关键词: 航空发动机, 气路参数, 偏差值, 离群点, 类指数平滑算法

Abstract: To keep the true mutation data which contained aero-engine fault or operation status information,a data smoothing technology was proposed by combining the outlier mining and similar exponential smoothing algorithm.The rolling sample outlier mining algorithm based on statistics was used to mine the outliers,and the similar double exponential smoothing algorithm based on weight was used to smooth the un-outlier in rolling mode.The smoothed data of factory was taken as learning objectives to optimize the parameters with minimum mean square error.Deviations were smoothed by the proposed smoothing technology and ten point smoothing algorithm.By comparing with original smoothing data of factory system,the result showed that the proposed smoothing technology could preserve the real mutation data,and the other engine gas path parameter deviation could smoothed reasonably.

Key words: aero-engine, gas path parameter, deviation, outlier, similar exponential smoothing algorithm