[1]程露萍,何中其.多硝基含能化合物5 s爆发点的定量构效关系[J].爆破器材,2023,52(02):13-18.[doi:10.3969/j.issn.1001-8352.2023.02.003]
　CHENG Luping,HE Zhongqi.Quantitative Structure Property Relationship of 5 s Explosion Temperature of Polynitro Energetic Materials[J].EXPLOSIVE MATERIALS,2023,52(02):13-18.[doi:10.3969/j.issn.1001-8352.2023.02.003]
点击复制

多硝基含能化合物5 s爆发点的定量构效关系()
分享到：

《爆破器材》[ISSN:1001-8352/CN:32-1163/TJ]

卷:
52
期数:
2023年02
页码:
13-18
栏目:
基础理论
出版日期:
2023-03-30

文章信息/Info

Title:
Quantitative Structure Property Relationship of 5 s Explosion Temperature of Polynitro Energetic Materials
文章编号:
5763
作者:
程露萍; 何中其
南京理工大学化学与化工学院（江苏南京，210094）
Author(s):
CHENG Luping;  HE Zhongqi
School of Chemistry and Chemical Engineering, Nanjing University of Science and Technology (Jiangsu Nanjing, 210094)
关键词:
多硝基含能材料; 5 s爆发点; 随机森林; 人工神经网络; 定量构效关系
Keywords:
polynitro energetic material;  5 s explosion temperature;  random forest (RF);  artificial neural network (ANN);  quantitative structure property relationship (QSPR)
分类号:
TJ55；TQ560.7; O641
DOI:
10.3969/j.issn.1001-8352.2023.02.003
文献标志码:
A
摘要:
为精确预测含能材料的5 s爆发点，解决大量新型含能材料实验测试难度大、安全数据不全等问题，基于定量构效关系（QSPR）原理，研究多硝基含能材料分子结构与5 s爆发点（lnTE）间的内在定量关系。应用集成学习算法随机森林（RF）筛选出8个对5 s爆发点具有显著影响的分子描述符；采用人工神经网络（ANN）建立90种多硝基含能材料5 s爆发点的预测模型。73种训练集的复决定系数为0.918，均方根误差为0.036，平均绝对误差为0.027。17个检验样本的复决定系数为0.903，均方根误差为0.061，平均绝对误差为0.053。对模型进行了验证以及应用域评价。结果表明:模型具备较好的预测性和泛化性能，可用于对多硝基含能材料的5 s爆发点进行精度较高的预测，有效解决现有含能材料的爆发点数据不够全面的问题，为相关产品研制与生产安全提供参考。
Abstract:
In order to accurately predict the 5 s explosion temperature of energetic materials and solve the problems of difficult experimental testing and incomplete safety data of a large number of new energetic materials, based on the principle of quantitative structure property relationship (QSPR), the intrinsic quantitative relationship between molecular structure of polynitro energetic materials and 5 s explosion temperature (ln TE) was studied. Ensemble learning algorithm random forest (RF) was applied to screen eight molecular descriptors that have significant impact on 5 s explosion temperature. Artificial neural networks (ANN) were used to build prediction model of 5 s explosion temperature of 90 kinds of polynitro energetic materials. The coefficient of multiple determination of 73 training sets is 0.918, the root mean square error is 0.036, and the mean absolute error is 0.027. The coefficient of multiple determination of 17 test samples is 0.903, the root mean square error is 0.061, and the mean absolute error is 0.053. The model was validated and its application domain was evaluated. Results show that the model has good predictability and generalization performance, and can be used to predict 5 s explosion temperature of polynitro energetic materials with high accuracy. It can effectively solve the problem that the explosion temperature data of existing energetic materials is not comprehensive enough, and provide reference for the development and production safety of related products.

参考文献/References:

［1］EL-SAYED S A. Review of thermal decomposition, kinetics parameters and evolved gases during pyrolysis of energetic materials using different techniques ［J］. Journal of Analytical and Applied Pyrolysis, 2022, 161: 105364.
［2］李国新，程国元，焦清介.火工品实验与测试技术［M］.北京: 北京理工大学出版社, 1998: 15-20.
［3］COOPER P W. Explosives engineering ［M］. New York: VCH Publishers, Inc., 1997: 83-89.
［4］中国兵器工业总公司. 炸药试验方法：GJB 772A—97 ［S］. 北京：国防科工委军标发行部， 1997.
NORINCO. Explosive test method: GJB 772A—97 ［S］. Beijing: Military Standard Publishing and Distribution Department of COSTIND, 1997.
［5］陈捷, 张朝阳. 炸药5秒延滞期爆发点的测量不确定度评定［J］. 计量与测试技术， 2009, 36（7）: 63-64.
CHEN J, ZHANG C Y. Evaluation of uncertatinty in the determination of the 5 s explosion temperature of explosive［J］. Metrology & Measurement Technique, 2009，36（7）: 63-64.
［6］肖忠良.火炸药导论［M］.北京：国防工业出版社，2020: 260-268.
［7］SANTIAGO , RAZO-HERN-NDEZ R S, PASTOR N. Revealing the structural contributions to thermal adaptation of the TATA-box binding protein: molecular dynamics and QSPR analyses ［J］. Journal of Chemical Information and Modeling, 2020, 60: 866-879.
［8］QIN S Y, JIN T Y, LEHN R C V, et al. Predicting critical micelle concentrations for surfactants using graph convolutional neural networks ［J］. Journal of Physical Chemistry B, 2021, 125(37): 10610-10620.
［9］MATHIEU D. Sensitivity of energetic materials: theoretical relationships to detonation performance and molecular structure［J］. Industrial & Engineering Chemistry Research, 2017, 56(29): 8191-8201.
［10］FAYET G, KNORR A, ROTUREAU P. First QSPR models to predict the thermal stability of potential selfreactive substances ［J］. Process Safety and Environmental Protection, 2022, 163: 191-199.
［11］DUCAMP M, COUDERT F. Prediction of thermal properties of zeolites through machine learning［J］. The Journal of Physical Chemistry C, 2022, 126(3): 1651-1660.
［12］第五机械工业部第二零四研究所. 火炸药手册: 第一分册［M］. 1981: 3-179.
［13］韦爱勇. 单质与混合火工药剂［M］.哈尔滨: 哈尔滨工程大学出版社, 2014: 24-182.
［14］SHAHLAIE M,FASSIHI A, POURHOSSEIN A, et al. Statistically validated QSAR study of some antagonists of the human CCR5 receptor using least square support vector machine based on the genetic algorithm and factor analysis ［J］. Medicinal Chemistry Research, 2013, 22: 1399-1414.
［15 ] ARORA A, LIN T S, REBELLO N J, et al. Random forest predictor for diblock copolymer phase behavior［J］. ACS Macro Letters, 2021, 10(11): 1339-1345.
［16］张学工，汪小我.模式识别: 模式识别与机器学习［M］. 北京: 清华大学出版社, 2021: 120-137.
ZHANG X G, WANG X W. Pattern recognition: pattern recognition and machine learning ［M］. Beijing: Tsinghua University Press, 2021: 120-137.
［17］LI Y, FEI C H, MAO C Q, et al. Physicochemical parameters combined flash GC e-nose and artificial neural network for quality and volatile characterization of vinegar with different brewing techniques ［J］. Food Chemistry, 2022, 374: 131658.
［18］时静洁. 有机物的结构与粘度等安全参数的定量构效关系模型研究［D］. 南京: 南京理工大学, 2015.
SHI J J. Researches on the quantitative relationship models between structures and viscosity and other safety parameters of organic compounds ［D］. Nanjing: Nanjing University of Science and Technology, 2015.
［19］钱博文, 陈利平, 陈网桦. 基于遗传算法的人工神经网络预测多硝基化合物撞击感度［J］.含能材料, 2016, 24(7): 644-650.
QIAN B W, CHEN L P, CHEN W H. Prediction of impact sensitivity of polynitro compounds by artificial neural network based on the genetic algorithm ［J］. Chinese Journal of Energetic Materials, 2016, 24(7): 644-650.
［20］HAO S, HAN X, LIU H, et al. Prediction and sensitivity analysis of the cetane number of different biodiesel fuels using an artificial neural network ［J］. Energy & Fuels, 2021, 35(21): 17711-17720.
［21］蔺向阳，郑文芳.火药学［M］.北京: 化学工业出版社, 2020: 240-250.
［22］CHIRICO N, GRAMATICA P. Real external predictivity of QSAR models. Part 2. New intercomparable thresholds for different validation criteria and the need for scatter plot inspection ［J］. Journal of Chemical Information and Modeling, 2012, 52(8): 2044-2058.
［23］CHIAPPINI F A, ALLEGRINI F, GOICOECHEA H C, et al. Sensitivity for multivariate calibration based on multilayer perceptron artificial neural networks ［J］. Analytical Chemistry, 2020, 92 (18): 12265-12272.
［24］时静洁, 陈利平, 陈网桦. 基于迭代自组织数据分析算法与蚁群算法建立有机物黏度的QSPR模型［J］. 物理化学学报, 2014, 30(5): 803-810.
SHI J J, CHEN L P, CHEN W H. QSPR models of compound viscosity based on iterative self-organizing data analysis technique and ant colony algorithm ［J］.? Acta Physico-Chimica Sinica, 2014, 30(5): 803-810.

备注/Memo

备注/Memo:
收稿日期：2022-09-19
第一作者：程露萍(1998－),女,硕士研究生，主要从事安全评价研究。E-mail:18768160440@163.com
通信作者：何中其(1978－),男,博士,主要从事爆炸作用及其应用、安全技术及工程研究。E-mail:hzq555@163.com
更新日期/Last Update: 2023-03-30