| 注册
首页|期刊导航|含能材料|基于机器学习的NEPE推进剂燃速预测与配方筛选

基于机器学习的NEPE推进剂燃速预测与配方筛选

陈少臣 李铁斌 高素琪 彭君晟 赵向阳 严永庆 徐鹏程 李军

含能材料2026,Vol.34Issue(10):1160-1172,13.
✕
含能材料2026,Vol.34Issue(10):1160-1172,13.DOI:10.11943/CJEM2026101

基于机器学习的NEPE推进剂燃速预测与配方筛选

Predicting the Burning Rate of NEPE Propellant and Formulation Screening Based on Machine Learning Models

陈少臣 1李铁斌 1高素琪 1彭君晟 1赵向阳 1严永庆 1徐鹏程 1李军1

作者信息

  • 1. 湖北航天化学技术研究所,湖北 襄阳 441003||航天化学能源全国重点实验室,湖北 襄阳 441003
  • 折叠

摘要

Abstract

To reduce the cost and cycle time of iterative design experiments for composite solid propellant(CSP)formulations,this study combines machine learning with virtual formulation generation algorithms to conduct high-throughput virtual screen-ing of nitrate ester plasticized polyether(NEPE)propellant burning rate performance and formulations.First,a dataset was con-structed using 85 experimental data samples of NEPE propellants,with formulation composition,theoretical molar mass(MT),and working pressure(P)as inputs.A gradient boosting regression tree(GBRT)model was developed to predict the burning rate of NEPE propellants,and the Shapley Additive Explanations(SHAP)method was employed to calculate feature importance and identify key factors influencing burning rate.Subsequently,a constrained grid search algorithm was used to generate a large num-ber of virtual formulations,and the GBRT model was applied to calculate the burning rates of all virtual formulations at multiple working pressures and the burning rate pressure exponents across various pressure ranges.Finally,virtual formulations were fil-tered and ranked according to different screening criteria.The results show that the GBRT model achieved a coefficient of deter-mination of 0.980,mean absolute error of 0.427 mm·s-1,root mean square error of 0.574 mm·s⁻¹,and symmetric mean abso-lute percentage error of 6.972%on the test set.P,MT,and the mass percentage of Φ-Pb were identified as the three most impor-tant features.Using the constrained grid search algorithm,377,127 virtual formulations were generated.After four rounds of screening(criteria:burning rate at 6 MPa within(10.00±0.10)mm·s-1,and burning rate pressure exponents below 0.5 across the ranges of 4-10,6-10,and 4-6 MPa),637 virtual formulations met the requirements.Finally,the top 10 virtual formula-tions were selected based on proximity to the target burning rate(10.00 mm·s-1)and the magnitude of burning rate pressure ex-ponents,respectively.The formulation screening framework proposed in this study provides an efficient and feasible pathway for achieving intelligent design of CSP formulations.

关键词

复合固体推进剂(CSP)/NEPE/燃速预测/机器学习/配方筛选

Key words

composite solid propellant(CSP)/NEPE/burning rate prediction/machine learning/formulation screening

分类

军事科技

引用本文复制引用

陈少臣,李铁斌,高素琪,彭君晟,赵向阳,严永庆,徐鹏程,李军..基于机器学习的NEPE推进剂燃速预测与配方筛选[J].含能材料,2026,34(10):1160-1172,13.

基金项目

湖北省自然科学基金-襄阳创新发展联合基金联合资助项目(2025AFD104) Hubei Provincial Natural Science Foundation and Xiangyang Innovation and Development Joint Fund of China(2025AFD104) (2025AFD104)

含能材料

1006-9941

访问量0
|
下载量0
段落导航相关论文