A predictive maintenance model using Long Short-Term Memory neural networks and Bayesian inference
Davide Pagano
The fourth industrial revolution is a profound transformation utilizing emerging technologies like smart automation, large-scale machine-to-machine communication, and the internet of things to change traditional manufacturing and industrial practices. The analysis of the huge amount of data collected in all modern industrial plants not only greatly benefited from modern tools of artificial intelligence but has also spurred the development of new ones. In this context, we present a new approach based on the combined use of Long Short-Term Memory (LSTM) neural networks and Bayesian inference for the predictive maintenance of an industrial plant. Hotelling's T2 and Q metrics, assessing the degree of compatibility between the time-evolving industrial data and the output of the LSTM, trained on a reference period of good working condition, are used to update the Bayesian posterior probability about the good working condition of the plant. This method has successfully been applied to a real industrial case, and the results are presented and discussed.
Year of publication: |
2023
|
---|---|
Authors: | Pagano, Davide |
Published in: |
Decision analytics journal. - Amsterdam : Elsevier, ISSN 2772-6622, ZDB-ID 3106160-6. - Vol. 6.2023, Art.-No. 100174, p. 1-8
|
Subject: | Bayesian inference | Industrial plant | Long short-term memory | Neural networks | Predictive maintenance | Theorie | Theory | Neuronale Netze | Prognoseverfahren | Forecasting model | Bayes-Statistik | Instandhaltung | Maintenance policy |
Saved in:
freely available
Saved in favorites
Similar items by subject
-
Predictive maintenance of complex system with multi-level reliability structure
Lee, Dongjin, (2017)
-
Leukel, Jörg, (2023)
-
An intelligence-based model for condition monitoring using artificial neural networks
Jenab, K., (2013)
- More ...