The mutual information based minimum spanning tree to detect and evaluate dependencies between aero-engine gas path system variables

There is a great interest in studying statistical dependence characteristics of aero-engine gas path system time series. The mutual information is effective, mainly in quantifying the dependency of time series. By applying the mutual information and average mutual information method to aero-engine gas path system, the statistical dependence between two data steams from a finite number of samples are established. To better understand dependency of gas path system time series, we define the mutual information distance and propose the mutual information based minimum spanning tree to investigate the performance parameters and their interaction of gas path system. By examining the minimum spanning tree, we find that the exhaust gas temperature (EGT) and the low spool rotor speed (N1) are confirmed as the predominant variables in fourteen gas path parameters. The results show that the proposed method is effective to detect the statistical dependence of gas path system parameters and has more valuable information. (C) 2018 Elsevier B.V. All rights reserved.