节点文献
基于遗传算法的偏最小二乘法在预测含能材料爆轰性能中的应用
Application of GA-based PLS analysis in QSAR studies
【摘要】 运用偏最小二乘(PLS)和遗传算法(GA)预测含能材料的爆炸性能。利用GA在"分子结构—爆炸性能(QSDR)"数据中选取较少的变量个数,以较少的变量个数包含较多的变量信息,再用PLS进行结构性能模型的建立和性能预测。将这种方法应用于呋咱和芳香类含能材料的性能预测当中,可以验证方法的有效性。
【Abstract】 The combination of two methods is proposed to construct GA based PLS analysis,which is applied to QSDR(quantitative structure-detonation relationship)studies for variable selection and model construction.By the method,a few latent variables can in- clude the information of more variables,thus better QSDR models can be obtained.The method is applied to furazan derivatives and ar- omatic compound,it demonstrates the validity of the method.
【关键词】 含能材料;
偏最小二乘;
遗传算法;
分子结构;
爆轰性能;
【Key words】 energetic materials; partial least squares; genetic algorithms; quantitative structure; detonation relationship;
【Key words】 energetic materials; partial least squares; genetic algorithms; quantitative structure; detonation relationship;
【基金】 国家自然科学基金(20675063);国防科工委重大专项
- 【文献出处】 计算机与应用化学 ,Computers and Applied Chemistry , 编辑部邮箱 ,2008年02期
- 【分类号】TQ560.1
- 【被引频次】5
- 【下载频次】356