Transformer Encoder Enhanced by an Adaptive Graph Convolutional Neural Network for Prediction of Aero-Engines’ Remaining Useful Life
Open accessAbstract
Accurate prediction of remaining useful life (RUL) plays a significant role in ensuring the safe flight of aircraft. With the recent rapid development of deep learning, there has been a growing trend towards more precise RUL prediction. However, while many current deep learning methods are capable of extracting spatial features—those along the sensor dimension—through convolutional kernels or fully connected layers, their extraction capacity is often limited due to the small scale of kernels and the high uncertainty associated with linear weights. Graph neural networks (GNNs), emerging as effective approaches for processing graph-structured data, explicitly consider the relationships between sensors. This is akin to imposing a constraint on the training process, thereby allowing the learned results to better approximate real-world situations. In order to address the challenge of GNNs in extracting temporal features, we augment our proposed framework for RUL prediction with a Transformer encoder, resulting in the adaptive graph convolutional transformer encoder (AGCTE). A case study using the C-MAPSS dataset is conducted to validate the effectiveness of our proposed model.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Comparing the results of [102] with those of [97,101], the model of [102] shows some improvement, which could be due to the parallel approach in that work.
“Comparing the results of [102] with those of [97,101], it can be seen that the model of [102] shows some improvement compared with these models, which could be due to the parallel approach in this work.”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [97]
The Results and Analysis section reports that AGCTE performs better than the compared methods on FD002 and FD004 and ranks first on average, though not on every subdataset. The Conclusions describe separate modules extracting spatial and temporal features relatively independently, but the paper does not attribute its improvement to a parallel approach; its Results and Analysis offer other possible explanations. (LLM, conf=0.83)
Experimental — accuracy not yet measuredThe architecture of [97] follows the design approach of [101] by using GAT to extract spatial features and multi-head self-attention to extract temporal features, with the exception that in [97] an adaptive embedding vector is added to each node within the GCN.
“A look at the architectures of this model shows that it follows the design approach of [101] by using GAT to extract the spatial features and multi-head self-attention to extract the temporal features, with the exception that in [97], an adaptive embedding vector is added to each node within the GCN.”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [97]
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredTable 3 shows that the model presented in [97] occupies the penultimate position in terms of performance.
“Table 3 also shows that the model presented in [97] occupies the penultimate position in terms of performance.”
From TVGeAN: Tensor Visibility Graph-Enhanced Attention Network for Versatile Multivariant Time Series Learning Tasks (2024) · cites this paper as [97]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Damage propagation modeling for aircraft engine run-to-failure simulation
Saxena, A., Goebel, K., Simon, D., & Eklund, N. (2008) · 2008 International Conference on Prognostics and Health Management · doi:10.1109/phm.2008.4711414 · Cited by 1,954 · see citing works
Flagged first, then by citations
Research works printed but not linked: 32
- Wang, H.; Zhang, Z.; Li, X.; Deng, X.; Jiang, W. Comprehensive Dynamic Structure Graph Neural Network for Aero-engine Remaining Useful Life Prediction. IEEE Trans. Instrum. Meas. 2023, 72, 3533816. [CrossRef] · DOI
- Chen, J.; Shen, C.; Jing, Z.; Wu, Y.; Chen, R. Remaining useful life prediction of aircraft flap control system with mode transition. AIAA J. 2022, 60, 1104-1115. [CrossRef] · DOI
- Wang, H.; Ma, X.; Zhao, Y. An improved Wiener process model with adaptive drift and diffusion for online remaining useful life prediction. Mech. Syst. Signal Proc. 2019, 127, 370-387. [CrossRef] · DOI
- Chiachío, J.; Jalón, M.L.; Chiachío, M.; Kolios, A. A Markov chains prognostics framework for complex degradation processes. Reliab. Eng. Syst. Saf. 2020, 195, 106621. [CrossRef] · DOI
- Li, Y.; Li, J.; Wang, H.; Liu, C.; Tan, J. Knowledge enhanced ensemble method for remaining useful life prediction under variable working conditions. Reliab. Eng. Syst. Saf. 2024, 242, 109748. [CrossRef] · DOI
- Li, T.; Zhao, Z.; Sun, C.; Yan, R.; Chen, X. Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction. Reliab. Eng. Syst. Saf. 2021, 215, 107878. [CrossRef] · DOI
- Zhang, X.; Kang, J.; Jin, T. Degradation modeling and maintenance decisions based on Bayesian belief networks. IEEE Trans. Reliab. 2014, 63, 620-633. [CrossRef] · DOI
- Benkedjouh, T.; Medjaher, K.; Zerhouni, N.; Rechak, S. Health assessment and life prediction of cutting tools based on support vector regression. J. Intell. Manuf. 2015, 26, 213-223. [CrossRef] · DOI
- Bezerra Souto Maior, C.; das Chagas Moura, M.; Didier Lins, I.; Lopez Droguett, E.; Henrique Lima Diniz, H. Remaining useful life estimation by empirical mode decomposition and support vector machine. IEEE Latin Am. Trans. 2016, 14, 4603-4610. [CrossRef] · DOI
- Li, X.; Ding, Q.; Sun, J.-Q. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Saf. 2018, 172, 1-11. [CrossRef] · DOI
- Sayah, M.; Guebli, D.; Noureddine, Z.; Al Masry, Z. Deep LSTM enhancement for RUL prediction using Gaussian mixture models. Autom. Control Comp. Sci. 2021, 55, 15-25. [CrossRef] · DOI
- Chen, D.; Qin, Y.; Wang, Y.; Zhou, J. Health indicator construction by quadratic function-based deep convolutional auto-encoder and its application into bearing RUL prediction. ISA Trans. 2021, 114, 44-56. [CrossRef] [PubMed] · DOI
- Kamei, S.; Taghipour, S. A comparison study of centralized and decentralized federated learning approaches utilizing the transformer architecture for estimating remaining useful life. Reliab. Eng. Syst. Saf. 2023, 233, 109130. [CrossRef] · DOI
- Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; Philip, S.Y. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2020, 32, 4-24. [CrossRef] [PubMed] · DOI · Paper page
- Li, J.; Li, X.; He, D. A directed acyclic graph network combined with CNN and LSTM for remaining useful life prediction. IEEE Access 2019, 7, 75464-75475. [CrossRef] · DOI
- Kong, Z.; Jin, X.; Xu, Z.; Zhang, B. Spatio-temporal fusion attention: A novel approach for remaining useful life prediction based on graph neural network. IEEE Trans. Instrum. Meas. 2022, 71, 1-12. [CrossRef] · DOI
- Liu, N.; Guo, J.; Chen, S.; Zhang, X. Aero-Engines Remaining Useful Life Prognostics Based on Multi-Hierarchical Gated Recurrent Graph Convolutional Network. In Proceedings of the 2023 International Conference on Cyber-Physical Social Intelligence (ICCSI), Xi'an, China, 20-23 October 2023; pp. 642-647.
- Gilmer, J.; Schoenholz, S.S.; Riley, P.F.; Vinyals, O.; Dahl, G.E. Neural message passing for quantum chemistry. In Proceedings of the International Conference on Machine Learning, Sydney, Australia, 6-11 August 2017; pp. 1263-1272.
- Deng, A.; Hooi, B. Graph neural network-based anomaly detection in multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, Virtual, 2-9 February 2021; pp. 4027-4035.
- Zhang, X.; Leng, Z.; Zhao, Z.; Li, M.; Yu, D.; Chen, X. Spatial-temporal dual-channel adaptive graph convolutional network for remaining useful life prediction with multi-sensor information fusion. Adv. Eng. Inform. 2023, 57, 102120. [CrossRef] · DOI
- Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907. · arXiv
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30.
- Ogunfowora, O.; Najjaran, H. A Transformer-based Framework For Multi-variate Time Series: A Remaining Useful Life Prediction Use Case. arXiv 2023, arXiv:2308.09884. · arXiv
- Mo, Y.; Wu, Q.; Li, X.; Huang, B. Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit. J. Intell. Manuf. 2021, 32, 1997-2006. [CrossRef] · DOI
- Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv 2018, arXiv:1810.04805. · arXiv
- Dong, Y.; Cordonnier, J.-B.; Loukas, A. Attention is not all you need: Pure attention loses rank doubly exponentially with depth. In Proceedings of the International Conference on Machine Learning, Virtual, 18-24 July 2021; pp. 2793-2803.
- Sateesh Babu, G.; Zhao, P.; Li, X.-L. Deep convolutional neural network based regression approach for estimation of remaining useful life. In Proceedings of the Database Systems for Advanced Applications: 21st International Conference, DASFAA 2016, Dallas, TX, USA, 16-19 April 2016; Proceedings, Part I 21; pp. 214-228.
- Zheng, S.; Ristovski, K.; Farahat, A.; Gupta, C. Long short-term memory network for remaining useful life estimation. In Proceedings of the 2017 IEEE international conference on prognostics and health management (ICPHM), Dallas, TX, USA, 19-21 June 2017; pp. 88-95.
- Ellefsen, A.L.; Bjørlykhaug, E.; Æsøy, V.; Ushakov, S.; Zhang, H. Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture. Reliab. Eng. Syst. Saf. 2019, 183, 240-251. [CrossRef] · DOI
- Liu, X.; Xiong, L.; Zhang, Y.; Luo, C. Remaining Useful Life Prediction for Turbofan Engine Using SAE-TCN Model. Aerospace 2023, 10, 715. [CrossRef] · DOI
- Mo, H.; Iacca, G. Evolutionary neural architecture search on transformers for RUL prediction. Mater. Manuf. Process. 2023, 38, 1881-1898. [CrossRef] · DOI
- Wang, L.; Cao, H.; Xu, H.; Liu, H. A gated graph convolutional network with multi-sensor signals for remaining useful life prediction. Knowl.-Based Syst. 2022, 252, 109340. [CrossRef · DOI
Cited by
Sorted by citations
Baz, M. (2024) · Mathematics · doi:10.3390/math12213320 · Cited by 1 · see citing works
- Authors
- Ma, M., Wang, Z., & Zhong, Z.
- Affiliations
- Xi'an Jiaotong University (CN)
- Venue
- Aerospace
- Publisher
- MDPI AG
- Published
- 2024-04-09
- Volume
- 11
- Issue
- 4
- Pages
- 289
- ISSN
- 2226-4310 (ISSN-L)
- OpenAlex
- W4394619753
- Cited by
- 18
- References
- 1
- Citations by year
- 2026: 12 · 2025: 5 · 2024: 1
- FWCI
- 2.81
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Aerospace (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (52205124, 2021M702634, 2022-JCJQ-JJ-0643, xxj032022011)
- Postdoctoral Science Fund (52205124, 2021M702634, 2022-JCJQ-JJ-0643, xxj032022011)
- Basic Research Program of China (52205124, 2021M702634, 2022-JCJQ-JJ-0643, xxj032022011)
- Basic Research Fund of Xi’an Jiaotong University (52205124, 2021M702634, 2022-JCJQ-JJ-0643, xxj032022011)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Reliability and Maintenance Optimization
- Physical Sciences › Engineering › Automotive Engineering › Technical Engine Diagnostics and Monitoring
- Keywords
- remaining useful life prediction, Transformer encoder, graph neural networks, temporal feature extraction, C-MAPSS dataset, aircraft safety
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
