利用机器学习发现电喷推进器的推进剂

Rafid Bendimerad, Elaine Petro
{"title":"利用机器学习发现电喷推进器的推进剂","authors":"Rafid Bendimerad, Elaine Petro","doi":"arxiv-2408.16951","DOIUrl":null,"url":null,"abstract":"This study introduces a machine learning framework to predict the suitability\nof ionic liquids with unknown physical properties as propellants for\nelectrospray thrusters based on their molecular structure. We construct a\ntraining dataset by labeling ionic liquids as suitable (+1) or unsuitable (-1)\nfor electrospray thrusters based on their density, viscosity, and surface\ntension. The ionic liquids are represented by their molecular descriptors\ncalculated using the Mordred package. We evaluate four machine learning\nalgorithms: Logistic Regression, Support Vector Machine (SVM), Random Forest,\nand Extreme Gradient Boosting (XGBoost), with SVM demonstrating superior\npredictive performance. The SVM predicts 193 candidate propellants from a\ndataset of ionic liquids with unknown physical properties. Further, we employ\nShapley Additive Explanations (SHAP) to assess and rank the impact of\nindividual molecular descriptors on model decisions.","PeriodicalId":501304,"journal":{"name":"arXiv - PHYS - Chemical Physics","volume":"36 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Propellant Discovery For Electrospray Thrusters Using Machine Learning\",\"authors\":\"Rafid Bendimerad, Elaine Petro\",\"doi\":\"arxiv-2408.16951\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study introduces a machine learning framework to predict the suitability\\nof ionic liquids with unknown physical properties as propellants for\\nelectrospray thrusters based on their molecular structure. We construct a\\ntraining dataset by labeling ionic liquids as suitable (+1) or unsuitable (-1)\\nfor electrospray thrusters based on their density, viscosity, and surface\\ntension. The ionic liquids are represented by their molecular descriptors\\ncalculated using the Mordred package. We evaluate four machine learning\\nalgorithms: Logistic Regression, Support Vector Machine (SVM), Random Forest,\\nand Extreme Gradient Boosting (XGBoost), with SVM demonstrating superior\\npredictive performance. The SVM predicts 193 candidate propellants from a\\ndataset of ionic liquids with unknown physical properties. Further, we employ\\nShapley Additive Explanations (SHAP) to assess and rank the impact of\\nindividual molecular descriptors on model decisions.\",\"PeriodicalId\":501304,\"journal\":{\"name\":\"arXiv - PHYS - Chemical Physics\",\"volume\":\"36 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Chemical Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.16951\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Chemical Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.16951","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本研究介绍了一种机器学习框架,可根据分子结构预测物理性质未知的离子液体是否适合用作电喷雾推进器的推进剂。我们根据离子液体的密度、粘度和表面张力,将其标记为适合(+1)或不适合(-1)电喷雾推进器,从而构建了训练数据集。离子液体由使用 Mordred 软件包计算的分子描述符表示。我们评估了四种机器学习算法:我们评估了四种机器学习算法:逻辑回归、支持向量机 (SVM)、随机森林和极梯度提升 (XGBoost),其中 SVM 的预测性能更优。SVM 可从一组物理性质未知的离子液体中预测出 193 种候选推进剂。此外,我们还采用了沙普利相加解释(SHAP)来评估和排列单个分子描述符对模型决策的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Propellant Discovery For Electrospray Thrusters Using Machine Learning
This study introduces a machine learning framework to predict the suitability of ionic liquids with unknown physical properties as propellants for electrospray thrusters based on their molecular structure. We construct a training dataset by labeling ionic liquids as suitable (+1) or unsuitable (-1) for electrospray thrusters based on their density, viscosity, and surface tension. The ionic liquids are represented by their molecular descriptors calculated using the Mordred package. We evaluate four machine learning algorithms: Logistic Regression, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost), with SVM demonstrating superior predictive performance. The SVM predicts 193 candidate propellants from a dataset of ionic liquids with unknown physical properties. Further, we employ Shapley Additive Explanations (SHAP) to assess and rank the impact of individual molecular descriptors on model decisions.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Phase-cycling and double-quantum two-dimensional electronic spectroscopy using a common-path birefringent interferometer Developing Orbital-Dependent Corrections for the Non-Additive Kinetic Energy in Subsystem Density Functional Theory Thermodynamics of mixtures with strongly negative deviations from Raoult's law. XV. Permittivities and refractive indices for 1-alkanol + n-hexylamine systems at (293.15-303.15) K. Application of the Kirkwood-Fröhlich model Mutual neutralization of C$_{60}^+$ and C$_{60}^-$ ions: Excitation energies and state-selective rate coefficients All-in-one foundational models learning across quantum chemical levels
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1