What question did this study set out to answer?

This research aims to create machine learning models to accurately predict the dynamic viscosity of fatty acid methyl esters based on various input parameters.

April 27, 2026Chemical Engineering & Technology1 citations

View Full Paper

Modeling Dynamic Viscosity of Pure Fatty Acid Methyl Esters via Robust Machine Learning Approaches

AAAhmad Adel Abu-SharehaUniversiti Sains Islam Malaysia MZMagdi E. A. ZakiImam Mohammad ibn Saud Islamic University RARaed AlfilhIraqi University

Key Points

This research aims to create machine learning models to accurately predict the dynamic viscosity of fatty acid methyl esters based on various input parameters.
Built models using decision tree, AdaBoost, elastic net, KNN, random forest, CNN, support vector regression, and MLP-ANN
Utilized 488 data points for training and validation, implementing five-fold cross-validation
Evaluated model performance with metrics like R², mean squared error, and average absolute relative error.
MLP-ANN achieved the highest accuracy with R² = 0.9987 and MSE = 0.0038
Decision tree and AdaBoost models exhibited higher errors; elastic net was the least effective with R² = 0.8486
Pressure was identified as the most significant parameter affecting viscosity, validated by SHAP analysis.

Abstract

ABSTRACT Fatty acid methyl esters (FAMEs) are renewable, biodegradable biofuels. This study built machine learning models (DT, AdaBoost, EL, K ‐nearest neighboring ( K NN), random forest (RF), EN, CNN, SVR, and MLP‐ANN) to predict their dynamic viscosity using 488 literature data points. Inputs: temperature, pressure, molar mass, and C/H/O fractions. Models used five‐fold cross‐validation (90% training/validation, 10% testing). Metrics: R 2 , mean squared error (MSE), AARE%. MLP‐ANN performed best ( R 2 = 0.9987, MSE = 0.0038, and AARE = 1.68%). DT and AdaBoost showed higher errors; elastic net was weakest ( R 2 = 0.8486, AARE ≈ 25.78%). Pressure was the most impactful parameter, followed by temperature. SHapley Additive exPlanations (SHAP) analysis confirmed pressure as dominant. The framework is robust, accurate, and cost‐effective across broad thermodynamic conditions.

AIに質問

Bookmark

View Full Paper

Cite This Study

Abu-Shareha et al. (Wed,) studied this question.

synapsesocial.com/papers/69eefd43fede9185760d4010 https://doi.org/https://doi.org/10.1002/ceat.70220

AIに質問

Bookmark

View Full Paper