基于相关向量机的再生混凝土收缩徐变预测

Prediction about shrinkage and creep of recycled aggregate concrete based on relevance vector machine

针对再生混凝土收缩徐变与其影响因素之间存在着复杂的非线性关系,难以建立精准预测模型.提出一种基于相关向量机的再生混凝土收缩徐变预测模型,该模型通过对少量学习样本的学习,精准预测仅知道影响因素的预测样本的收缩徐变值.将该模型应用于再生混凝土收缩徐变预测,研究结果表明,该方法具有精度高、小样本、容易实现等优点,为再生混凝土收缩徐变获取提供了一条新途径。

In order to build an accurate model to predict the nonlinear mapping relationship between shrinkage creep of recycled aggregate concrete and its main influencing factors,the model based on relevance vector machine is proposed for forecasting of shrinkage and creep of recycled aggregate concrete.By learning a few learning samples,the shrinkage and creep of predicting samples can be accurately predicted.The model has been applied to predict the shrinkage and creep of recycled aggregate concrete,the results show that this method can high accurately predict new samples.The model also has merits of few learning samples and easy-to-implement rules.It provides a new way for reasonably determining shrinkage and creep of recycled aggregate concrete.