Aeroengine prognosis through genetic distal learning applied to uncertain Engine Health Monitoring data

Genetic Fuzzy Systems have been successfully applied to assess Engine Health Monitoring (EHM) data from aeroengines, not only due to their robustness towards noisy gas path measurements and engine-to-engine variability, but also because of their capability to produce human-readable expressions. These techniques can detect the presence of certain types of abnormal events or specific engine conditions, where a combination of the EHM signals only appears when these occur. However, an engine that repeatedly operates under unfavourable conditions will also have a reduced life. Smooth deteriorations do no manifest themselves as combinations of the EHM signals, the current existing techniques can therefore not assess these. In this paper it is proposed to use distal learning to build a model that indirectly identifies the deterioration rate of an aeroengine. It will be shown that the integral of the modelled rate is a prognostic indicator of the remaining life of the engine to a selected end condition. The results are subsequently tested on a representative sample of aeroengine data.