摘要
再生保温混凝土作为一种新型绿色混凝土,对发展绿色循环经济和高效节能建筑具有重要意义。其抗压强度受多个因素影响,各因素之间存在着复杂的非线性关系。提出一种基于相关向量机的再生保温混凝土抗压强度预测模型,该模型通过对少量样本的学习,可以建立各影响因素与抗压强度的非线性映射关系,对仅知道影响因素的预测样本进行抗压强度值精准预测。将该模型应用于再生保温混凝土抗压强度实例并与BP神经网络模型对比,研究结果表明,该模型具有精度高、容易实现和离散性小等优点,为再生保温混凝土抗压强度预测提供了一条新途径。
As a new type of green concrete,recycled thermal insulation concrete is of great significance for the development of green recycling economy and efficient,energy-saving buildings.Its compressive strength is affected by many factors,and there are complex nonlinear relationships among various factors.A prediction model of compressive strength of recycled thermal insulation concrete based on relevance vector machine is proposed.By learning a small number of samples,the nonlinear mapping relationship between influencing factors and compressive strength can be established.The compressive strength value is accurately predicted for the forecast samples that only contain the influencing factors.The model is applied to the example of compressive strength of recycled thermal insulation concrete and compared with back propagation(BP)neural network model.The results show that the model has the advantages of high precision,easy realization and small dispersion.It provides a new way for reasonably predicting the compressive strength of recycled thermal insulation concrete.
作者
张研
邝贺伟
曾建斌
ZHANG Yan;KUANG Hewei;ZENG Jianbin(School of Civil and Architecture Engineering,Guilin University of Technology,Guilin 541004,China)
出处
《混凝土》
CAS
北大核心
2020年第9期10-14,共5页
Concrete
基金
国家自然科学基金(51409051)。
关键词
再生保温混凝土
抗压强度
相关向量机
预测模型
regenerative thermal insulation
compressive strength
relevance vector machine
predictive model
