Abstract:Aiming at the problem of fuzzy boundaries between aeroengine maintenance levels and low accuracy of decisionmaking, a decisionmaking method of engine maintenance levels based on large margin nearest neighbor algorithm and knearest neighbor algorithm is proposed. Firstly, the large margin nearest neighbor(LMNN) algorithm is adopted to obtain the transformation matrix based on the historical maintenance data of the engine. Then, the engine monitoring data is mapped to the optimal feature space by the transformation matrix. Finally, the Knearest neighbor algorithm is utilized to establish the decisionmaking model with the optimized data as the training samples, which determines the maintenance level by the evaluation of the state of the engine before it is removed from the aircraft. The method is verified using the performance parameters and maintenance level data of an aeroengine, and its decision accuracy is higher than the support vector machine model and neural network model which are commonly used.