Practical options for adopting recurrent neural network and its variants on remaining useful life prediction

Simple item page
dc.contributor.authorWang, Youdao
dc.contributor.authorZhao, Yifan
dc.contributor.authorAddepalli, Sri
dc.date.accessioned2021-07-15T10:09:16Z
dc.date.available2021-07-15T10:09:16Z
dc.date.issued2021-07-12
dc.description.abstractThe remaining useful life (RUL) of a system is generally predicted by utilising the data collected from the sensors that continuously monitor different indicators. Recently, different deep learning (DL) techniques have been used for RUL prediction and achieved great success. Because the data is often time-sequential, recurrent neural network (RNN) has attracted significant interests due to its efficiency in dealing with such data. This paper systematically reviews RNN and its variants for RUL prediction, with a specific focus on understanding how different components (e.g., types of optimisers and activation functions) or parameters (e.g., sequence length, neuron quantities) affect their performance. After that, a case study using the well-studied NASA’s C-MAPSS dataset is presented to quantitatively evaluate the influence of various state-of-the-art RNN structures on the RUL prediction performance. The result suggests that the variant methods usually perform better than the original RNN, and among which, Bi-directional Long Short-Term Memory generally has the best performance in terms of stability, precision and accuracy. Certain model structures may fail to produce valid RUL prediction result due to the gradient vanishing or gradient exploring problem if the parameters are not chosen appropriately. It is concluded that parameter tuning is a crucial step to achieve optimal prediction performance .en_UK
dc.identifier.citationWang Y, Zhao Y, Addepalli S. (2021) Practical options for adopting recurrent neural network and its variants on remaining useful life prediction. Chinese Journal of Mechanical Engineering, Volume 34, July 2021, Article number 69en_UK
dc.identifier.issn1000-9345
dc.identifier.urihttps://doi.org/10.1186/s10033-021-00588-x
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/16881
dc.language.isoenen_UK
dc.publisherSpringeren_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectGated recurrent uniten_UK
dc.subjectBi-directional long short-term memoryen_UK
dc.subjectLong short-term memoryen_UK
dc.subjectRecurrent neural networken_UK
dc.subjectDeep learningen_UK
dc.subjectRemaining useful life predictionen_UK
dc.titlePractical options for adopting recurrent neural network and its variants on remaining useful life predictionen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Practical_options_adopting_recurrent_neural_network_and_variants-2021.pdf
Size:
2.23 MB
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)