Study On Earthquake Damage Prediction Of Urban Buildings And Earthquake Economic Lossess

Once the city suffered a destructive earthquake, it is bound to cause huge economic losses and casualties. Accordingly, before the destructive earthquake occurred, predicting scientifically the earthquake damage of buildings, Correctly evaluating the seismic capability of urban buildings and reasonably predicting the economic losses can provide guidance information for the post-earthquake emergency relief and the planning of earthquake resistance and disaster prevention. The traditional prediction method of earthquake losses requires the building details of all types in the area, it Will cost a huge human, financial and material resources to collect the details. Accordingly, it needs to develop a quick and easy prediction method of seismic damage losses to improve the quantitative research level of the earthquake disaster.Based on the background above, the following aspects about seismic disaster rapid prediction of urban buildings and economic losses are mainly studied. Firstly,the article summarizes the traditional prediction methods of earthquake losses and their characteristics, and illuminates the importance of developing a quick and easy prediction methods of seismic damage loss. Secondly,the paper presents a rapid prediction method of earthquake damage of buildings based on the analog of feature parameters. Minkowski distance in fuzzy mathematics is used to measure the degree of similarity of both buildings,and the weights of feature parameters are obtained through FAHP. So it is more simple and more rapid to collect the work-site data. Thirdly, in this paper ,the assessment data of destructive earthquake since 1989, population,GDP and other relevant information in the earthquake-hit area are collected. based on the data,the Neural Network is used to assess the earthquake economic losses, then Genetic Algorithm is used to optimize the weights and thresholds. A new and rapid assessment method of earthquake economic losses is established based on BP Neural Network and Genetic Algorithm. Finally, through the Case Study, it shows that the new method is feasible and reasonable. The Application of this method in Wenchuan earthquake further indicates the feasibility and practicality of the method.