A methodfor optimizing the prediction ofimpact sensitivity ofexplosive molecules hv neural networks is presented. The database we used consisted 0/272 molecules containing C,H,N,0 ofknown sensitivity and belonging to several chemicalfamilies. Pertinent molecular desriptors were selected by a preliminary multilinear treatment. The effects of the network's topology, the extent of the training, the choice of descriptors were examined and optimized. The predictions are satisfactory with a correlation coefficient of 0.94 obtained through cross-validation. Moreover 95% of compounds are correctiy classißed in a 3sensitivity scale and the remaining 5% are classißed äs ambiguous which is very encouragingfor a real worid implementation. The neural networks approach proves more accurate and more general than previous methods.

A new method for predicting the impact sensitivity of explosive molecules is presented. This method makes use of a network of formal neurons. The experiment uses 124 molecules belonging to different families. The molecular descriptors taken into account are the molecule's oxygen balance and the enumeration of certain groups. The results obtained are satisfactory: 80% of the molecules are correctly classed on a scale of four sensitivities. Comparison with a multivariate linear regression analysis gives a slight advantage to the neural network method.

No abstract