Machine learning prediction of hydrocarbon mixture lower flammability limits using quantitative structure‐property relationship models

2019 ◽  
Vol 39 (2) ◽  
Author(s):  
Zeren Jiao ◽  
Shuai Yuan ◽  
Zhuoran Zhang ◽  
Qingsheng Wang
Keyword(s):  
Machine Learning ◽  
Hydrocarbon Mixture ◽  
Quantitative Structure ◽  
Structure Property ◽  
Flammability Limits ◽  
Quantitative Structure Property Relationship ◽  
Property Relationship ◽  
Structure Property Relationship

scholarly journals Prediction of Lower Flammability Limits for Binary Hydrocarbon Gases by Quantitative Structure—Property Relationship Approach

Molecules ◽  
2019 ◽  
Vol 24 (4) ◽  
pp. 748 ◽  
Author(s):  
Yong Pan ◽  
Xianke Ji ◽  
Li Ding ◽  
Juncheng Jiang
Keyword(s):  
Molecular Structures ◽  
Quantitative Structure ◽  
Structure Property ◽  
Flammability Limits ◽  
Hydrocarbon Gases ◽  
Quantitative Structure Property Relationship ◽  
Property Relationship ◽  
Structure Property Relationship ◽  
Mathematical Formulas ◽  
Lower Flammability Limit

The lower flammability limit (LFL) is one of the most important parameters for evaluating the fire and explosion hazards of flammable gases or vapors. This study proposed quantitative structure−property relationship (QSPR) models to predict the LFL of binary hydrocarbon gases from their molecular structures. Twelve different mixing rules were employed to derive mixture descriptors for describing the structures characteristics of a series of 181 binary hydrocarbon mixtures. Genetic algorithm (GA)-based multiple linear regression (MLR) was used to select the most statistically effective mixture descriptors on the LFL of binary hydrocarbon gases. A total of 12 multilinear models were obtained based on the different mathematical formulas. The best model, issued from the norm of the molar contribution formula, was achieved as a six-parameter model. The best model was then rigorously validated using multiple strategies and further extensively compared to the previously published model. The results demonstrated the robustness, validity, and satisfactory predictivity of the proposed model. The applicability domain (AD) of the model was defined as well. The proposed best model would be expected to present an alternative to predict the LFL values of existing or new binary hydrocarbon gases, and provide some guidance for prioritizing the design of safer blended gases with desired properties.

Quantitative Structure- Property Relationship (QSPR) Investigation of Camptothecin Drugs Derivatives

2018 ◽  
Vol 21 (7) ◽  
pp. 533-542 ◽  
Author(s):  
Neda Ahmadinejad ◽  
Fatemeh Shafiei ◽  
Tahereh Momeni Isfahani
Keyword(s):  
Thermodynamic Properties ◽  
Predictive Ability ◽  
Total Sample ◽  
Basis Sets ◽  
Quantitative Structure ◽  
Structure Property ◽  
Quantitative Structure Property Relationship ◽  
Chemical Structures ◽  
Property Relationship ◽  
Structure Property Relationship

Aim and Objective: Quantitative Structure- Property Relationship (QSPR) has been widely developed to derive a correlation between chemical structures of molecules to their known properties. In this study, QSPR models have been developed for modeling and predicting thermodynamic properties of 76 camptothecin derivatives using molecular descriptors. Materials and Methods: Thermodynamic properties of camptothecin such as the thermal energy, entropy and heat capacity were calculated at Hartree–Fock level of theory and 3-21G basis sets by Gaussian 09. Results: The appropriate descriptors for the studied properties are computed and optimized by the genetic algorithms (GA) and multiple linear regressions (MLR) method among the descriptors derived from the Dragon software. Leave-One-Out Cross-Validation (LOOCV) is used to evaluate predictive models by partitioning the total sample into training and test sets. Conclusion: The predictive ability of the models was found to be satisfactory and could be used for predicting thermodynamic properties of camptothecin derivatives.

Sign in / Sign up

Export Citation Format

Share Document