Prediction of the auto-ignition temperature of binary liquid mixtures based on the quantitative structure–property relationship approach
- 19 Downloads
The auto-ignition temperature (AIT) is one of the most important parameters in flammability risk assessment and management in the chemical process. Therefore, in this work, quantitative structure–property relationship approach was employed to estimate the AIT of binary liquid mixtures only based on the information of molecular structures. Various kinds of molecular descriptors were calculated using Dragon 6.0 software after the geometry optimization of molecular structures. Genetic algorithm (GA) was used to select the best subset of descriptors which have a significant contribution to AIT. Two novel models including multiple linear regression (MLR) model and support vector machine (SVM) model were developed based on the GA-selected molecular descriptors. The resulted models showed satisfied goodness-of-fit, robustness and external predictability after the rigorous verification based on appropriate criteria. The MLR model showed great performance with the average absolute error (AAE) of training set and test set being 13.420 °C and 15.076 °C, while the AAE of SVM model was reduced to 5.629 °C and 9.206 °C, respectively. The two optimal models could provide a convenient and effective way to predict the AIT of binary liquid mixtures as well as guidance for the safety design of the chemical process industry.
KeywordsAuto-ignition temperature Quantitative structure–property relationship Binary liquid mixtures Genetic algorithm Support vector machine
This work was financially supported by the Fundamental Research Funds for the Central Universities (No. DUT19LAB27).
This research was supported by National Natural Science Fund of China (No. 21576136, 51974165), and National Program on Key Basic Research Project of China (2017YFC0804801, 2016YFC0801502).
- 4.ASTM International, ASTM standard test method E659-15, West Conshohocken, PA, 2000.Google Scholar
- 22.Wang BB, Park H, Xu KL, et al. Prediction of lower flammability limits of blended gases based on quantitative structure-property relationship. J Therm Anal Calorim. 2018;132:1124–30.Google Scholar
- 24.Ye LT, Pan Y, Jiang JC. Experimental determination and calculation of auto-ignition temperature of binary flammable liquid mixtures. Pet Process Sect. 2015;31:753–9.Google Scholar
- 29.Todeschini R, Consonni V, Pavan M. DRAGON 6 user’s manual. http://www.talete.mi.it/help/dragon_help/index.html. 2010.
- 34.Vapnik VN. Statistical learning theory. New York: Wiley; 1998.Google Scholar
- 40.Hsu CW, Chang CC, Lin CJ. A practical guide to support classification. http://www.csie.ntu.edu.tw/~cjlin. 2016.
- 41.OECD. Guidance document on the validation of (quantitative) structure–activity relationship [(Q)SAR] models. 2007.Google Scholar
- 44.Tropsha A, Gramatica P, Gombar VK. The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. Mol Inf. 2003;22(1):69–77.Google Scholar
- 54.Hair JF, Black B, Bebin BJ, et al. Multivariate data analysis. Pearson new international edition (7th edn). 2013.Google Scholar