Penetration Depth Prediction of Infinite Thick Metal Target based on Prior Knowledge

The existing traditional penetration research of infinite thick metal target mainly includes experimental research and theoretical analysis methods. Penetration data need to be obtained through extensive experiments. There are many problems, such as high experimental cost, many measurement parameters and limited parameter range. The pure data-driven method based on artificial neural network needs a large amount of data for fitting, and the effect is poor in low data area. In this paper, a prediction method of penetration depth of infinite thick metal target based on prior knowledge is proposed. The relative density and relative strength of projectile-target in Chen formula are taken as new features and integrated into the traditional artificial neural network in the form of prior knowledge. The experimental results show that the model based on the prior knowledge of Chen formula has better performance than the traditional method, and improves the prediction accuracy of the penetration depth of infinite thick metal target.