Molecular kinematic viscosity prediction of natural ester insulating oil based on sparse Machine learning models

The high viscosity property of natural ester insulating oils can be improved by means of molecular structure modification. However, it is difficult to find the optimal molecular structure that meets the conditions in the vast chemical space by relying on macroscopic experiments. Herein, the kinematic viscosity prediction models of triglyceride molecules based on sparse machine learning methods are proposed in this paper. Firstly, the mo-lecular dynamics technique is used to simulate the kinematic viscosity (-20 & DEG;C to 40 & DEG;C) of the main 20 triglyceride molecules in natural ester insulating oil, which provides extensive characterization data for subsequent model training. Secondly, the molecular descriptors are calculated for each triglyceride molecule based on density functional theory (DFT). Thirdly, four sparse feature selection methods (Boruta, RFECV, Pearson correlation coefficient, and mutual information) are used to identify the most relevant molecular descriptors for the kine-matic viscosity of natural ester insulating oil and further analysis is performed. Finally, quantitative structur-e-property relationship (QSPR) models are constructed using automated machine learning methods to achieve efficient and accurate prediction of kinematic viscosity (average R2 reached 0.96). This study provides certain mechanistic explanations from the perspective of molecular descriptors and provides a predictive model basis for the viscosity modification of natural ester molecules, which serves as a theoretical guide to improve the kine-matic viscosity of natural ester insulating oil.

Automated summary

In this paper, kinematic viscosity prediction models of triglyceride molecules based on sparse machine learning methods are proposed. Molecular dynamics simulations are used to obtain extensive characterization data for main 20 triglyceride molecules in natural ester insulating oil. Sparse feature selection methods are employed to identify the most relevant molecular descriptors, and quantitative structure-property relationship models are constructed for efficient and accurate kinematic viscosity prediction.