NEURAL NETWORK BASED RESISTIVITY PREDICTION OF NANO-MARINE CONCRETE
This paper investigates the feasibility of neural network for concrete resistivity prediction by measuring the nano-concrete resistivity of under Cl-erosion and dry-wet cycle coupling by Wenner's four-electrode method,for predicting the resistivity measurements using BP neural network and Elman neural network.The results show that BP neural network is better than Elman neural network,as the prediction error of BP neural network is lower,and the correlation between its input and output parameters is stronger.The use of neural networks in concrete relat-ed research has certain practicality.
万方数据
维普
