神经网络在混凝土断裂能预测中的应用  

Application of Neural Network in Forecast of Concrete Fracture Energy

作　　者：王兆忠[1] 陈凤山[2] 周迎新[1] 

机构地区：[1]广州四航工程技术研究院,广东广州510023 [2]大连理工大学,辽宁大连116024

出　　处：《水运工程》2005年第9期49-54,共6页Port & Waterway Engineering

摘　　要：通过神经网络中最广泛使用的BP网络建立预测模型,预测混凝土的断裂能。对模型的预测值与试验数据及已有的数学预测公式的预测值进行了比较。研究表明,神经网络方法由于综合考虑了更多的混凝土断裂能影响因素,而且能够实现非线性关系,所以具有较高的预测精度。神经网络预测模型在混凝土断裂能预测中具有广阔的应用前景。Concrete fracture energy is forecasted by the model based on BP （Back-propagation） network, which is widely used in Neural Network. The forecasted values are compared with experiment data and the values calculated by empirical formulae. The research indicates that Neural Network has high accuracy because it is able to realize nonlinear relations and because more factors influencing fracture energy are taken into account. The Neural Network forecast model has a wide application prospect in the forecast of concrete fracture energy.

关 键 词：混凝土 断裂能 神经网络 BP反向传播算法 MATLAB 预测模型 

分 类 号：TU528[建筑科学—建筑技术科学]