Have a personal or library account? Click to login
Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life Cover

Comparative Analysis of Deep Learning and Decision Tree Approaches for Predicting Aircraft Engine Remaining Useful Life

Open Access
|Nov 2024

Figures & Tables

Fig. 1.

Simple CNN-1D architecture with two convolutional layers (Frederick et al., 2007).
Simple CNN-1D architecture with two convolutional layers (Frederick et al., 2007).

Fig. 2.

Example of a decision tree.
Example of a decision tree.

Fig. 3.

Simplified engine diagram simulated in C-MAPSS (Heimes, 2008).
Simplified engine diagram simulated in C-MAPSS (Heimes, 2008).

Fig. 4.

The distribution of the dataset’s features.
The distribution of the dataset’s features.

Fig. 5.

Bar chart of influential features.
Bar chart of influential features.

Fig. 6.

Correlation heatmap for selected dataset features.
Correlation heatmap for selected dataset features.

Fig. 7.

Diagram of model degradation of all engines.
Diagram of model degradation of all engines.

Fig. 8.

Decision Tree structure.
Decision Tree structure.

Fig. 9.

Diagram of true and predicted RUL using CNN-1D.
Diagram of true and predicted RUL using CNN-1D.

Fig. 10.

Diagram of true and predicted RUL using DT.
Diagram of true and predicted RUL using DT.

The meanings of C-MAPSS data sources_

DescriptionSymbolUnits
Total temperature at the fan inletT2°R
Total temperature at the LPC outletT24°R
Total temperature at the HPC outletT30°R
Total temperature at the LPT outletT50°R
Pressure at the fan inletP2Psia
Total pressure in bypass-ductP15Psia
Total pressure at the HPC outletP30Psia
Physical fan speedNfrpm
Physical core speedNcrpm
Engine pressure ratio (P50/P2)Epr
Static pressure at the HPC outletPs30Psia
Ratio of fuel flow to Ps30PhiPPS/psi
Corrected fan speedNRfrpm
Corrected core speedNRcRpm
Bypass ratioBPR
Burner fuel-air ratiofarB
Bleed enthalpybleed
Demanded fan speedNf_dmdRpm
Demanded corrected fan speedPCNR_dmdRpm
Coolant bleed (HPT)W31HPT1bm/s
Coolant bleed (LPT)W32LPT1bm/s
The total temperature at the HPT outletParameters for calculating Health Index
Fan stall marginSmFan
LPC stall marginSmLPC
HPC stall marginSmHPC

Description of FD001 datasets_

DatasetCMAPSS (FD001)
Training engine100
Testing engine100
Working condition1
Fault modes2

The evaluation metrics_

ModelMSERMSER2
Train setCNN-1D459.511421.43620.7461
Test set735.564727.12130.5707
Train setDT567.896523.83050.6761
Test set837.133928.93320.5588

CNN-1D structure_

Layer (type)Output ShapeParam #
conv1d (Conv1D)(None, 23, 32)96
flatten (Flatten)(None, 736)θ
dense (Dense)(None, 64)47168
dense_1 (Dense)(None, 1)65
DOI: https://doi.org/10.2478/fas-2023-0012 | Journal eISSN: 2300-7591 | Journal ISSN: 2081-7738
Language: English
Page range: 183 - 200
Published on: Nov 19, 2024
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year

© 2024 Hassina Madjour, Hanane Zermane, Djemaa Rahmouni, Mohammed Djamel Mouss, published by ŁUKASIEWICZ RESEARCH NETWORK – INSTITUTE OF AVIATION
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.