Performance evaluation of aero-engine based on information entropy and symbolization

Using information entropy can measure of the disorder degree of the source system to discussing its application in the aero-engine performance evaluation, combined with the symbolization processing of time series. In the extraction of entropy, directly extracting the joint entropy aimed at the symbolic series of multiple performance parameters, and extracting the entropy aimed at the short-symbol series which reconstruction single parameter to generate short-symbol series, were used respectively. Experiments of actual flight data have been done, and the results shows that the two characteristic indicator of information entropy described in the healthy evolution of aero-engine coincide with the actual situation. The methods can reflect the health condition, and can support the performance evaluation of aero-engine.