用自适应梯度Boosting算法研究了影响多硝基芳香族化合物(PNACs)密度的主因子.选择分子结构描述码作影响特征参数,采用影响多硝基芳香族化合物密度的分子结构描述码,依据相关影响程度给出了相应分子结构描述码,预测密度值与文献值的相对误差在10%以内.%The main factors affecting the densities of polynitroaromatic compounds (PNACs) were studied by using the adaptive gradient Boosting algorithm. The molecular structure describers (MSDs) are used as the input feature parameters. The MSDs affecting the densities of PNACs are chosen and the corresponding MSDs are given according to their relative degree of influencing. The relative error between the predicted values and literature ones of the densities of PNACs is within 10%.
展开▼