摘要
针对目前粉煤灰分类研究存在的片面性,在分析影响粉煤灰品质有关的化学成分和物理性质的基础上,选择细度、玻璃体、烧失量、K2O、SO3和CaO作为投影寻踪聚类分析的特征指标,以活性特征为目标,建立了投影寻踪聚类分析模型,编制了基于MATLAB的相应程序,采用遗传算法寻求最优投影方向,根据投影特征指标值对粉煤灰进行分类。研究表明该模型克服了以往传统分类法的不足,能较全面地反映粉煤灰产品品质性能。
Aimed at one-sidedness existed in classification of fly ash at present, the chemical compositions and physical properties influencing the quality of fly ash was analyzed. Degree of fines£-vitric£-loss on ignition, K20, SO3 and CaO chosen as the criterion indices for classification of fly ash, the pozzolanic activity of fly ash are considered. A classification method of projection pursuit was established£-related program based MATLAB was written. Its projection direction was optimized by using Genetic Algorithm.
出处
《粉煤灰》
2009年第6期7-10,共4页
Coal Ash China
基金
广西教育厅2008年度广西高校优秀人才资助计划项目(桂教人〔2008〕40号)
关键词
粉煤灰
混凝土
投影寻踪回归
蚁群算法
聚类分析
fly ash
concrete
projection pursuit regression
Ant colony algorithm
Cluster analysis