Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models

Hydroxyl-terminated-polybutadiene (HTPB)-based composite solid propellants are extensively used in aerospace and defense applications due to their high energy density, thermal stability, and processability. However, the presence of highly sensitive energetic components in their formulations leads to...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Wang, Kai Cui, Jinxiang Liu, Wenhai He, Qiuyu Zhang, Weihai Zhang, Tianshuai Wang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/12/7/622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067401189621760
author Fei Wang
Kai Cui
Jinxiang Liu
Wenhai He
Qiuyu Zhang
Weihai Zhang
Tianshuai Wang
author_facet Fei Wang
Kai Cui
Jinxiang Liu
Wenhai He
Qiuyu Zhang
Weihai Zhang
Tianshuai Wang
author_sort Fei Wang
collection DOAJ
description Hydroxyl-terminated-polybutadiene (HTPB)-based composite solid propellants are extensively used in aerospace and defense applications due to their high energy density, thermal stability, and processability. However, the presence of highly sensitive energetic components in their formulations leads to a significant risk of accidental ignition under electrostatic discharge, posing serious safety concerns during storage, transportation, and handling. To address this issue, this study explores the prediction of electrostatic sensitivity in HTPB propellants using machine learning techniques. A dataset comprising 18 experimental formulations was employed to train and evaluate six machine learning models. Among them, the Random Forest (RF) model achieved the highest predictive accuracy (R<sup>2</sup> = 0.9681), demonstrating a strong generalization capability through leave-one-out cross-validation. Feature importance analysis using SHAP and Gini index methods revealed that aluminum, catalyst, and ammonium perchlorate were the most influential factors. These findings provide a data-driven approach for accurately predicting electrostatic sensitivity and offer valuable guidance for the rational design and safety optimization of HTPB-based propellant formulations.
format Article
id doaj-art-3cacd7664669439d87e4e87cc08090dc
institution DOAJ
issn 2226-4310
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-3cacd7664669439d87e4e87cc08090dc2025-08-20T02:48:19ZengMDPI AGAerospace2226-43102025-07-0112762210.3390/aerospace12070622Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning ModelsFei Wang0Kai Cui1Jinxiang Liu2Wenhai He3Qiuyu Zhang4Weihai Zhang5Tianshuai Wang6Xi’an Key Laboratory of Functional Organic Porous Materials, School of Chemistry and Chemical Engineering, Northwestern Polytechnical University, Xi’an 710000, ChinaXi’an Key Laboratory of Functional Organic Porous Materials, School of Chemistry and Chemical Engineering, Northwestern Polytechnical University, Xi’an 710000, ChinaXi’an North Huian Chemical Industry Co., Ltd., Xi’an 710302, ChinaXi’an North Huian Chemical Industry Co., Ltd., Xi’an 710302, ChinaXi’an Key Laboratory of Functional Organic Porous Materials, School of Chemistry and Chemical Engineering, Northwestern Polytechnical University, Xi’an 710000, ChinaXi’an North Huian Chemical Industry Co., Ltd., Xi’an 710302, ChinaXi’an Key Laboratory of Functional Organic Porous Materials, School of Chemistry and Chemical Engineering, Northwestern Polytechnical University, Xi’an 710000, ChinaHydroxyl-terminated-polybutadiene (HTPB)-based composite solid propellants are extensively used in aerospace and defense applications due to their high energy density, thermal stability, and processability. However, the presence of highly sensitive energetic components in their formulations leads to a significant risk of accidental ignition under electrostatic discharge, posing serious safety concerns during storage, transportation, and handling. To address this issue, this study explores the prediction of electrostatic sensitivity in HTPB propellants using machine learning techniques. A dataset comprising 18 experimental formulations was employed to train and evaluate six machine learning models. Among them, the Random Forest (RF) model achieved the highest predictive accuracy (R<sup>2</sup> = 0.9681), demonstrating a strong generalization capability through leave-one-out cross-validation. Feature importance analysis using SHAP and Gini index methods revealed that aluminum, catalyst, and ammonium perchlorate were the most influential factors. These findings provide a data-driven approach for accurately predicting electrostatic sensitivity and offer valuable guidance for the rational design and safety optimization of HTPB-based propellant formulations.https://www.mdpi.com/2226-4310/12/7/622hydroxyl-terminated polybutadiene solid propellantsstatic sensitivitymachine learning
spellingShingle Fei Wang
Kai Cui
Jinxiang Liu
Wenhai He
Qiuyu Zhang
Weihai Zhang
Tianshuai Wang
Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
Aerospace
hydroxyl-terminated polybutadiene solid propellants
static sensitivity
machine learning
title Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
title_full Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
title_fullStr Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
title_full_unstemmed Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
title_short Prediction of Propellant Electrostatic Sensitivity Based on Small-Sample Machine Learning Models
title_sort prediction of propellant electrostatic sensitivity based on small sample machine learning models
topic hydroxyl-terminated polybutadiene solid propellants
static sensitivity
machine learning
url https://www.mdpi.com/2226-4310/12/7/622
work_keys_str_mv AT feiwang predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT kaicui predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT jinxiangliu predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT wenhaihe predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT qiuyuzhang predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT weihaizhang predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels
AT tianshuaiwang predictionofpropellantelectrostaticsensitivitybasedonsmallsamplemachinelearningmodels