Research About Evaluation Methods Of Suitability In Southern Shanxi Relocation Site Selection

Immigrants relocation project in southern Shaanxi is a complicated system engineering confronting many issues,in which site selection is most high lighted,since the social impact caused by siting is directly related to the success of the entire relocation work;The key of the site selection is to establish an effective and feasible evaluation index system and evaluation method to comprehensively evaluate the suitability of the geological,resources and environment of the resettlement area.Nowadays the research of evaluation methods of resettlement relocation is mainly focused on resettlement of Three Gorges Reservoir and relocation of WENCHUAN Earthquake.In view of few studies about southern Shaanxi have been done,the study about suitability evaluation method is of great significance to southern Shaanxi.To explore the technologies which are suitable for site selection and evaluating the suitability facilitate the site selection in the future in southern Shaanxi,this thesis relies on the ' Evaluation technology research project 'and' science and technology projects in Shaanxi Province 'work to Mian Country as an example,the progress and results are listed as follows:1?Based on the analysis of the law of development of geological disasters in Mian County and the necessary conditions of residents' living,the suitability evaluation index system of relocation sites in southern Shaanxi was established,and the weights of each evaluation index was determined by analytic hierarchy process.2?Based on the characteristics of southern Shaanxi,this paper adopted the multi-index comprehensive evaluation method in decision-making science to convert the practical problems into mathematical problems and carried out quantitative analysis.Three kinds of traditional mathematical evaluation models were established: fuzzy comprehensive evaluation method,ideal point method evaluation model,uncertainty measurement theory;and the accuracies of the three evaluation results were tested.The analysis showed that the evaluation results of the three methods are close to each other in the same evaluation area,which were in good agreement with the results of the field survey,and among that,the results of the uncertainty measurement theory were more reasonable.3?In order to overcome the shortcomings of the basic bats optimization algorithm,this thesis proposed to introduce the bacterial migration factor into the basic bat optimization algorithm to form the Bats Algorithm(EDBA)based on bacterial migration.The threshold of evolutionary stagnation algebra was set up,when the conditions were met,different migration probabilities were given according to the different fitness values of the individual to prevent the degeneration of the solution,thus effectively avoiding the algorithm from falling into local optimum.At the same time,the local search strategy of the basic bat optimization algorithm was changed,and the global searching ability and convergence speed of the algorithm was improved.4?In this paper,the improved bat optimization algorithm and the projection pursuit method were combined,since the best projection value of the projection pursuit method is based on the global sample data,which would weaken the leading role of single raster data in a grid evaluation,the game theory was introduced,and the optimal projection value and the weight based on the entropy weight theory were combined to optimize the weight value for a single grid and improve the evaluation accuracy of the model.5?In order to solve the premature convergence problem of fruit fly optimization algorithm,this paper introduced the hybridization factor and the Simplex Algorithm with strong local search ability into the basic fruit fly optimization algorithm.This method took the evolutionary stagnation step as the triggering condition and avoided the local optimal solution by the hybrid factor avoiding algorithm.After introducing the simplex algorithm,the local search ability and the convergence speed of the algorithm were improved.The improved fruit fly optimization algorithm and generalized regression artificial neural network(GRNN)were combined with adopting spread value of fruit fly optimization algorithm,which accelerated the convergence speed and improved the fitting accuracy of GRNN.6?To solve the insufficient accuracy of late convergence of the standard particle swarm optimization(PSO),a hybrid particle swarm optimization(MPSO)algorithm was proposed by introducing the hybridization factor of the genetic algorithm into the standard particle swarm optimization algorithm,which was based on the hybridization idea of the genetic algorithm.This method enriched the population diversity and improved the global optimization performance and convergence rate of the PSO algorithm.Combining the hybrid particle swarm optimization algorithm with least squares support vector machine(LSSVM),the regularization parameter ? and the kernel width ? of LSSVM were optimized by MPSO,which improved the nonlinear fitting accuracy and the generalization performance of the model.7?In order to overcome the shortcomings of standard GEP algorithm,the backtracking mechanism and the simplex algorithm were introduced into the standard GEP method.By setting a certain number of checkpoints in the evolutionary process,this method avoided ceaseless evolution at the local optimal solution,It can jump out of the local optimum in time and enhance the accuracy of the late convergence of the algorithm.At the same time,it was applied to the parameter estimation of the multiple linear regression,which improved the modeling efficiency and precision.8?Since traditional K-means clustering algorithm is easy to fall into the local optimal,the K-means clustering method based on cat-cluster algorithm was proposed in this thesis,the results showed that compared with the traditional K-means clustering method,this method can improve the accuracy of the model and the stability of the model.9?Through the eight established evaluation models,combined with GIS technology,the results of the evaluation of the relocation site selection in Mian Country were zoned,which provided the reference for suitability evaluation and optimization of relocation site selection.