A novel hybrid machine learning model for predicting rate constants of the reactions between alkane and CH3 radical. (15th August 2022)

• Record Type: Journal Article
• Authors: Yu, Jinhui; Shan, Dezun; Song, Hongwei; Yang, Minghui
• Is Part Of: Fuel. Volume 322(2022)
• Publication Date: 2022-08-15
• Subjects: Machine learning -- Artificial neural network -- Combustion -- Alkane -- Methyl radical -- Rate constant; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2022.124150
• Languages: English
• ISSNs: 0016-2361

Abstract

Graphical abstract: Highlights: Developing a novel and robust hybrid XGB-FNN model for predicting rate constants of combustion reactions. Providing a rate constant dataset for the important combustion reactions between alkane and CH3 radical. Screening six effective descriptors suitable for describing the H-abstraction reactions by free radicals. Abstract: The rate constants of H-abstraction reactions of alkanes by free radicals are crucial for optimizing combustion reaction network, improving combustion efficiency and designing aero engines. In this study, three different machine learning (ML) algorithms-Feedforward Neural Network (FNN), eXtreme Gradient Boosting (XGB) and Random Forest -were used to develop ML models for predicting the rate constants of reactions of alkane and CH3 radical. The results showed that the FNN algorithm with 6 descriptors has better overall performance than the other two ML algorithms. A novel hybrid ML model combining FNN with XGB (XGB-FNN) was then developed, by which the prediction accuracy was visibly improved (p-value < 0.05). The average deviation of XGB-FNN model on the prediction set is 42.35%. The rate constants of the primary hydrogen abstraction reactions between CH3 radical and normal alkanes with 5 ∼ 12 carbon atoms were predicted over a temperature range of 300 ∼ 2500 K, which follow well the modified three-parameter Arrhenius equation and/or agree well with available experimental rate constants, indicating that the hybrid XGB-FNN model is robust in predicting the rate constants in the temperature range of combustion.