高等学校化学学报 ›› 2026, Vol. 47 ›› Issue (6): 20250297.doi: 10.7503/cjcu20250297

• 物理化学 • 上一篇    下一篇

基于机器学习方法的含能材料分解温度预测

郭莉莉1, 户梦倩1, 黄孟梅1, 卢艳华2, 李伟2, 张庆友1(), 郭翔2()   

  1. 1.河南大学河南省工业循环水处理工程研究中心,河南省环境污染防治材料国际联合实验室,开封 475004
    2.湖北航天化学技术研究所航天化学动力实验室,襄阳 441003
  • 收稿日期:2025-10-15 出版日期:2026-06-10 发布日期:2025-12-24
  • 通讯作者: 张庆友,郭翔 E-mail:zhqingyou@163.com;guoxiang@casc42.cn
  • 基金资助:
    中国航天化学动力实验室开放研究基金(120201B01)

Prediction of Decomposition Temperature of Energetic Materials Based on Machine Learning Methods

GUO Lili1, HU Mengqian1, HUANG Mengmei1, LU Yanhua2, LI Wei2, ZHANG Qingyou1(), GUO Xiang2()   

  1. 1.Henan Engineering Research Center of Industrial Circulating Water Treatment,Henan Joint International Research Laboratory of Environmental Pollution Control Materials,Henan University,Kaifeng 475004,China
    2.Science and Technology on Aerospace Chemical Power Laboratory,Hubei Institute of Aerospace Chemotechnology,Xiangyang 441003,China
  • Received:2025-10-15 Online:2026-06-10 Published:2025-12-24
  • Contact: ZHANG Qingyou, GUO Xiang E-mail:zhqingyou@163.com;guoxiang@casc42.cn
  • Supported by:
    the Open Research Fund of the Science and Technology on Aerospace Chemical Power Laboratory, China(120201B01)

摘要:

提出一种新型复合描述符系统, 构建了一个高性能的含能材料分解温度预测模型. 首先根据基团贡献理论提出了分子结构描述符, 随后引入键解离能(BDE)作为关键补充参数, 量化化学键强度对热稳定性的影响, 最后通过RDKit软件生成了RDKit描述符, 并将这3类描述符整合构建为一个多维特征集. 将该特征集分别提交给随机森林(RF)、 支持向量机(SVM)及偏最小二乘(PLS)构建多个预测模型, 并进行了系统性比较. 其中, 使用随机森林构建的模型取得了最佳结果, 其预测性能优于文献报道结果, 表明所提出的复合描述符能够有效地捕捉影响分解温度的关键因素. 此外, 借助沙普利加法解释(SHAP)可视化技术对最优模型进行了解析, 为理解含能材料的热稳定性机理提供了有价值的数据洞察.

关键词: 分解温度, 分子基团描述符, 定量构效关系, 随机森林

Abstract:

In this study, a novel composite descriptor system was suggested, and a high-performance prediction model for the decomposition temperature of energetic materials was constructed. First, molecular structure descriptors based on group contribution were proposed. Then, bond dissociation energy(BDE) was introduced as a key supplementary parameter to quantify the effect of bond strength on decomposition temperature. Finally, RDKit descriptors were generated using the RDKit software, ultimately integrating them into a multidimensional feature set. This feature set was submitted to random forest(RF), support vector machine(SVM), and partial least squares(PLS) individually to construct multiple prediction models and conduct a systematic comparison. Among them, the best results were obtained using the model built by RF. Its prediction performance was superior to the results reported in the literature, indicating that the proposed composite descriptors can effectively capture the key factors affecting the decomposition temperature. To further interpret the model and identify critical influencing factors, Shapley additive explanations(SHAP) visualization technology was employed to analyze the optimal model, thereby providing valuable data-driven insights into the thermal stability mechanisms of energetic materials.

Key words: Decomposition temperature, Molecular group descriptor, Quantitative structure-property relationship(QSPR), Random forest(RF)

中图分类号: 

TrendMD: