권5호
• /
• pp.406-412
• /
• 2001

본 논문은 기존의 퍼지 단층 퍼셉트론 알고리즘의 학습 시간과 수렴성을 개선하기 위해 인간 신경계의 생리학적 뉴런 구조를 분석하며 퍼지 논리를 이용한 새로운 뉴런 구조를 제시하고, 이를 바탕으로 생리학적 퍼지 단층 퍼셉트론(P-FLSP: Physiological Fuzzy Single Layer Perceptron)에 대한 학습 모형과 학습 알고리즘을 제안한다. 제안된 학습 알고리즘의 성능을 평가하기 위해 Exclusive OR 문제, 3-bit parity 문제 그리고 차량 번호판 인식 문제 등에 적용하여 피곤의 피지 단층 퍼셉트론 알고리즘과 성능을 비교, 분석하였다. 실험 결과에서는 제안된 학습 알고리즘(P-FSLP)이 기존의 퍼지 단층 학습 알고리즘보다 지역 최소화에 빠질 가능성이 감소하였으며 학습 시간과 수렴성도 개선되었을 뿐만 아니라, 영상 인식등에 대한 응용 가능성도 제시되었다.

• 조명전기설비학회논문지
• /
• 제20권3호
• /
• pp.53-61
• /
• 2006

본 논문은 유도전동기 드라이브의 고성능 제어를 위한 적응 퍼지-뉴로 제어기를 제시한다. 이 알고리즘의 설계는 퍼지제어와 신경회로망을 사용하는 퍼지-신경회로망 제어기에 기초한다. 적응 퍼지-뉴로 제어기는 신경회로망의 학습패턴과 같은 퍼지 룰을 사용하고 또한 지령값과 실제값 사이의 오차를 최소화하기 위하여 신경회로망의 뉴런사이의 하중을 역전파 알고리즘 방법을 사용하여 조절한다. 적응 기준 모델 설계는 기준모델의 출력과 전동기 속도 사이의 오차와 오차 변화분을 기초로 한 퍼지 로직에 의하여 실행되는 적응 메카니즘을 제시한다. 적응 퍼지-뉴로 제어기의 제어 성능은 다양한 동작 상태에 대한 분석으로 평가한다. 제안한 제어시스템의 실험 결과는 고성능과 파리미터 변동과 정상상태 정확성, 순시응답의 강인성을 가진다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 B
• /
• pp.1248-1250
• /
• 2004

This paper is proposed adaptive fuzzy-neural network controller(NFC) for speed control of surface permanent magnet synchronous motor(SPMSM) drive. The design of this algorithm based on NFC that is implemented using fuzzy control and neural network. This controller uses fuzzy rule as training patterns of a neural network. Also, this controller uses the back-propagation method to adjust the weights between the neurons of neural network in order to minimize the error between the command output and actual output. A model reference adaptive scheme is proposed in which the adaptation mechanism is executed by fuzzy logic based on the error and change of error measured between the motor speed and output of a reference model. The control performance of the adaptive NFC is evaluated by analysis for various operating conditions. The results of analysis prove that the proposed control system has strong high performance and robustness to parameter variation, and steady-state accuracy and transient response.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권2호
• /
• pp.45-51
• /
• 2006

In this paper, we propose a new architecture of Information Granulation based genetically optimized Self-Organizing Fuzzy Polynomial Neural Networks (IG_gSOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially information granulation and genetic algorithms. The proposed IG_gSOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). To evaluate the performance of the IG_gSOFPNN, the model is experimented with using two time series data(gas furnace process and NOx process data).

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권6호
• /
• pp.264-273
• /
• 2006

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) by means of consecutive optimization and also discuss its comprehensive design methodology involving mechanisms of genetic optimization. The network is based on a structurally as well as parametrically optimized fuzzy polynomial neurons (FPNs) conducted with the aid of information granulation and genetic algorithms. In structurally identification of FPN, the design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). For the parametric identification, we obtained the effective model that the axes of MFs are identified by GA to reflect characteristic of given data. Especially, the genetically dynamic search method is introduced in the identification of parameter. It helps lead to rapidly optimal convergence over a limited region or a boundary condition. To evaluate the performance of the proposed model, the model is experimented with using two time series data(gas furnace process, nonlinear system data, and NOx process data).

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.423-425
• /
• 1998

An optical system which can autonomously form and display an impression of a picture made up by many figures has been developed. This system consists of optical fuzzy-neurons which calculate the correlation between the input picture and the reference image by incoherent optics. The calculated signal is applied to an amplifier whereby the output signal increases, then decreases according to increase of the input signal . These outputs are synthesized, and are used for changing the position where the system gaze on a part of the input picture by light beam. In this system, the light intensity used for gazing changes chaotically, The attractor drawn from the change of light intensity corresponds to the impression of the picture. This paper shows the results that are calculated by the numerical simulation. The system has been simulated to express the impression for a picture formed by 4figures.

• 산업기술연구
• /
• 제15권
• /
• pp.187-193
• /
• 1995

In this paper, a short-term load forecasting expert system considering the load variation due to the change in temperature is presented. The change in temperature is an important load variation factor that varies the normal load pattern. The conventional load forecasting methods by artificial neural networks have used the technique where the temperature variables were included in the input neurons of artificial neural networks. However, simply adding the input units of temperature data may make the forecasting accuracy worse, since the accuracy of the load forecasting in this method depends on the accuracy of weather forecasting. In this paper, the fuzzy expert system that modifies the forecasted load using fuzzy rules representing the relations of load and temperature is presented and compared with a conventional load forecasting technique. In the test case of 1991, the proposed model provided a more accurate forecast than the conventional technique.

• 한국정보통신학회논문지
• /
• 제5권4호
• /
• pp.766-776
• /
• 2001

다층 신경회로망의 모델의 구성은 적용분야에 따라서 임의로 선택되어지고, 최적의 모델 구 성은 긴 시간에 걸친 시행착오를 통하여 결정된다. 본 논문에서는 다층 신경회로망 모델의 은닉층 뉴런 수를 학습 과정에서 퍼지 규칙을 이용하여 최적화하는 방식을 제안하였다. 임의의 패턴 문제와 도립진자의 멥핑에 적용하여 제안한 알고리즘의 유용성을 비교 검토하였다.