论文部分内容阅读
本文应用主成分分析(PCA)、遗传算法(GA)等方法进行变量选择确定对含能材料爆轰性能影响显著的分子结构描述符,再用偏最小二乘(PLS)和人工神经元网络等方法建立含能材料预测模型。通过预测模型进行计算,预测密度、爆速、生成焓和爆压等爆轰性能参数。与已知的爆轰性能参数比较,其准确度可达到98%。这说明了模型的准确性,可以用于未知含能材料的爆轰性能的预测。
In this paper, Principal Component Analysis (PCA), Genetic Algorithm (GA) and other methods were used to determine the molecular structure descriptors that have significant effect on the detonation performance of energetic materials. Then, PLS and artificial neural networks Methods to establish a predictive model of energetic materials. The prediction model is used to predict the detonation performance parameters such as density, detonation velocity, enthalpy of formation and explosion pressure. Compared with the known detonation performance parameters, the accuracy can reach 98%. This shows the accuracy of the model and can be used to predict the detonation performance of unknown energetic materials.