为了预测混凝土的抗压强度,在分析BP、RBF神经网络原理的基础上,提出用BP、RBF神经网络模拟混凝土抗压强度与搅拌机各主要影响参数间关系的方法。根据搅拌机的实际工作状况,分别建立了4维输入向量、1维输出向量的BP、RBF神经网络模型,通过19组试验,验证了2种模型的可靠性。结果表明,实测结果与预测结果相接近,该2种神经网络模型能较准确地快速预测混凝土抗压强度。 In order to predict the compressive strength of concrete, a method to simulate the relationship between the compressive strength of concrete and the main influence parameters of the mixer by BP neural network and RBF neural network is proposed based on the analysis of BP neural network and RBF neural network. According to the actual working conditions of the mixer, the BP neural network model of 4-dimensional input vector and 1-dimensional output vector are established respectively. The reliability of the 2 models is verified by 19 sets of experiments. The results show that the measured results are close to the predicted results. The two neural network models can predict the compressive strength of concrete more accurately and accurately.