| Summary: | 碩士 === 國立清華大學 === 化學工程學系 === 87 === On the process of pultrusion of glass fiber/phenolic resin composites,there are three process parameters T1,T2(temperature) and V(velocity).To find the optimal process parameter,the article proposes the experimental desing method,which includes artificial neural network,smoothness factor,random search algorithm,fuzzy classification and information theory.An initial batch of experimental data is first collected to construct a neural-network model.Random search generates a number of candidates for the next batch of experiments.A fuzzy classification algorithm is used to find the cluster centers of these candidates.An information free energy index is defined to balance the need for better classification and the relevance of each class in optimization.New experiments are performed at these cluster centersto validate the model.The procedure is repeated until an optimal solution is reached.
|
|---|
