Purpose The purpose of this paper is to propose and develop artificially intelligent methodologies to discover degradation trends through the detection of engine’s status. The objective is to predict these trends by studying their effects on the engine measurable parameters. Design/methodology/approach The method is based on the implementation of an artificial neural network (ANN) trained with well-known cases referred to real conditions, able to recognize degradation because of two main gas turbine engine deterioration effects: erosion and fouling. Three different scenarios are considered: compressor fouling, turbine erosion and presence of both degraded conditions. The work consists of three parts: the first one contains the mathematical model of real jet engine in healthy and degraded conditions, the second step is the optimization of ANN for engine performance prediction and the last part deals with the application of ANN for prediction of engine fault. Findings This study shows that the proposed diagnostic approach has good potential to provide valuable estimation of engine status. Practical implications Knowledge of the true state of the engine is important to assess its performance capability to meet the operational and maintenance requirements and costs. Originality/value The main advantage is that the engine performance data for model validation were obtained from real flight conditions of the engine VIPER 632-43.

Jet engine degradation prognostic using artificial neural networks

De Giorgi, Maria Grazia
;
Ficarella, Antonio;
2019-01-01

Abstract

Purpose The purpose of this paper is to propose and develop artificially intelligent methodologies to discover degradation trends through the detection of engine’s status. The objective is to predict these trends by studying their effects on the engine measurable parameters. Design/methodology/approach The method is based on the implementation of an artificial neural network (ANN) trained with well-known cases referred to real conditions, able to recognize degradation because of two main gas turbine engine deterioration effects: erosion and fouling. Three different scenarios are considered: compressor fouling, turbine erosion and presence of both degraded conditions. The work consists of three parts: the first one contains the mathematical model of real jet engine in healthy and degraded conditions, the second step is the optimization of ANN for engine performance prediction and the last part deals with the application of ANN for prediction of engine fault. Findings This study shows that the proposed diagnostic approach has good potential to provide valuable estimation of engine status. Practical implications Knowledge of the true state of the engine is important to assess its performance capability to meet the operational and maintenance requirements and costs. Originality/value The main advantage is that the engine performance data for model validation were obtained from real flight conditions of the engine VIPER 632-43.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11587/428797
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 22
  • ???jsp.display-item.citation.isi??? 19
social impact