Loading...

Optimized age dependent clustering algorithm for prognosis: A case study on gas turbines

Mahmoodian, A ; Sharif University of Technology | 2021

235 Viewed
  1. Type of Document: Article
  2. DOI: 10.24200/sci.2020.53863.3459
  3. Publisher: Sharif University of Technology , 2021
  4. Abstract:
  5. 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. © 2021 Sharif University of Technology. All rights reserved
  6. Keywords:
  7. Cell proliferation ; Gas turbines ; Genetic algorithms ; Mapping ; Turbofan engines ; ADC model ; Age-based ; Fitting tools ; Fuzzy techniques ; Health monitoring ; Optimal model ; Optimizing structures ; Remaining useful lives ; Clustering algorithms ; Algorithm ; Cluster analysis ; Optimization ; Turbine
  8. Source: Scientia Iranica ; Volume 28, Issue 3 B , 2021 , Pages 1245-1258 ; 10263098 (ISSN)
  9. URL: http://scientiairanica.sharif.edu/article_22108.html