Study On Dam Deformation Prediction Based On Improved Grey Wolf Optimization And Support Vector Machine

As an important engineering measure to optimize the allocation of water resources and to regulate the spatial and temporal distribution of water resources,the dam plays an important role in controlling flood,storing water and regulating drought.But,the working conditions of the dam are complex and the factors affecting the dam are numerous.At present,the deficiency existing in common forecasting methods lead to prediction accuracy of dam deformation is low,therefore,how to improve the prediction accuracy of dam deformation,accurate to quickly predict the dam deformation becomes extremely important.The main work of the thesis is as follows:First of all,the thesis expounds the forecasting research background,research significance and research status at home and abroad of dam deformation.Aiming at the deficiency existing in the dam deformation forecasting method,this paper proposes a method based on Improved Grey Wolf Optimization(IGWO)algorithm to optimize support vector machine(SVM),which using for dam deformation prediction.Secondly,the paper using the normalized method to preprocess sample data,using Matlab2014 a development platform to design and run some programs and code,and by using the Improved Gray Wolf algorithm to find the best parameters of SVM,and using the best parameters to design the model of dam deformation based on the improved SVM.In the end,the designed model of dam deformation based on the Improved Gray Wolf Optimization algorithm optimize the SVM is used in the prediction of dam deformation for the dam of Fengman and the dam of the key water project at Xiaolangdi on the Yellow River.By comparing with the Cuckoo Search algorithm,the Differential Evolution algorithm,the Particle Swarm Optimization algorithm and the basic Gray Wolf Optimization algorithm,the experimental results show that the Improved Gray Wolf Optimization algorithm for parameter optimization of SVM is more effective.The prediction effect is good based on the established model,and the purpose of the dam deformation forecasting accuracy is raised.