Extrapolation for Aeroengine Gas Path Faults with SVM Bases on Genetic Algorithm

Mining aeroengine operational data and developing fault diagnosismodels for aeroengines are to avoid running aeroengines under undesired conditions.Because of the complexity of working environment and faults of aeroengines,it is unavoidable that the monitored parameters vary widely and possesslarger noise levels. This paper reports the extrapolation of a diagnosis modelfor 20 gas path faults of a double-spool turbofan civil aeroengine. By applyingsupport vector machine (SVM) algorithm together with genetic algorithm (GA),the fault diagnosis model is obtained from the training set that was based onthe deviations of the monitored parameters superimposed with the noise levelof 10%. The SVM model (C = 24.7034; γ = 179.835) was extrapolated for thesamples whose noise levels were larger than 10%. The accuracies of extrapolationfor samples with the noise levels of 20% and 30% are 97% and 94%, respectively.Compared with the models reported on the same faults, the extrapolation resultsof the GASVM model are accurate.