Structures Under Earthquake Response Prediction And Fuzzy Predictive Control

In this paper, we discussed method and localization of the traditional prediction, and studied the fuzzy neural network excellent capability. A new fuzzy Modular neural network is added to the traditional prediction thus the prediction based on the fuzzy neural network is formed. It considers the effects of diversified fuzzy factors on the structure synthetically, so it can get over the disadvantage of the traditional prediction, and it is based on the physics characteristic of the object but not the object mathematics model. At last this method is developed for on-line prediction of the response of a certain building. Such prediction can provide the standard of more exact optimize capability to the active control on the architectural structure. In researching progress, first the model of fuzzy neural network is formed and its parameters are decided. Then the responses of first 2 seconds calculated using Wilson ?0 method are input and trained in the network, finally the network predicts the rest responses after first 2 seconds. The results show that the fuzzy Modular neural network has some excellent function of prediction. It has high precision, and it takes short time. In the paper we also discussed the variety of the precision and calculating time while the network parameters are changed. Finally we use the predictive control system of fuzzy neural network from this paper to process active control on some SDQF structures. The last result indicates that this predictive control system of fuzzy neural system has a series of good capabilities.