The invention discloses an axial flow compressor stall surge prediction method based on deep learning, and belongs to the technical field of aero-engine modeling and simulation. The method comprises:firstly, preprocessing aircraft engine surge data, and dividing a test data set and a training data set from experimental data; secondly, sequentially constructing an LR branch network module, a WaveNet branch network module and an LR-WaveNet prediction model; and finally, performing real-time prediction on the test data: firstly, preprocessing the test set data in the same way, and adjusting thedata dimension according to the input requirement of the LR-WaveNet prediction model; according to the time sequence, by adopting an LR-WaveNet prediction model, giving the surge prediction probability of each sample; and by adopting an LR-WaveNet prediction mode, giving the surge probability of data with noise points along with time, and testng the anti-interference performance of the model. According to the method, the time domain statistical characteristics and the change trend are integrated, the prediction precision is improved, and certain anti-interference performance is achieved; and the active control performance of the engine can be improved, and certain universality is achieved.