Backpropagation Neural Networks Study On The Correlation Between Impact Sensitivity Of Energetic Explosives And Molecular Structure

The study on the correlation between impact sensitivity of energetic materials and molecular structures has recently been an on-going area of research in explosive theory. Since storage, synthesis, and application of energetic materials are significantly affected by impact or shock sensitivity, the researches about the impact sensitivity is of primary importance. Although many works succeeded in finding a certain kind of correlations between some of specific molecular properties and the impact sensitivity, many of the correlation almost existed in a certain type of explosive and the number of the explosive in each type was usually small. In addition, most of the works simply examined the correlation between one or two molecular properties and impact sensitivity of explosive compounds.The neural network is a nonlinear function of many parameters that maps particular inputs (in our case, molecular properties) to an output (in our case, impact sensitivity). Neural networks have been applied to various engineering problems, such as robotics, pattern recognition, speech, etc. But for the explosive engineering, there exists few reports about the impact sensitivity based on neural networks method.It is being demonstrated with increasing frequency that density functional theory (DFT) can be an effective approach to compute reaction energetics. A key advantage is that density functional procedures can be applied to much larger systems. In this paper, we will utilize the back-propagation neural network (BP) to analyze the correlation between impact sensitivity of nitramines and molecular properties.Backpropagation neural networks are firstly used to study about the correlation between impact sensitivity and molecular properties of twenty-nine explosives molecules. All the molecular properties are calculated via B3P86/6-31G**. Eight different sets of molecular properties are utilized to train and test our net. The training and testing results show that the input vector with the descriptor (HOMO-LUMO)*BDE can obtain the relatively better outcomes than other descriptors after training and testing several times. It further indicates that with the same net structure and training parameters, molecular descriptor (HOMO-LUMO)*BDE has the strongest correlation with impact sensitivity of explosives.Besides, based on our former research, we again utilize the above method to study the correlation order between impact sensitivity and 33 nitramine explosives the molecular properties via B3P86/6-31G**. The training and testing results show that the input vector with the descriptorâ–³E can obtain the relatively better outcomes. It further indicates that molecular descriptorâ–³E has the strongest correlation with impact sensitivity of explosives, which indicates thatâ–³E can be a symbolic index to predict the impact sensitivity of nitramines.