Fusion Approach for Prognostics Framework of Heritage Structure

Rosunally, Yasmine; Stoyanov, Stoyan; Bailey, C.; Mason, Peter C.; Campbell, S. A.; Monger, George; Bell, Ian M.

doi:10.1109/tr.2011.2104451

Cited by 10 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimization-based KM [10] Distance-based [12], [13], [14] CNN [15] * , [16] LSTM [15] * GPR [17] * Feature-level KPCA [18], [19] (1) Degradation characteristics can be enhanced by using independent feature-level analysis techniques;…”

Section: Data-levelmentioning

confidence: 99%

“…Bayesian network [13] AdaBoost [30] Stacking [30] * : hybrid information fusion on more than a single level predefined Failure Threshold (FT), i.e., the predicted last value from a regression model for each CM signal at the End of Life (EoL) of each degraded unit. This category of distance-based methods fuses the information in a nonlinear way without optimizing desired properties for prediction, and the pattern of fusion is also fixed.…”

Section: Data-levelmentioning

confidence: 99%

“…For an in-situ operating monitored system, based on the signal from source j, CDF of its RUL can be independently derived as F * ,j|RU L≥0 (t) according to (13), and the Probability Density Function (PDF) can be obtained as P * ,j|RU L≥0 (t) = dF * ,j|RU L≥0 (t) /dt, and consequently, they can be combined in the frame of BFT.…”

Section: B Decision Fusion For Estimating Remaining Useful Lifementioning

confidence: 99%

See 2 more Smart Citations

Remaining Useful Life Prediction of IIoT-Enabled Complex Industrial Systems With Hybrid Fusion of Multiple Information Sources

Wen

Chen

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

Industrial Internet of Things has significantly boosted predictive maintenance for complex industrial systems, where the accurate prediction of remaining useful life with high-level confidence is challenging. By aggregating multiple informative sources of system degradation, information fusion can be applied to improve the prediction accuracy and reduce the uncertainty. It can be performed on the data-level, featurelevel, and decision-level. To fully exploit the available degradation information, this paper proposes a hybrid fusion method on both the data level and decision level to predict the remaining useful life. On the data level, Genetic Programming is adopted to integrate physical sensor sources into a composite health indicator, resulting in an explicit nonlinear data-level fusion model. Subsequently, the predictions of the remaining useful life based on each physical sensor and the developed composite health indicator are synthesized in the framework of belief functions theory, as the decision-level fusion method. Moreover, the decision-level method is flexible for incorporating other statistical data-driven methods with explicit estimations of the remaining useful life. The proposed method is verified via a case study on NASA's C-MAPSS data set. Compared to the singlelevel fusion methods, the results confirm the superiority of the proposed method for higher accuracy and certainty of predicting the remaining useful life.

show abstract

Section: Data-levelmentioning

confidence: 99%

Section: Data-levelmentioning

confidence: 99%

Section: B Decision Fusion For Estimating Remaining Useful Lifementioning

confidence: 99%

See 1 more Smart Citation

Remaining Useful Life Prediction of IIoT-Enabled Complex Industrial Systems With Hybrid Fusion of Multiple Information Sources

Wen

Chen

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Therefore, the accuracy of the fusion approach should be higher than both model and data driven approaches when used individually [26], although for a real-time analysis it may not be suitable due to 215 the significant computational resources required. The fusion approach has been reported to be used in many applications before [26,64,65,66,67,68,69].…”

Section: Fusion Approachmentioning

confidence: 99%

“…As prognostics can provide state-of-health (SOH) and RUL information of the fuel cell, the operation of the fuel cell can be optimised using an appropriate control strategy. Maintenance tasks can be scheduled, thus 65 reducing down time. Although prognostics was used in safety critical systems in early days, it is nowadays an integral part in many engineering systems, products and applications [26].…”

mentioning

confidence: 99%

A review on prognostics and health monitoring of proton exchange membrane fuel cell

Sutharssan

Montalvão

Chen

et al. 2017

Renewable and Sustainable Energy Reviews

197

View full text Add to dashboard Cite

Fuel cell technology can be traced back to 1839 when British scientist Sir William Grove discovered that it was possible to generate electricity by the reaction between hydrogen and oxygen gases. However, fuel cell still cannot compete with internal combustion engines although they have many advantages including zero carbon emissions. Fossil fuels are cheaper and present very high volumetric energy densities compared with the hydrogen gas. Furthermore, hydrogen storage as a liquid is still a huge challenge. Another important disadvantage is the lifespan of the fuel cell because of their durability, reliability and maintainability.Prognostics is an emerging technology in sustainability of engineering systems through failure prevention, reliability assessment and remaining useful lifetime estimation. Prognostics and health monitoring can play a critical role in enhancing the durability, reliability and maintainability of the fuel cell system. This paper presents a review on the current state-of-the-art in prognostics and health monitoring of Proton Exchange Membrane Fuel Cell (PEMFC), aiming at identifying research and development opportunities in these fields. This paper also highlights the importance of incorporating prognostics and failure modes, mechanisms and effects analysis (FMMEA) in PEMFC to give them sustainable * Corresponding author Email address: (tsutharssan@iee.org) (Thamo Sutharssan)Preprint submitted to Renewable & Sustainable Energy Reviews November 14, 2016 competitive advantage when compared with other non-clean energy solutions.

show abstract

Maintenance Modeling and Policies

Wang

Pham

2013

Springer Series in Reliability Engineering

View full text Add to dashboard Cite

Fusion Approach for Prognostics Framework of Heritage Structure

Cited by 10 publications

References 17 publications

Remaining Useful Life Prediction of IIoT-Enabled Complex Industrial Systems With Hybrid Fusion of Multiple Information Sources

Remaining Useful Life Prediction of IIoT-Enabled Complex Industrial Systems With Hybrid Fusion of Multiple Information Sources

A review on prognostics and health monitoring of proton exchange membrane fuel cell

Maintenance Modeling and Policies

Contact Info

Product

Resources

About