A New Machine Learning Algorithm to Optimize A Reduced Mechanism of 2-Butanone and the Comparison with Other Algorithms

Abstract

View Article Online 2-butanone (methyl ethyl ketone) has been identified as a potential alternative fuel and fuel tracer in recent studies. In this work, a reduced mechanism containing 50 species and 190 reactions for 2-butanone is developed for the first time. The raw reduced mechanism is built in three parts using decoupling methodology, a reduced CC sub-mechanism, a reduced CC sub-mechanism and a detailed H /CO/C sub-4 n 2 3 2 1 mechanism. Subsequently, the self-adaptive differential evolution algorithm of machine learning is proposed for optimizing the reaction rates of 31 reactions in the CC sub-mechanism to predict the ignition delay times and laminar flame speeds in constant volume bombs. The 4 n optimized reduced mechanism is validated by the ignition delay times in shock tubes and laminar flame speeds in constant volume bombs. The results of the optimized reduced mechanism are similar to those of the detailed mechanism, which show it is reliable. Moreover, the performance of the self-adaptive differential evolution algorithm is much better than the genetic algorithm and the particle swarm optimization.

The Weighted Values of Solar Evaporation’s Environment Factors Obtained by Machine Learning

“…It can be concluded that a more accurate calculation by machine learning requires more complete data. Compared to other fields such as materials, [29,30] they have a complete database of physical properties and theoretical calculation methods. However, in the current study, the shortage of reported data is a hard problem because authors do not provide exact values of some descriptors.…”

Physical Modifications and Algorithmic Predictions behind Further Advancing 2D Water Splitting Photocatalyst: An Overview

“…A self-adaptive differential evolution algorithm is used by Wang et al in optimizing a reduced mechanism of 2-Butanone. [110] Zhang et al came up with an overview of machine learning methods for predicting the thermal conductivity of different alloys, compounds, composites, and alloys. [111] Pilania et al combined linear least square regression with kernel ridge regression in the bandgap prediction of double perovskites.…”

Machine Learning to Predict the L-Point Direct Bandgap of Bi1-xSbx Nanomaterials

“…However, the strong correlation between the electrons and holes at the L-point are making it challenging to accurately and efficiently predict the bandgap either with ab initio calculations or with k•p perturbations. [5][6][7][8] With the recent rapid development of artificial intelligence, many black-box and phenomenological tools have been created and accepted by researchers to predict various materials properties in an economical and efficient manner [9][10][11][12][13][14][15][16][17][18][19][20][21][22] using machine learning methodologies. [23][24][25][26][27][28] Owolabi et al [29] have used support vector (SV) regression to predict bandgaps of doped TiO 2 semiconductors and to generate the crystal lattice parameters of pseudo-cubic/cubic perovskites.…”