Calculation Method of Continuous Collapse of Concrete Frame Structure Based on Neural Network
Based on the optimization of neural network,this study predicts the bearing capacity of concrete frame structure by using parameters such as concrete strength,reinforcement strength,beam length,span-to-height ratio,beam cross-sectional area and reinforcement ratio.By establishing the back propagation neural network(BPNN)model,the input parameters are associated with the bearing capacity of the arch pressure structure,so as to achieve accurate prediction of the bearing capacity.In order to make the model prediction more accurate,this paper focuses on the optimization method of the model,and compares the excellent BP neural network through common optimization methods such as network structure design,activation function selection,learning rate adjustment etc.,and improves the accuracy and generalization ability of the model.At the same time,the approximate weight of each factor in the continuous collapse of the frame structure is calculated by using the finite element simulation method,and each parameter of the neural network is assigned as the initialization weight,which accelerates the convergence and training of the model and further optimizes the neural network model.It provides a fast and accurate method for predicting the bearing capacity of the continuous collapse of frame structures,which can have positive significance for the prevention and treatment of collapse accidents.
NETL
NSTL
万方数据
