ProgNet: A Transferable Deep Network for Aircraft Engine Damage Propagation Prognosis under Real Flight Conditions

Berghout, Tarek; Mouss, Mohamed-Djamel; Mouss, Leïla Hayet; Benbouzid, Mohamed

doi:10.3390/aerospace10010010

Cited by 17 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By analysing similar strategies, the paper Li et al (2018) developed a new strategy for the prediction of the lifetime of a dynamic process via a deep CNN (DCNN) based on constructing samples with time-varying windows. The samples were prepared by time windows to better achieve feature extraction, and experiments on the aero-propulsion system data set (Berghout et al, 2023), which are exploited by this paper, highlighted that the reconstruction of the RUL index was more accurate than other mainstream research approaches. On the other hand, the work Zhu et al ( 2019) considered an approach using CNN tools for the estimation of the RUL indicator for multiple scale bearings.…”

Section: Rul Prediction Methodsmentioning

confidence: 98%

“…These data sets will be shortly referred to 'set i', with the index i varying from 1 to 4, respectively. More details on these time sequences are available in Ramasso ( 2014), Thakkar and Chaoui (2022), Berghout et al (2023).…”

Section: Methodsmentioning

confidence: 99%

“…The sequences that are utilised for the experimental validation of the solutions presented in Section 5 were detailed in detail in Section 4. These sequences were borrowed from the well-known benchmark of an aero-propulsion system data set (Berghout et al, 2023). The robustness and sensitivity characteristics of the proposed schemes are also investigated.…”

Section: Achievements and Comparisonsmentioning

confidence: 99%

“…The sequences that are utilised for the experimental validation of the solutions presented in Section 5 are detailed in detail in Section 4. These sequences were taken from a wellknown benchmark of an aero-propulsion system data set (Berghout et al, 2023), which may be found in Section 5. The findings that were obtained help to illustrate the effectiveness and advantages of the suggested PSN, which is also contrasted with several other methods.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamic Neural Network Architecture Design for Predicting Remaining Useful Life of Dynamic Processes

Simani¹,

Lam²,

Farsoni³

et al. 2023

JDSIS

View full text Add to dashboard Cite

The prediction of remaining useful life is critical in predictive health management. This is done to reduce the expenses associated with operation and maintenance by avoiding errors and failures in dynamic processes. Recently, the abilities of feature classification and automated extraction of neural networks in its convolutional forms have shown fascinating performance when used for estimating the remaining useful life of dynamic processes using deep learning structures. This was accomplished by putting these talents to the task of predicting how long the procedures would be beneficial. Existing network topologies, on the other hand, virtually entirely extract features at a single scale while neglecting important information at other sizes. Meanwhile, because of the architecture of a single network path, the comprehensiveness of the features discovered by these tools is limited. To address these concerns, the authors propose a network structure based on a feature fusion strategy on a parallel multiscale architecture. This structure is then utilized to compute the remaining useful life. This prototype is divided into two sections: the first is a multiscale feature extraction module designed to extract local information features, and the second is a causal convolution module designed to extract global information features by combining multi-layer causal convolution with average pooling. The multiscale feature extraction module is intended for the extraction of local information features, while the causal convolution module is intended for the extraction of global information features. Finally, the two distinct paths are joined to create a fully integrated layer. The simulations and results show that this method has the potential to improve the efficiency and accuracy of estimating the remaining useful life index. Furthermore, the advantages of the established strategy are shown by comparing the results obtained with those produced by applying cutting-edge techniques on a well-known data-set depicting a simulated turbofan engine.

show abstract

Section: Rul Prediction Methodsmentioning

confidence: 98%

Section: Methodsmentioning

confidence: 99%

Section: Achievements and Comparisonsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Neural Network Architecture Design for Predicting Remaining Useful Life of Dynamic Processes

Simani¹,

Lam²,

Farsoni³

et al. 2023

JDSIS

View full text Add to dashboard Cite

show abstract

“…Advanced techniques leveraging long short-term memory (LSTM) networks and attention mechanisms improved RUL prediction for time series data (Song et al, 2022). Berghout et al (2022) further illustrated how these architectures can benefit from transfer learning to improve prognostic performance. This paper will focus on the new Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS) dataset, which was featured in the 2021 PHM Data Challenge and centered on accurately estimating the RUL for a small fleet of turbofan engines (Chao et al, 2021b).…”

Section: Introductionmentioning

confidence: 99%

Fault Prognosis of Turbofan Engines

Cohen

Huan

2023

IJPHM

View full text Add to dashboard Cite

In the era of industrial big data, prognostics and health management is essential to improve the prediction of future failures to minimize inventory, maintenance, and human costs. Used for the 2021 PHM Data Challenge, the new Commercial Modular Aero-Propulsion System Simulation dataset from NASA is an open-source benchmark containing simulated turbofan engine units flown under realistic flight conditions. Deep learning approaches implemented previously for this application attempt to predict the remaining useful life of the engine units, but have not utilized labeled failure mode information, impeding practical usage and explainability. To address these limitations, a new prognostics approach is formulated with a customized loss function to simultaneously predict the current health state, the eventual failing component(s), and the remaining useful life. The proposed method incorporates principal component analysis to orthogonalize statistical time-domain features, which are inputs into supervised regressors such as random forests, extreme random forests, XGBoost, and artificial neural networks. The highest performing algorithm, ANN–Flux with PCA augmentation, achieves AUROC and AUPR scores exceeding 0.94 for each classification on average. In addition to predicting eventual failures with high accuracy, ANN–Flux achieves comparable remaining useful life RMSE for the same test split of the dataset when benchmarked against past work, with significantly less computational cost.

show abstract

A transformer with layer-cross decoding for remaining useful life prediction

Guo

Liu

et al. 2023

J Supercomput

View full text Add to dashboard Cite

ProgNet: A Transferable Deep Network for Aircraft Engine Damage Propagation Prognosis under Real Flight Conditions

Cited by 17 publications

References 20 publications

Dynamic Neural Network Architecture Design for Predicting Remaining Useful Life of Dynamic Processes

Dynamic Neural Network Architecture Design for Predicting Remaining Useful Life of Dynamic Processes

Fault Prognosis of Turbofan Engines

A transformer with layer-cross decoding for remaining useful life prediction

Contact Info

Product

Resources

About