optimized age dependent clustering algorithm for prognosis: a case study on gas turbines

This paper proposes an age-dependent clustering (adc) structure to be used for prognostics. to achieve this aim, a step-by-step methodology is introduced, that includes clustering, reproduction, mapping, and finally estimation of remaining useful life (rul). in the mapping step, a neural fitting tool is used. to clarify the age-based clustering concept, the main elements of the adc model is discussed. a genetic algorithm (ga) is used to find the elements of the optimal model. lastly, the fuzzy technique is applied to modify the clustering. by investigating a case study on the health monitoring of some turbofan engines, the efficacy of the proposed method is demonstrated. the results showed that the concept of clustering without optimization processes is efficient even for the simplest form of performance. however, by optimizing structure elements and fuzzy clustering, the prognosis accuracy increased up to 71%. the effectiveness of adc prognosis is proven in comparison with other methods.