A Robust Conformal Framework for IoT-Based Predictive Maintenance
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index; 5 of the 22 sources its claims cite were checked for support.
Abstract
This study, set within the vast and varied research field of industrial Internet of Things (IoT) systems, proposes a methodology to address uncertainty quantification (UQ) issues in predictive maintenance (PdM) practices. At its core, this paper leverages the commercial modular aero-propulsion system simulation (CMAPSS) dataset to evaluate different artificial intelligence (AI) prognostic algorithms for remaining useful life (RUL) forecasting while supporting the estimation of a robust confidence interval (CI). The methodology primarily involves the comparison of statistical learning (SL), machine learning (ML), and deep learning (DL) techniques for each different scenario of the CMAPSS, evaluating the performances through a tailored metric, the S-score metric, and then benchmarking diverse conformal-based uncertainty estimation techniques, remarkably naive, weighted, and bootstrapping, offering a more suitable and reliable alternative to classical RUL prediction. The results obtained highlight the peculiarities and benefits of the conformal approach, despite probabilistic models favoring the adoption of complex models in cases where the operating conditions of the machine are multiple, and suggest the use of weighted conformal practices in non-exchangeability conditions while recommending bootstrapping alternatives for contexts with a more substantial presence of noise in the data.
Overview
CoChat Summary
TL;DR
This paper proposes a "Robust Conformal Prognostic" framework that couples deep-learning RUL predictors with clamp-regulated (monotonicity-enforced) conformal prediction to produce distribution-free lower-bound confidence intervals for IoT-based predictive maintenance. Evaluated on the CMAPSS turbofan dataset, it benchmarks naive, weighted, and bootstrap conformal margins against probabilistic (Prophet) uncertainty quantification.
Key findings
- On FD2, bootstrap conformal achieved the highest coverage (0.513, margin 41.66), followed by weighted (0.510, margin 40.57) and naive (0.476, margin 32.92); the authors conclude bootstrap best balances interval tightness and coverage in noisy settings.
- Across the four CMAPSS subsets, the best point-prediction models were N-BEATS on FD1 (MSE 347.67, MAE 14.34, RMSE 18.64, R² 0.86, S-score 24069) and FD3 (MSE 226.29, MAE 10.61, RMSE 15.04, R² 0.911, S-score 22870); CNN-GRU on FD2 (MSE 300.32, MAE 13.06, RMSE 17.73, R² 0.82, S-score 75307); and BiLSTM on FD4 (MSE 505.24, MAE 17.28, RMSE 22.48, R² 0.800, S-score 273456).
- Conformal coverage on FD1/FD3/FD4 was 0.505 (weighted, margin 40.171), 0.423 (weighted, margin 36.06), and 0.488 (weighted, margin 64.52) respectively.
- Kaplan–Meier survival analysis set degradation-onset thresholds at cycle 125 for the single-condition datasets (FD1–FD3) and cycle 150 for the multi-condition datasets (FD2–FD4).
- The authors report that Prophet overfits the piecewise-linear RUL target and produces "probabilistic gaps" that fail to capture sensor dynamics, whereas regulated conformal intervals adapt to degradation patterns.
Methods
- Design: an end-to-end pipeline that (1) generates RUL predictions, (2) enforces non-increasing monotonicity ("clamp regulation"), (3) computes residuals on a calibration set, and (4) applies naive, weighted (exponential), or bootstrap margin estimators at α = 0.05 (bootstrap B = 200), selecting the margin with highest coverage.
- Data: the NASA CMAPSS turbofan run-to-failure dataset (FD1–FD4; per Table 1, 100/260/100/249 training units, 1 or 6 operating conditions, 1 or 2 fault modes), with a unit-wise 80/20 train–validation split and a 30-lag context window.
- Models and analysis: LSTM, BiLSTM, N-BEATS, CNN-GRU, and XGBoost compared using MSE, MAE, RMSE, R², and the asymmetric S-score (Eq. 21); conformal performance assessed via margin, coverage (Eq. 19), and EoL-proximity (Δ_index).
Limitations
- The paper states no dedicated limitations section; it notes future work could add domain constraints, more advanced learning strategies across equipment types, and data augmentation for data-scarce regimes.
- Evident from the text: reported conformal coverage values (0.423–0.513) fall far below the nominal 1 − α = 0.95 target, so the claimed coverage guarantee is not empirically achieved on these validation sets.
- Evident from the text: evaluation is confined to the simulated CMAPSS dataset with no real IoT sensor deployment, and the RUL target itself is constructed ex post from a piecewise-linear/survival model rather than observed failure labels.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
4 Valid · 10 Not valid · 14 Not checked · 73 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results from the tailored survival analysis, through Kaplan–Meier estimation curves, define different time (operational cycles) thresholds (for the two different classes of datasets, FD1–FD3 (single operational conditions) and FD2–FD4 (multiple operational condition), when the survival probability starts to decrease, standing at cycle 125 for the first set and cycle 150 for the second set.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 4. Commercial Modular Aeropropulsion Simulation System (CMAPSS)Dataset
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“[Figure 6](https://doi.org/10.3390/fi17060244#fig_body_display_futureinternet-17-00244-f006), which refers to the FD1 dataset, clearly shows how the survival threshold and the sensor drift (Nc sensor) are correlated”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 4. Commercial Modular Aeropropulsion Simulation System (CMAPSS)Dataset
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Models such as CNN-GRU and BiLSTM consistently demonstrate superior performance, particularly in the FD4–FD2 datasets (see [Section 4](https://doi.org/10.3390/fi17060244#sec4-futureinternet-17-00244)), suggesting that their capacity to capture both temporal dependencies and localized signal variations is instrumental in handling complex operational regimes.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 7. Discussion
hedgedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The highest $R^{2}$ values and the lowest error metrics (MSE, MAE, RMSE) for the FD1–FD3 dataset class are achieved using the N-BEATS model, suggesting that the chosen architectures can capture sensor behavior more effectively when fewer operating regimes and clearly defined fault modes are involved.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 6. Experimental Results and Performance Evaluation: A Case Study on CMAPSS Datasets > 6.3. Aggregate Performance Evaluation
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Moreover, the weighted margin estimator stands out for its ability to adapt to local trends in the residual distribution, thereby delivering a compelling blend of coverage stability and predictive adaptability.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 8. Conclusions
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
20 more claims
Create a free account to see all 101 claims and every source verdict.
- Probably not a substantial claim. 55
- It may state two separate claims as one. 35
- The quote only partly states this claim. 7
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 5. Robust Conformal Prognostic for Reliable Predictive Maintenance > 5.3. Experimental Setting
“It ensures that the chosen CI meets the desired coverage level while effectively balancing the width of the prediction intervals and the predictive performance and chooses the best strategic approach.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > References
“| Bootstrap | 41.66 | 0.513 |”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“| MSE | 347.67 | 300.32 | 226.29 | 505.239090 | | MAE | 14.34 | 13.06 | 10.610778 | 17.281365 | | RMSE | 18.64 | 17.73 | 15.04 | 22.477524 |”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > References
Reported 300.32 · recomputed 314.3529
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > References
“| Bootstrap | 41.66 | 0.513 |”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > References
“| Margin | 40.171 | 41.63 | 36.06 | 64.52 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 6. Experimental Results and Performance Evaluation: A Case Study on CMAPSS Datasets > 6.1. Detailed Performance Analysis on FD004
“### 6.1. Detailed Performance Analysis on FD004”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 6. Experimental Results and Performance Evaluation: A Case Study on CMAPSS Datasets > 6.1. Detailed Performance Analysis on FD004
“**Figure 9.** Aggregated FD2 loss curves for LSTM, BiLSTM, N-BEATS, and CNN-GRU, illustrating differences in convergence behaviors.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > 4. Commercial Modular Aeropropulsion Simulation System (CMAPSS)Dataset
“Specifically, FD001 and FD002 consist of 100 engine units each, whereas FD003 and FD004 consist of 260 and 249 units, respectively.”
§ A Robust Conformal Framework for IoT-Based Predictive Maintenance > References
“| Engine units (train) | 100 | 260 | 100 | 249 |”
Citations
Cites
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
A review on machinery diagnostics and prognostics implementing condition-based maintenance
Jardine, A. K. S., Lin, D., & Banjevic, D. (2006) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2005.09.012 · Cited by 4,816
Forecasting principles and practice
Hyndman, R. J., & Athanasopoulos, G. (2018) · Cited by 4,405
Machinery health prognostics: A systematic review from data acquisition to RUL prediction
Lei, Y., Li, N., Guo, L., Li, N., Yan, T., & Lin, J. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2017.11.016 · Cited by 2,634
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
Fog Computing: A Platform for Internet of Things and Analytics
Bonomi, F., Milito, R., Natarajan, P., & Zhu, J. (2014) · Studies in Computational Intelligence · doi:10.1007/978-3-319-05029-4_7 · Cited by 1,222
An Introduction to Predictive Maintenance
(2002) · Elsevier eBooks · doi:10.1016/b978-0-7506-7531-4.x5000-3 · Cited by 1,151
Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey
Zhang, W., Yang, D., & Wang, H. (2019) · IEEE Systems Journal · doi:10.1109/jsyst.2019.2905565 · Cited by 732
Fink, O., Wang, Q., Svensén, M., Dersin, P., Lee, W.-J., & Ducoffe, M. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103678 · Cited by 549
Predictive Maintenance Techniques
Mobley, R. K. (2002) · An Introduction to Predictive Maintenance · doi:10.1016/b978-075067531-4/50006-3 · Cited by 373
Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics
Arias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. (2021) · Data · doi:10.3390/data6010005 · Cited by 339
Conformal prediction beyond exchangeability
Barber, R. F., Candès, E. J., Ramdas, A., & Tibshirani, R. J. (2023) · The Annals of Statistics · doi:10.1214/23-aos2276 · Cited by 305
Machine Learning approach for Predictive Maintenance in Industry 4.0
Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., & Loncarski, J. (2018) · 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA) · doi:10.1109/mesa.2018.8449150 · Cited by 296
Zhou, H., Huang, X., Wen, G., Lei, Z., Dong, S., Zhang, P., & Chen, X. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117297 · Cited by 212
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
Oreshkin, B. N., Carpov, D., Chapados, N., & Bengio, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10437 · Cited by 162
Improved Online Conformal Prediction via Strongly Adaptive Online LearningPreprint
Bhatnagar, A., Wang, H., Xiong, C., & Bai, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.07869 · Cited by 143
Žunić, E., Korjenić, K., Hodžić, K., & Đonko, D. (2020) · International Journal of Computer Science and Information Technology · doi:10.5121/ijcsit.2020.12203 · Cited by 130
Šimundić, A.-M. (2008) · Biochemia Medica · doi:10.11613/bm.2008.015 · Cited by 99
System Health Management: With Aerospace Applications
(2011) · doi:10.1002/9781119994053 · Cited by 98
RUL prediction of lithium ion battery based on CEEMDAN-CNN BiLSTM model
Guo, X., Wang, K., Yao, S., Fu, G., & Ning, Y. (2023) · Energy Reports · doi:10.1016/j.egyr.2023.05.121 · Cited by 95
Integrated Vehicle Health Management: Perspectives on an Emerging Field
(2011) · doi:10.4271/r-405 · Cited by 77
A Comprehensive Review of Remaining Useful Life Estimation Approaches for Rotating Machinery
Kumar, S., Raj, K. K., Cirrincione, M., Cirrincione, G., Franzitta, V., & Kumar, R. (2024) · Energies · doi:10.3390/en17225538 · Cited by 68
Fernandes, M., Canito, A., Bolón‐Canedo, V., Conceição, L., Praça, I., & Marreiros, G. (2018) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2018.10.006 · Cited by 65
A data-driven approach for condition-based maintenance optimization
Cai, Y., Teunter, R. H., & de Jonge, B. (2023) · European Journal of Operational Research · doi:10.1016/j.ejor.2023.05.002 · Cited by 43
Remaining useful life (RUL) regression using Long–Short Term Memory (LSTM) networks
Yousuf, S., Khan, S. A., & Khursheed, S. (2022) · Microelectronics Reliability · doi:10.1016/j.microrel.2022.114772 · Cited by 42
End-to-End Industrial IoT Platform for Actionable Predictive Maintenance
Christou, I. T., Kefalakis, N., Zalonis, A., Soldatos, J., & Bröchler, R. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.11.028 · Cited by 41
The Adoption of Prognostic Technologies in Maintenance Decision Making: A Multiple Case Study
Tiddens, W. W., Braaksma, A. J. J., & Tinga, T. (2015) · Procedia CIRP · doi:10.1016/j.procir.2015.08.028 · Cited by 38
Prediction of remaining useful life using the CNN-GRU network: A study on maintenance management
Azyus, A. F., Wijaya, S. K., & Naved, M. I. (2023) · Software Impacts · doi:10.1016/j.simpa.2023.100535 · Cited by 28
Saidy, C., Xia, K., Kircaliali, A., et al. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-3-030-57745-2_87 · Cited by 18
Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction
Qian, W., Zhao, C., Li, Y., Ma, F., Zhang, C., & Huai, M. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i13.29382 · Cited by 16
Intelligent Systems in Maintenance Planning and Management
Sirvio, K. M. (2015) · Intelligent systems reference library · doi:10.1007/978-3-319-17906-3_10 · Cited by 15
Wang, Y., & Politis, D. N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12156 · Cited by 2
Research works printed but not linked: 2
- Jennions, I. (2011). Algorithms and their impact on integrated vehicle health management. Integrated Vehicle Health Management: Perspectives on an Emerging Field, SAE International. · DOI · Paper page
- Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2020). On Calibration of Modern Neural Networks. arXiv.
Cited by
Predictive maintenance: A historical survey of models with imperfect inspections
Ulansky, V., & Raza, A. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111939 · Cited by 7
Maintenance-Aware Risk Curves: Correcting Degradation Models with Intervention Effectiveness
Bellido-López, F. J., Sanz-Bobi, M. A., Roque, A. M. S., et al. (2025) · Applied Sciences · doi:10.3390/app152010998 · Cited by 1
Bisht, S. C. S. S. (2025) · International Journal of Research & Technology · doi:10.64882/ijrt.v13.i3.484
AI Design Principles for Compliance-Driven Industrial IoT Systems
Amato, F., Ghosh, R. C., Moccardi, A., & Pelosi, M. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-10344-4_22 · Cited by 1
Self-citationU-TraCE: a conformal prediction approach to uncertainty quantification in black-box models
Marchi, E., & Liebl, M. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae35ce · Cited by 1
Metadata
- Authors
- Moccardi, A., Conte, C., Chandra Ghosh, R., & Moscato, F.
- Affiliations
- University of Naples Federico II (IT)
- Department of Electrical Engineering and Information Technology, University of Naples Federico II, 80125 Naples, Italy
- University of Salerno (IT)
- Corresponding author
- Moccardi, Alberto
- Venue
- Future Internet
- Publisher
- MDPI AG
- Published
- 2025-05-30
- Volume
- 17
- Issue
- 6
- Pages
- 244
- ISSN
- 1999-5903 (ISSN-L)
- OpenAlex
- W4410902221
- Semantic Scholar
- 03801e87a2bdc5f38e7aa4b2c759a56db685d333
- Cited by
- 12
- References
- 30
- Citations by year
- 2026: 7 · 2025: 5
- FWCI
- 3.33
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Future Internet (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- PNRR MUR (PE0000013-FAIR)
- 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 › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- predictive maintenance, uncertainty quantification, conformal prediction, remaining useful life prediction, C-MAPSS dataset, bootstrapping, confidence intervals, prognostics, Industrial Internet of Things, deep learning, machine learning
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.