基于正交设计的BP神经网络在油页岩渣制砖配方研究中的应用

采用正交实验设计与BP神经网络相结合,建立了油页岩渣砖配比与抗压强度之间的非线性关系模型,以正交实验数据为基础进行神经网络训练,得到了油页岩渣砖的BP神经网络预测模型.并对模型进行验证,预测结果基本满意.同时用训练好的BP神经网络预测模型建立了配方中单因素分析,对寻找最优配方有一定的指导意义.最终达到缩短实验周期,节省人力、物力的目的.

Application of BP neural network based on the orthogonal design in the study of oil shale waste brick formula

The BP neural network based on orthogonal design is used to establish a nonlinear relation prediction model between oil shale waste brick and compressive strength.Based on orthogonal test,the BP neural network model was trained.The prediction results show the trained model is good.The model can predict compressive strength with any brick formula.In addition,the model can do factors analysis,which is sand and cement have influence on compressive strength.It has guiding significance for finding optimal formul...