Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit
Prognostics and health management is an engineering discipline that aims to support system operation while ensuring maximum safety and performance. Prognostics is a key step of this framework, focusing on developing effective maintenance policies based on predictive methods. Traditionally, prognosti...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/10/4/354 |
| _version_ | 1797606843823947776 |
|---|---|
| author | Marcia L. Baptista Helmut Prendinger |
| author_facet | Marcia L. Baptista Helmut Prendinger |
| author_sort | Marcia L. Baptista |
| collection | DOAJ |
| description | Prognostics and health management is an engineering discipline that aims to support system operation while ensuring maximum safety and performance. Prognostics is a key step of this framework, focusing on developing effective maintenance policies based on predictive methods. Traditionally, prognostics models forecast the degradation process using regression techniques that approximate a mapping function from input to continuous remaining useful life estimates. These models are typically of high complexity and low interpretability. Classification approaches are an alternative solution to these types of models. We propose a predictive classification model that translates the input into discrete output variables instead of mapping the input to a single remaining useful life estimate. Each discrete output variable corresponds to a range of remaining useful life values. In other words, each output class variable represents the likelihood or risk of failure within a specific time range. We apply this model to a real-world case study involving the unscheduled and scheduled removals of a set of engine bleed valves from a fleet of Boeing 737 aircraft. The model can reach an area under the (micro-average) receiver operating characteristic curve of 72%. Our results suggest that the proposed multiclass gated recurrent unit network can provide valuable information about the different fault stages (corresponding to intervals of residual lives) of the studied valves. |
| first_indexed | 2024-03-11T05:20:43Z |
| format | Article |
| id | doaj.art-41ff51ea61ba4bea9758d51fdd538708 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-11T05:20:43Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-41ff51ea61ba4bea9758d51fdd5387082023-11-17T17:52:19ZengMDPI AGAerospace2226-43102023-04-0110435410.3390/aerospace10040354Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent UnitMarcia L. Baptista0Helmut Prendinger1Air Transport and Operations, Faculty of Aerospace Engineering, Delft University of Technology (TU Delft), 2628 CD Delft, The NetherlandsNational Institute of Informatics, Tokyo 1018430, JapanPrognostics and health management is an engineering discipline that aims to support system operation while ensuring maximum safety and performance. Prognostics is a key step of this framework, focusing on developing effective maintenance policies based on predictive methods. Traditionally, prognostics models forecast the degradation process using regression techniques that approximate a mapping function from input to continuous remaining useful life estimates. These models are typically of high complexity and low interpretability. Classification approaches are an alternative solution to these types of models. We propose a predictive classification model that translates the input into discrete output variables instead of mapping the input to a single remaining useful life estimate. Each discrete output variable corresponds to a range of remaining useful life values. In other words, each output class variable represents the likelihood or risk of failure within a specific time range. We apply this model to a real-world case study involving the unscheduled and scheduled removals of a set of engine bleed valves from a fleet of Boeing 737 aircraft. The model can reach an area under the (micro-average) receiver operating characteristic curve of 72%. Our results suggest that the proposed multiclass gated recurrent unit network can provide valuable information about the different fault stages (corresponding to intervals of residual lives) of the studied valves.https://www.mdpi.com/2226-4310/10/4/354prognosticsdata-drivenmulticlassificationdegradation stagesgated recurrent unit |
| spellingShingle | Marcia L. Baptista Helmut Prendinger Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit Aerospace prognostics data-driven multiclassification degradation stages gated recurrent unit |
| title | Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit |
| title_full | Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit |
| title_fullStr | Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit |
| title_full_unstemmed | Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit |
| title_short | Aircraft Engine Bleed Valve Prognostics Using Multiclass Gated Recurrent Unit |
| title_sort | aircraft engine bleed valve prognostics using multiclass gated recurrent unit |
| topic | prognostics data-driven multiclassification degradation stages gated recurrent unit |
| url | https://www.mdpi.com/2226-4310/10/4/354 |
| work_keys_str_mv | AT marcialbaptista aircraftenginebleedvalveprognosticsusingmulticlassgatedrecurrentunit AT helmutprendinger aircraftenginebleedvalveprognosticsusingmulticlassgatedrecurrentunit |