基于深度学习与修正IMK模型的夹层叠合板受弯性能研究OA

The flexural performance properties of ceramsite foamed concrete sandwich composite slabs is critical to the overall safety of building structures.However,predictive models for such slabs remain limited.To this end,five ceramsite foamed concrete sandwich composite slabs were designed for static loading tests in this paper.A refined finite element model was developed and validated.The test data and simulation data of the modified Ibarra-Medina-Krawinkler(IMK)model were integrated to construct a composite slab database,and a prediction model was established in combination with the BP neural network.The load-displacement curves generated by the prediction model and those from the tests were compared and analyzed.The results indicate that the evaluation indexes of the BP neural network prediction model combined with the modified IMK model have a maximum RMSE of 9.69,a maximum MAPE of 9.64%,and a minimum R2 of 0.94,indicating strong generalization capability and high prediction accuracy.The load-displacement curves generated by the prediction model are basically consistent with the test load-displacement curves,confirming that the proposed model can effectively simulate the flexural behavior of such composite slabs.