摘要
人工神经网络技术由于自组织、自学习、自适应的能力,常被引入灰色系统模型建立、模式识别、目标分类等研究领域。本次研究运用人工神经网络技术,选取土聚水泥碱激发体系中的碱激发剂浓度(COH-)、碱硅摩尔比(M2O/SiO2)和硅摩尔比(Al2O3/SiO2)为预测指标,基于MATLAB神经网络工具箱,建立预测方法,对土聚水泥的28 d抗压强度进行预测。结果表明,预测精度较高。
The artificial neural network technology as a result of self-organization,self-learning,adaptive capacity,is often used in the gray system for model establishing,pattern recognition and target classification.This research uses MATLAB neural network toolbox,selecting the concentration of alkali activator（COH-）,the molar ratio of alkali-silica（M2O/SiO2） and the molar ratio of silicon（Al2O3/SiO2） as forecast indicators,to predict the 28 d compressive strength of geopolymeric cement.After testing,this prediction model has higher prediction accuracy and can be used as production practice guidance.
出处
《四川建筑科学研究》
北大核心
2011年第1期201-203,共3页
Sichuan Building Science
关键词
土聚水泥
人工神经网络
抗压强度
geopolymeric cement
artificial neural network
the compressive strength
