Development of the Forecasting Model for the Complex Technical Systems' Failures Time During the Proactive Maintenance Using the Recurrent Neural Networks' Technology

Demidova, Liliya; Marchev, D.V.

doi:10.1109/summa50634.2020.9280781

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…because it allows us to deduce the future values of a series from its past values with a margin of error. Numerous successful applications in several domains, such as engineering [3,4] and manufacturing, energy production and management [5,6], and other fields, have been documented in the appropriate literature. The use of deep learning tools for forecasting time series data trends is relatively recent, and continues to attract the attention of the scientific community in different fields of technology.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Recurrent neural network optimization for wind turbine condition prognosis

Kerboua¹,

Kelaiaia²

2022

Diagnostyka

View full text Add to dashboard Cite

This research focuses on employing Recurrent Neural Networks (RNN) to prognosis a wind turbine operation's health from collected vibration time series data, by using several memory cell variations, including Long Short Time Memory (LSTM), Bilateral LSTM (BiLSTM), and Gated Recurrent Unit (GRU), which are integrated into various architectures. We tune the training hyperparameters as well as the adapted depth and recurrent cell number of the proposed networks to obtain the most accurate predictions. Tuning those parameters is a hard task and depends widely on the experience of the designer. This can be resolved by integrating the training process in a Bayesian optimization loop where the loss is considered as the objective function to minimize. The obtained results show the effectiveness of the proposed method, which generates more accurate recurrent models with a more accurate prognosis of the operating state of the wind turbine than those generated using trivial training parameters.

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%