In order to reduce the impact of aircraft engine exhaust gas temperature on aircraft safety flight, the IQPSO-SVR(improved quantum-behaved particle swarm optimization support vector regression) model was proposed to predict the aero-engine exhaust gas temperature, Take the V2500 engine of A319 aircraft as an example, the performance parameter data from condition monitoring are selected as both the training and test samples, The high pressure-rotor speed, low-pressure rotor speed, fuel flow and high pressure compressor outlet temperature of the aero engine are taken as the inputs of the model, The aero-engine exhaust gas temperature is used as the output of the model, The IQPSO-SVR model is tested under the condition of different training samples, and compared with QPSO-SVR(quantum behaved particle swarm optimization support vector regression) and SVR (support vectorregression), experimental results show that the quantum adaptive particle swarm optimization SVR is more accurate than the other two methods in the prediction of aero-engine exhaust gas temperature and the QAPSO-SVR has better prediction ability innoise reduction.