Evaluation Method of Aero-engine Performance Based on Hybrid AP-HMM Model

As the aero-engine is the heart of aircraft, it is very important to monitor and diagnose the performance of the aero-engine effectively. In this paper, a method based on AP(Affinity Propagation) clustering HMM(Hidden Markov Model) model is proposed to evaluate the aero-engine performance. First, the correlation analysis method is used to extract the main attributes of the original data. Then, AP theory and K-NN are used for clustering with different performances to establish the HMM model for performance analysis. The experimental results show that this method has good effect on the performance analysis of aero-engine, which can improve the clustering effect, the classification accuracy of boundary sampling points and the accuracy of performance evaluation results.