Deep neural networks (DNNs) obtained remarkable achievements in remaining useful life (RUL) prediction of industrial components. The architectures of these DNNs are usually determined empirically, usually with the goal of minimizing prediction error without considering the time needed for training. However, such a design process is timeconsuming as it is essentially based on trial-and-error. Moreover, this process may be inappropriate in those industrial applications where the DNN model should take into account not only the prediction accuracy but also the training computational cost. To address this challenge, we present a neural architecture search (NAS) technique based on an evolutionary algorithm (EA) that explores the combinatorial parameter space of a one-dimensional convolutional neural network (1-D CNN) to search for the best architectures in terms of a trade-off between RUL prediction error and number of trainable parameters. In particular, a novel way to accelerate the NAS is introduced in this paper. We successfully shorten the lengthy training process by making use of two techniques, namely architecture score without training and extrapolation of learning curves. We test our method on a recent benchmark dataset, the N-CMAPSS, on which we search for trade-off solutions (in terms of prediction error vs. number of trainable parameters) using NAS. The results show that our method considerably reduces the training time (and, as a consequence, the total time of the evolutionary search), yet successfully discovers architectures compromising the two objectives.

Accelerating Evolutionary Neural Architecture Search for Remaining Useful Life Prediction / Mo, Hyunho; Iacca, Giovanni. - 13627:(2022), pp. 15-30. (Intervento presentato al convegno BIOMA 2022 tenutosi a Maribor nel 17th -18th November 2022) [10.1007/978-3-031-21094-5_2].

Accelerating Evolutionary Neural Architecture Search for Remaining Useful Life Prediction

Mo, Hyunho;Iacca, Giovanni
2022-01-01

Abstract

Deep neural networks (DNNs) obtained remarkable achievements in remaining useful life (RUL) prediction of industrial components. The architectures of these DNNs are usually determined empirically, usually with the goal of minimizing prediction error without considering the time needed for training. However, such a design process is timeconsuming as it is essentially based on trial-and-error. Moreover, this process may be inappropriate in those industrial applications where the DNN model should take into account not only the prediction accuracy but also the training computational cost. To address this challenge, we present a neural architecture search (NAS) technique based on an evolutionary algorithm (EA) that explores the combinatorial parameter space of a one-dimensional convolutional neural network (1-D CNN) to search for the best architectures in terms of a trade-off between RUL prediction error and number of trainable parameters. In particular, a novel way to accelerate the NAS is introduced in this paper. We successfully shorten the lengthy training process by making use of two techniques, namely architecture score without training and extrapolation of learning curves. We test our method on a recent benchmark dataset, the N-CMAPSS, on which we search for trade-off solutions (in terms of prediction error vs. number of trainable parameters) using NAS. The results show that our method considerably reduces the training time (and, as a consequence, the total time of the evolutionary search), yet successfully discovers architectures compromising the two objectives.
2022
Bioinspired Optimization Methods and Their Applications (BIOMA) 2022
Cham, Svizzera
Springer
978-3-031-21093-8
978-3-031-21094-5
Mo, Hyunho; Iacca, Giovanni
Accelerating Evolutionary Neural Architecture Search for Remaining Useful Life Prediction / Mo, Hyunho; Iacca, Giovanni. - 13627:(2022), pp. 15-30. (Intervento presentato al convegno BIOMA 2022 tenutosi a Maribor nel 17th -18th November 2022) [10.1007/978-3-031-21094-5_2].
File in questo prodotto:
File Dimensione Formato  
Accelerating Evolutionary Neural Architecture Search for Remaining Useful Life Prediction.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 754.57 kB
Formato Adobe PDF
754.57 kB Adobe PDF   Visualizza/Apri
Accelerating_Evolutionary_Neural_Architecture_Search_for_Remaining_Useful_Life_Prediction.pdf

Open Access dal 13/11/2023

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 748.99 kB
Formato Adobe PDF
748.99 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/357522
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact