Prediction of the self-accelerating decomposition temperature of organic peroxides using QSPR models
- 485 Downloads
Organic peroxides are widely used unstable compounds that have caused many serious industrial incidents. Self-accelerating decomposition temperature (SADT) is one of the most important parameters to describe the thermal instability hazards of organic peroxides. However, it is very difficult to obtain experimental data of SADT due to high cost, the time involved and safety issues of laboratory tests. Quantitative structure–property relationship (QSPR) models have been proposed as an effective tool to predict thermal stability of organic peroxides. In this work, a dataset including 50 SADTs of organic peroxides was built and their molecular descriptors were calculated at B3LYP/6-31G(d) level using Gaussian 09. Two novel predictive models were successfully developed by multiple linear regression (MLR) and support vector machine (SVM). Both models were validated to have an excellent goodness of fit, internal robustness and external predictive ability. The MLR model was a linear equation with the average absolute error of training set and test set being 9.78 and 9.91, while the SVM model was a nonlinear model with the two values being 4.33 and 5.75, respectively. The SVM model has higher accuracy and is much more effective than the MLR model. This research provides general guidelines and methodology of establishing QSPR models to predict SADTs for other organic peroxides and unstable hazardous chemicals.
KeywordsSelf-accelerating decomposition temperature (SADT) Thermal analysis and stability Quantitative structure–property relationship (QSPR) Organic peroxides Gaussian 09
- 8.Foresman JB, Frisch AE. Exploring chemistry with electronic structure methods. 2nd ed. Gaussian Inc.: Pittsburgh, PA; 1996.Google Scholar
- 10.Ochterski JW. Thermochemistry in Gaussian. Gaussian Inc.; 2000. http://www.lct.jussieu.fr/manuels/Gaussian03/g_whitepap/thermo/thermo.pdf. Accessed 2 June 2000.
- 18.The PubChem Project. https://pubchem.ncbi.nlm.nih.gov/#opennewwindow.
- 19.Frisch MJ, Trucks GW, Schlegel HB, Scuseria GE, Robb MA, Cheeseman JR, Scalmani G, Barone V, Mennucci B, Petersson GA, Nakatsuji H, Caricato M, Li X, Hratchian HP, Izmaylov AF, Bloino J, Zheng G, Sonnenberg JL, Hada M, Ehara M, Toyota K, Fukuda R, Hasegawa J, Ishida M, Nakajima T, Honda Y, Kitao O, Nakai H, Vreven T, Montgomery JA Jr, Peralta JE, Ogliaro F, Bearpark M, Heyd JJ, Brothers E, Kudin KN, Staroverov VN, Keith T, Kobayashi R, Normand J, Raghavachari K, Rendell A, Burant JC, Iyengar SS, Tomasi J, Cossi M, Rega N, Millam JM, Klene M, Knox JE, Cross JB, Bakken V, Adamo C, Jaramillo J, Gomperts R, Stratmann RE, Yazyev O, Austin AJ, Cammi R, Pomelli C, Ochterski JW, Martin RL, Morokuma K, Zakrzewski VG, Voth GA, Salvador P, Dannenberg JJ, Dapprich S, Daniels AD, Farkas O, Foresman JB, Ortiz JV, Cioslowski J, Fox DJ. Gaussian, Inc., Wallingford; 2010.Google Scholar
- 25.Vapnik V. The nature of statistical learning theory. 2nd ed. Berlin: Springer; 2013.Google Scholar
- 26.Vapnik VN, Vapnik V. Statistical learning theory. London: Wiley; 1998.Google Scholar
- 33.Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011;2(3):27:1–27:27. http://www.csie.ntu.edu.tw/~cjlin/libsvm.