Application Of DPO - BP in Strength Prediction of Concrete

摘要

In the actual production process, the prediction of compressive strength of concrete 28d is of great significance. Prediction of compressive strength of concrete is a typical multi input single output nonlinear systems, which is very close to the BP neural network model. In this paper, the BP neural network is applied to the prediction of the compressive strength of concrete, but the training effect of the network is influenced by the initial weight and threshold value, and the generalization ability is not ideal. Given Dolphin Partners Optimization (DPO) has advantages of fast convergence speed, robustness and its application to BP neural network weights and threshold optimization problem on. Compared with the PSO-BP algorithm, proved its superiority in the prediction of compressive strength of concrete.