퍼지-뉴럴 네트워크의 새로운 설계와 비선형 공정으로의 응용 = A New Approach to Fuzzy-Neural Networks and Its Application to Nonlinear Processes

다국어 초록 (Multilingual Abstract)

In this paper, we suggest a new approach method to Fuzzy-Neural Networks(FNN) rnodel for complex and nonlinear process systems. The proposed FNNs architecture uses simplified and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. And we use an Genetic Algorithms(GAs) for optimization of model. That is, the parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And an aggregate objective function(performance index) with weighted value is proposed to achieve a sound balance between approximation and generalization abilities of the model. According to selection and adjustment of a weighting factor of an aggregate objective function, we show that it is available and effective to design an optimal FNN rnodel structure with a mutual balance and dependency between approximation and generalization abilities. Here, approximation and generalization abilities mean training and validation of model, respectively. In addition to training and validation. We use testing of model. To evaluate the performance of the proposed model, we use the time series data for gas fumace and the Nox emission process data of gas turbine power plant.