Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment

Francisco De Nolasco Santos; Pietro D'Antuono; Nymfa Noppe; Wout Weijtjens; Christof Devriendt

doi:10.14428/esann/2022.ES2022-16

Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment

Francisco De Nolasco Santos, Pietro D'Antuono, Nymfa Noppe, Wout Weijtjens, Christof Devriendt

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

Abstract

In this contribution we present a physics-informed neural network (PINN) approach for wind turbine fatigue estimation. This PINN incorporates physical information of the structure’s fatigue profile in its loss function, referred to as Minkowski logarithmic error (MLE) - an extension of the log loss for any given L p space. The function is mathematically analysed and differentiated in order to better understand its behaviour. The results obtained using the MLE are favourably compared with previous efforts using the mean squared logarithmic error. Finally, the long-term error is evaluated based on the effect of p.

Original language	English
Title of host publication	European Symposium on Artificial Neural Networks 2022
Publisher	European Symposium on Artificial Neural Networks
Pages	357-362
Number of pages	5
ISBN (Electronic)	978287587084-1
DOIs	https://doi.org/10.14428/esann/2022.ES2022-16
Publication status	Published - 2022
Event	30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2022 - Bruges, Belgium Duration: 5 Oct 2022 → 7 Oct 2022

Conference

Conference	30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2022
Country/Territory	Belgium
City	Bruges
Period	5/10/22 → 7/10/22

Access to Document

10.14428/esann/2022.ES2022-16

Cite this

@inproceedings{84b00191e3f34e13b9b854f5257321f9,

title = "Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment",

abstract = "In this contribution we present a physics-informed neural network (PINN) approach for wind turbine fatigue estimation. This PINN incorporates physical information of the structure{\textquoteright}s fatigue profile in its loss function, referred to as Minkowski logarithmic error (MLE) - an extension of the log loss for any given L p space. The function is mathematically analysed and differentiated in order to better understand its behaviour. The results obtained using the MLE are favourably compared with previous efforts using the mean squared logarithmic error. Finally, the long-term error is evaluated based on the effect of p. ",

author = "{De Nolasco Santos}, Francisco and Pietro D'Antuono and Nymfa Noppe and Wout Weijtjens and Christof Devriendt",

year = "2022",

doi = "10.14428/esann/2022.ES2022-16",

language = "English",

pages = "357--362",

booktitle = "European Symposium on Artificial Neural Networks 2022",

publisher = "European Symposium on Artificial Neural Networks",

note = "30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2022 ; Conference date: 05-10-2022 Through 07-10-2022",

}

De Nolasco Santos, F , D'Antuono, P , Noppe, N , Weijtjens, W & Devriendt, C 2022, Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment. in European Symposium on Artificial Neural Networks 2022. European Symposium on Artificial Neural Networks, pp. 357-362, 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2022, Bruges, Belgium, 5/10/22. https://doi.org/10.14428/esann/2022.ES2022-16

Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment. / De Nolasco Santos, Francisco ; D'Antuono, Pietro ; Noppe, Nymfa et al.
European Symposium on Artificial Neural Networks 2022. European Symposium on Artificial Neural Networks, 2022. p. 357-362.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

TY - GEN

T1 - Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment

AU - De Nolasco Santos, Francisco

AU - D'Antuono, Pietro

AU - Noppe, Nymfa

AU - Weijtjens, Wout

AU - Devriendt, Christof

PY - 2022

Y1 - 2022

N2 - In this contribution we present a physics-informed neural network (PINN) approach for wind turbine fatigue estimation. This PINN incorporates physical information of the structure’s fatigue profile in its loss function, referred to as Minkowski logarithmic error (MLE) - an extension of the log loss for any given L p space. The function is mathematically analysed and differentiated in order to better understand its behaviour. The results obtained using the MLE are favourably compared with previous efforts using the mean squared logarithmic error. Finally, the long-term error is evaluated based on the effect of p.

AB - In this contribution we present a physics-informed neural network (PINN) approach for wind turbine fatigue estimation. This PINN incorporates physical information of the structure’s fatigue profile in its loss function, referred to as Minkowski logarithmic error (MLE) - an extension of the log loss for any given L p space. The function is mathematically analysed and differentiated in order to better understand its behaviour. The results obtained using the MLE are favourably compared with previous efforts using the mean squared logarithmic error. Finally, the long-term error is evaluated based on the effect of p.

U2 - 10.14428/esann/2022.ES2022-16

DO - 10.14428/esann/2022.ES2022-16

M3 - Conference paper

SP - 357

EP - 362

BT - European Symposium on Artificial Neural Networks 2022

PB - European Symposium on Artificial Neural Networks

T2 - 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2022

Y2 - 5 October 2022 through 7 October 2022

ER -

Minkowski logarithmic error: A physics-informed neural network approach for wind turbine lifetime assessment

Abstract

Conference

Access to Document

Fingerprint

Cite this