Cavity pressure prediction method for air system of aero-engine

The invention belongs to the technical field of engine tests, and particularly relates to an aero-engine air system cavity pressure prediction method. The method comprises the steps that S1, the inlet pressure and temperature of an engine, the inlet pressure and temperature of a high-pressure compressor, the inlet pressure and temperature of a high-pressure turbine, the inlet pressure and temperature of a low-pressure turbine, the outlet pressure and temperature of the low-pressure turbine and the rotating speed of the low-pressure turbine are collected, and feature vectors are formed; s2, on the basis of a pre-constructed and trained BP neural network model for cavity pressure prediction, the feature vectors serve as model input, model output is obtained, and the BP neural network model for cavity pressure prediction is configured in the mode that the BP neural network model for cavity pressure prediction is trained on the basis of sample data, and the BP neural network model for cavity pressure prediction i