支持向量机法预测单质炸药爆速的研究  

Prediction the Detonating Velocity of Elemental Explosives by Support Vector Machine

作　　者：杨惠[1] 杨建钢[1] 方学谦 

机构地区：[1]西安近代化学研究所,陕西西安710065

出　　处：《爆破器材》2015年第2期28-31,35,共5页Explosive Materials

基　　金：2013年度火炸药燃烧国防科技重点实验室基金项目(9140C350406130C35126)

摘　　要：为了更好地预估新型含能材料的爆轰参数,应用支持向量机方法建立了单质炸药爆速的预测模型。利用炸药分子的相对分子质量(M)、装药密度(ρ)、氧平衡和碳、氢、氧、氮的质量分数(wC、wH、wO、wN)7种参数作为输入,构建了预测模型。模型预测结果表明,爆速预测值与实验值有较好的一致性,最大相对误差为4.79%,最小相对误差为0.04%,模型的预测精度较好,具有一定的外推性。该方法也可为炸药其他爆轰参数的预测提供指导,具有一定的实用价值。Aiming at the better explosive performance prediction for new energetic materials,the support vector machine（ SVM） method was applied to establish a predictive model for the detonation velocity of elemental explosive. The relative molecular mass of explosives（ M）,loading density（ ρ）,and oxygen balance the percentage composition of carbon,hydrogen,oxygen,nitrogen（ wC、wH、wO、wN）,were selected as inputs of the support vector machine models. The results of the model indicate that,the prediction results are in good agreement with the experimental values. The most relative error is 4. 79% and the least is 0. 04%. The prediction accuracy of the model is good,enabling a certain extrapolation. This method can also provide guidance to predict other detonation parameters of explosives,and has practical applications.

关 键 词：炸药 支持向量机 爆速 预测 

分 类 号：TD235.21[矿业工程—矿井建设]