Machine learning-quantitative structure property relationship (ML-QSPR) method for fuel physicochemical properties prediction of multiple fuel types
نویسندگان
چکیده
A machine learning-quantitative structure property relationship (ML-QSPR) method is proposed to predict 15 fuel physicochemical properties of 23 types. QSPR-UOB 3.0 functional group classification system developed extract and digitalize the molecular feature. ML algorithms are used map feature as well model parameter tuning. UOB Fuel Property Database (1797 pure compounds 465 mixtures) established provide massive data for training. Cross-validation chosen examine predictive precision, avoid overfitting estimate inter/extrapolation capacity. ML-QSPR has 4 distinct advantages compared published statistical methods: (1) It applies CN, RON, MON, Tm, Tb, ?Hvap, surface tension ?, LHV, liquid density ?, YSI, IT, FP, VP, LFL, UFL. (2) types alkanes, cycloalkanes, alkenes, cyclic alkadienes, alkynes, alcohols, cycloalcohols, aldehydes, ketones, ketone, saturated esters, unsaturated acyclic ethers, furans, other aromatics, carbonate ester, carboxylic anhydride, peroxide, hydroperoxide, polyfunctionals, acids. (3) High accuracy achieved average R2 reaches 0.9816. (4) The regression models display reasonable interpolation extrapolation capacity test new molecules. success attributed 2 key factors: accounts contribution structural features, interaction reactivity. accurately capture dependence on chemical structures.
منابع مشابه
Quantitative Structure Properties Relationship QSPR Models for Predicting Physicochemical Properties of some Organic Hydrocarbons
متن کامل
بوزدایی از fuel oil deodorization of fuel oil
مطالعات و بررسی های انجام گرفته نشان می دهد ترکیبات بودار موجود در fuel oil عمدتا ترکیبات سولفوردار سخت مثل تیوفن، دی متیل بنزوتیوفن و ... بوده و روشهای بوزدایی همچون استخراج با حلالهای اسیدی و بازی ، رقیق کاری با گازولین ، ماسکینگ با بوتیل استات نتایج چندان مطلوبی در بوزدایی از آن نشان نمی دهند.همچنین روش جذب سطحی برای بوزدایی fuel oil تنها با استفاده از جاذب هایی همچون بنتونیت و توفیت...
15 صفحه اولA Quantitative Structure-Property Relationship (QSPR) Study of Aliphatic Alcohols by the Method of Dividing the Molecular Structure into Substructure
A quantitative structure-property relationship (QSPR) analysis of aliphatic alcohols is presented. Four physicochemical properties were studied: boiling point (BP), n-octanol-water partition coefficient (lg P(OW)), water solubility (lg W) and the chromatographic retention indices (RI) on different polar stationary phases. In order to investigate the quantitative structure-property relationship ...
متن کاملQuantitative structure-property relationship (QSPR) model for predicting acidities of ketones
Ketones are one of the most common functional groups, and ketone-containing compounds are essential in both the nature and the chemical sciences. As such, the acidities (pKa) of ketones provide valuable information for scientists to screen for biological activities, to determine physical properties or to study reaction mechanisms. Direct measurements of pKa of ketones are not readily available ...
متن کاملQuantitative Structure-Property Relationship to Predict Quantum Properties of Monocarboxylic Acids By using Topological Indices
Abstract. Topological indices are the numerical value associated with chemical constitution purporting for correlation of chemical structure with various physical properties, chemical reactivity or biological activity. Graph theory is a delightful playground for the exploration of proof techniques in Discrete Mathematics and its results have applications in many areas of sciences. A graph is a ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Fuel
سال: 2021
ISSN: ['0016-2361', '1873-7153']
DOI: https://doi.org/10.1016/j.fuel.2021.121437