摘要
采用传统的数学函数关系难以表达和揭示浆体流变参数影响规律.文章以主要影响因素正交试验结果为基础,利用神经网络理论,建立了4个输入单元和2个输出单元的3层BP神经网络模型.采用该模型仿真和预测新试验样品的流变参数,并与实测参数对比.结果表明:预测准确率达90%以上,可以用于指导工程应用中浆体配比与制备.
It is difficult to express the influencing disciplinarian of the rheological parameters of slurry using traditional mathematic functions.The BP neural Network model with three tiers structure are founded by using the theory of neural Network and orthogonal experiment results in this article.The rheological parameters of new samples are simulated and forecasted using the model,and the results indicate that the veracity is over 90 percent through comparing with actual testing results.The model can be used to direct ration and preparation of slurry in engineering practice.
出处
《厦门大学学报(自然科学版)》
CAS
CSCD
北大核心
2005年第1期59-62,共4页
Journal of Xiamen University:Natural Science
基金
福建省自然科学基金(D0410008)资助
关键词
表达
预测
指导
影响因素
准确率
正交试验
对比
流变参数
浆体
工程应用
rheological parameters
influencing disciplinarian of factors
BP neural Network modeling
simulating and forecasting