基于BP神经网络的纤维混凝土力学性能预测模型

Prediction Model of Fiber Concrete Mechanical Properties Based on BP Neural Network

基于BP神经网络预测模型对不同材料掺量的纤维混凝土进行混凝土力学性能预测,找到适宜的隐藏层单元数和误差目标值。通过将预测数据和实测数据进行对比,研究该预测模型对于混杂纤维混凝土强度预测的可行性。经检验当隐藏层单元数为9个,目标误差值为1e-7时,预测值的准确性最高。

In this paper,based on BP neural network rediction model,the mechanical properties of fiber concrete with different materials content are predicted,and the appropriate hidden layer element number and error target value are found.The feasibility of the prediction model for strength prediction of hybrid fiber concrete is studied by comparing the predicted data with the actual data.When the number of hidden layers is 9 and the target error is 0.001,the prediction value is the most accurate.