Engine performance prediction method adopting sample adaptive weighting

The invention relates to the technical field of engine state monitoring, in particular to an engine performance prediction method adopting sample adaptive weighting, which comprises the following steps of: establishing a first data set and a second data set, the second data set comprises operation data sets of N other engines with the same model as the current engine; clustering the first data set and the second data set according to flight envelope distribution to obtain M clustering centers; sub-models are established, so that each of the M clustering centers comprises N sub-models; each clustering center initializes a prediction weight vector W, weighted averaging is carried out on N sub-models included in the prediction weight vector W, M linear weighted prediction models are constructed, and the linear weighted prediction models are used for predicting engine performance; and optimizing the prediction weight vector W of the clustering center. According to the method, data diversity is fully exerted, and