Study And Implementation On Flood Disaster Multi-Grade Fuzzy Comprehensive Evaluation Method

Flood disaster is a kind of natural phenomenon. The paradox is that on the one hand it has a strong destructive power, cause great damage to human society and natural environment, and on the other hand it is essential for maintaining natural ecological balance. The experience and lessons of water conservancy in the domestic and overseas show that the kind of pure "flood preventing" strategy is no way out. And, with the increasing of the economic construction scale near the basin and the rising trend of the scale of flood caused by many complicated factors, the threat of flood is becoming more and more serious. After suffered a painful lessons, the scholars put forward the concept of flood disaster risk managementThe complexity of flood mechanism, the randomness in the process and the differences of hazard-bearing body determines the immense difficulty of floods classfication. But in recent years with the frequent occuring of heavy disasters and its great harm, as an important part of flood disaster risk management, disaster grade evaluation is paid more and more attention for disaster forecasting and royal disaster loss. Based on the research on the theory of multistage fuzzy comprehensive evaluation and the principle of quantitative multi-dimensional multi-index classification, the dissertation take the flood disaster level assessment as the research object, study and discuss the questions that how to set complex random samples’accurate classification under the condition of standards lackness, how to set up a flood disaster level assessment criteria system with universal flood index, the space and time acrossing attribute, higher recognition, and how to assess the flood samples with large amount of information and high accuracy under a clear classification standard. Some solutions are given and their validity and reliability are verified. Related research achievement has been applied in engineering application. This article’s main research content and innovation can be described as follows:(1) According to the dependence on sample distribution of the fuzzy clustering iteration method for of, kernel function method was applied in fuzzy clustering model, through the kernel mapping, the sample space is mapped to a high-dimensional feature space, and looking for linear regression equation in high dimensional feature space, making the treated sample more suitable for clustering algorithm, effectively improving the effect and accuracy of clustering. And its computation complexity is not obvious increased with the increase of the feature space dimension.(2) In order to solve the problem that classification effect will rapid decrease with the occuring of a super big sample which cause large deviation of the fuzzy cluster centers, this article put forward the identification method of the super big samples by the weighted average relative distance and chebyshev inequality.(3) Aiming at the missing of the flood disaster evaluation standards which have strong universality and high recognition, this article deeply studied the theory of fuzzy clustering iteration method and process, develop the standards formulating function of fuzzy clustering iteration model based on the clustering center matrix and fuzzy classification of european-style distance discriminant and build a flood disaster level assessment standards formulating model. In the modeling process, indicators and the sample values carried on twice standardizing to ensure the universality of the standards. Model is verified to be feasible and effective through example.(4) In view of that the strong subjectivity in parameter setting and high dependence of training samples and the experience value in existing projection pursuit, this article put forward a new projection index function with a better explanation for projection pursuit clustering effect and build a new projection pursuit clustering model, which greatly improves the clustering objectivity and evaluation effect and reduces the computational complexity. The model can get a precision continuity level value of a sample by combining with polynomial function.(5) In consideration of that the traditional optimization algorithms perform poorly in the optimization problem in the flood classification model, an adaptive chaos differential evolution algorithm with the combination of cultural algorithm is put forward. With the learning and evolution ability of the cultural algorithm, the new algorithm improves the efficiency. Meanwhile, by using adaptive mutation factor and crossover factor, the convergence ability of the algorithm is improved.