Abstract: In order to research the relationship between the physical values of coating aging in the natural environment and the environmental factors , a genetic BP neural network with real coding, arithmetic crossover, Gauss mutation and climbing operation is designed. The physical values of coating are calculated according to the environmental factors. Visual Studio 2008 is used for programming, and a program is developed for neural network training and prediction program. Finally, an example of field aging data of coating is used for network training and prediction. The results show that the proposed model can be used to calculate the ultimate life of the coating. The calculated values are similar to the measured values. The genetic neural network model can be used for prediction of coating life.

Key words: ordnance science and technology, stealth coating, aging-resistant performance, BP artificial neural network, genetic algorithm, life prediction