Dynamic multistep uncertainty prediction in spatial geometry

Simple item page
dc.contributor.authorGrenyer, Alex
dc.contributor.authorSchwabe, Oliver
dc.contributor.authorErkoyuncu, John Ahmet
dc.contributor.authorZhao, Yifan
dc.date.accessioned2021-02-17T19:29:12Z
dc.date.available2021-02-17T19:29:12Z
dc.date.issued2021-02-10
dc.description.abstractMaintenance procedures for complex engineering systems are increasingly determined by predictive algorithms based on historic data, experience and knowledge. Such data and knowledge is accompanied by varying degrees of uncertainty which impact equipment availability, turnaround time and unforeseen costs throughout the system life cycle. Once quantified, these uncertainties call for robust forecasting to facilitate dependable maintenance costing and ensure equipment availability. This paper builds on the theory of spatial geometry as a methodology to forecast uncertainty where available data is insufficient for the application of traditional statistical analysis. To ensure continuous forecast accuracy, a conceptual dynamic multistep prediction model is presented applying spatial geometry with long-short term memory (LSTM) neural networks. Based in MATLAB, this deep learning model predicts uncertainty for the in-service life of a given system. The further into the future the model predicts, the lower the confidence in the uncertainty prediction. Forecasts are therefore also made for a single time step ahead. When this single step is reached in real time, the next step is forecast and used to update the long range prediction. The uncertainty here is contributed by an aggregation of quantitative data and qualitative, subjective expert opinions and additional traits such as environmental conditions. It is therefore beneficial to indicate which of these factors prompts the greatest impact on the aggregated uncertainty for each forecast point. Future work will include the option to simulate and interpolate input data to enhance the accuracy of the LSTM and explore suitable approaches to mitigate, tolerate or exploit uncertainty through deep learning.en_UK
dc.identifier.citationGrenyer A, Schwabe O, Erkoyuncu JA, Zhao Y. (2021) Dynamic multistep uncertainty prediction in spatial geometry. Procedia CIRP, Volume 96, pp.74-79. 8th CIRP Global Web Conference (CIRPe 2020): Flexible mass customisation, 14-16 October 2020, Virtual Eventen_UK
dc.identifier.issn2212-8271
dc.identifier.urihttps://doi.org/10.1016/j.procir.2021.01.055
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/16368
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectUncertaintyen_UK
dc.subjectSpatial geometryen_UK
dc.subjectPredictionen_UK
dc.subjectMultistepen_UK
dc.subjectLong-short term memory (LSTM)en_UK
dc.subjectForecasten_UK
dc.titleDynamic multistep uncertainty prediction in spatial geometryen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dynamic_mulitstep_uncertainty_prediction-2021.pdf
Size:
962.66 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)