In recent years,concrete dome structure using inflated forms which is introduced and being vigorously promoted in China is a new type of building structure form.It has important significance to predict the construction cost of the main of concrete dome structure using inflated forms quickly and accurately in its project management.In this thesis,particle swarm optimization(PSO)combined with Extreme Learning Machine(ELM)is introduced to predict the construction cost of the main of concrete dome structure using inflated forms.First,according to the structural characteristics of the main of concrete dome structure using inflated forms to analyze its factors of construction cost.The index system is established for the construction cost of concrete dome structure using inflated forms.Secondly,Using the PSO algorithm to optimize the Input weights and threshold of hidden layer of ELM,then to build a construction cost prediction model based on PSO-ELM.Finally,through forecast simulation of construction cost of the main of concrete dome structure using inflated forms,the results showed:accuracy of PSO-ELM is higher compared with ELM,which proves that the model is scientific and effective on prediction of the construction cost of the main of concrete dome structure using inflated forms. |