Analysis of neural network structure for implementation of the prescriptive maintenance strategy
Authors:
- Grzegorz Filo,
- Paweł Lempa
Abstract
This paper provides an initial analysis of neural network implementation possibilities in practical implementations of the prescriptive maintenance strategy. The main issues covered are the preparation and processing of input data, the choice of artificial neural network architecture and the models of neurons used in each layer. The methods of categorisation and normalisation within each distinguished category were proposed in input data. Based on the normalisation results, it was suggested to use specific neuron activation functions. As part of the network structure, the applied solutions were analysed, including the number of neuron layers used and the number of neurons in each layer. In further work, the proposed structures of neural networks may undergo a process of supervised or partially supervised training to verify the accuracy and confidence level of the results they generate.
- Record ID
- CUTc5eeeca695414bb3b7dc3adeffb28a8d
- Publication categories
- ; ;
- Author
- Pages
- 273-280
- Other elements of collation
- rys.; wykr.; Bibliografia (na s.) - 278-280; Bibliografia (liczba pozycji) - 29; Oznaczenie streszczenia - Abstr.
- Substantive notes
- Punktacja MNiSW/MEiN (rozdział) - 5
- Book
- Radek Norbert Norbert Radek (eds.): Terotechnology XII : 12th Conference on Terotechnology, 20-21 October 2021, Kielce, Poland, Materials Research Proceedings, no. 24, 2022, Millersville, PA, Materials Research Forum LLC, ISBN 978-1-64490-204-2 (print)
- Keywords in English
- artificial neural network, neuron model, layer model, prescriptive maintenance, input signal normalisation
- DOI
- DOI:10.21741/9781644902059-40 Opening in a new tab
- URL
- https://doi.org/10.21741/9781644902059-40 Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 20
- Score source
- journalList
- Score
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTc5eeeca695414bb3b7dc3adeffb28a8d/
- URN
urn:pkr-prod:CUTc5eeeca695414bb3b7dc3adeffb28a8d
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.