The invention discloses a method for predicting shock
waves through a multi-region conservation enhanced
physical information neural network, and belongs to the field of flow field prediction of shock
waves and strong nonlinear
physical phenomena in high-speed flow, and the method comprises the steps: S1, carrying out numerical
simulation through fluid dynamics
software to obtain a reference flow field solution of a to-be-solved N-S
control equation, the
verification module is used for verifying a model solving result; s2, constructing a neural network comprising an integral layer, a micro-layer and a
loss function error layer; s3, constructing a
physical information neural network; s4, training is carried out after
physical information neural network training parameters are set, and whether a convergence standard is met or not is determined by constructing a joint
loss function corresponding to the physical information neural network; and S5, applying the trained neural
network model to
shock wave prediction of high-speed flow
field simulation under different working conditions. Through the multi-region local conservation constraint, the width of the
shock wave transition region is effectively compressed, so that the relative error of the
physical quantity is obviously reduced compared with the existing method.