Study On The Application Of Improved Grey Neural Network In The Settlement Prediction Of High Rise Buildings

As the rapid economic development,a large number of high-rise buildings are constructed.These facilities are affected by various factors and deformation is produced in the process of construction and operation.When the deformation exceeds the allowable value,they will have predetermined damage and even lead to disaster,even causing huge losses to people's lives and property.Therefore,it is of great practical significance to analyze the dynamic deformation of the deformable body accurately.In order to overcome the problem that weight threshold in grey neural network is random,improved fruit fly optimization algorithm is proposed to optimize the gray neural network.The multi population co-evolution algorithm is improved by modifying the individual update strategy to reduce the blind search,using mutation operation method to maintain the diversity of the population.The improved algorithm can jump out of local optimum and avoid falling into local optimum and improve the performance of the algorithm.The improved fruit fly optimization algorithm is used to optimize the parameters of grey neural network,and the wavelet threshold method is applied to deal with the original time series.Then the gray neural network prediction model based on improved fruit fly optimization algorithm is established.The actual engineering settlement data are used to verify the prediction performance of the model,and the predicted results are compared with those of FOA-GNNM,PSO-GNNM and GNNM.The results show that the improved FOA-GNNM has high prediction accuracy and strong robustness.