Artificial neural network prediction of steric hindrance parameter of polymers

作者：Yu, Xinliang^*; Yu, Wenhao; Yi, Bing; Wang, Xueye

来源：CHEMICAL PAPERS, 2009, 63(4): 432-437.

DOI：10.2478/s11696-009-0036-4

• artificial neural network
• DFT
• QSPR
• steric hindrance parameter

An artificial neural network (ANN) model for modeling and prediction of the steric hindrance parameter sigma of polymers with three quantum chemical descriptors, the average polarizability of a molecule alpha, entropy S, and dipole moment mu, was developed. These descriptors were calculated from the monomers of the respective polymers according to the density functional theory at the B3LYP level of the theory with the 6-31G(d) basis set. Optimal conditions were obtained by adjusting various parameters by trial-and-error. Simulated with the final optimum BP neural network [3-1-1], the results show that the predicted sigma values are in good agreement with the experimental ones, with the root mean square (rms) error being 0.080 (R = 0.945) for the training set, and 0.078 (R = 0.918) for the test set, which indicates that the proposed model has better predictive capability than the existing one.

• 出版日期2009-8
• 单位湖南工程学院; 武汉大学; 湘潭大学