Intelligent Continuity Method of Site Classification and Characteristic Period

摘要

This paper presents an analysis of the bi-dimensional-membership-function-based site fuzzy classification method is presented. A site fuzzy classification method based on Back Propagation (BP) network is proposed. The training of fuzzy networks of four types of standard sites is fulfilled. The BP-based method overcomes the bi-dimensional membership function's defect of being not gradual or gentle but involving irregular or abrupt breaks at the surfaces (junctures of planes). Therefore, this method makes the classification result better meet requirements of practical construction. Based on the fuzzy classification networks of four standard sites, a BP-based site classification method is proposed. Space distribution graphics of this method is provided. Thus, intelligence, accuracy and continuity of site classification are realized. Finally, an intelligent continuity method of site characteristics period is established and space distribution graphics of characteristic period are presented as well. We can hereby ascertain both a continuous seismic reflection curve and the seismic action more objectively and reasonably.