Instytut Podstawowych Problemów Techniki
Polskiej Akademii Nauk

Partnerzy

P. Bartosik


Ostatnie publikacje
1.  Badora M., Bartosik P., Graziano A., Szolc T.A., Using physics-informed neural networks with small datasets to predict the length of gas turbine nozzle cracks, Advanced Engineering Informatics, ISSN: 1474-0346, DOI: 10.1016/j.aei.2023.102232, Vol.58, No.102232, pp.1-16, 2023

Streszczenie:
We created a Physics-Informed Neural Network (PINN) to model the propagation of fatigue cracks. The analyzed object is a high-pressure Nozzle of an industrial gas turbine. The models are based on a Recurrent Neural Network with an embedded Feedforward Neural Network to estimate the stress intensity factor. The thermal stresses are calculated based on engine operational data, leveraging a Finite Element Analysis. However, the time series are available just for 54% of the start-stop cycles, and only 13 crack measures were recorded. Three separate models were trained based on ten, two, and one observation, respectively. The importance of the empirical data was regulated during the training to avoid solutions inconsistent with the underlying physics. The models generalize well and predict accurately also outside the training domain. Additionally, we propose a novel method of scaling models based on PINNs and transferring knowledge between domains. It enables predicting in the target domain, even if damage measures are unavailable. The obtained results confirm the effectiveness of this approach.

Słowa kluczowe:
Physics-informed neural networks , Predictive maintenance , Fatigue cracks , Regression analysis , Small data , Turbomachinery

Afiliacje autorów:
Badora M. - IPPT PAN
Bartosik P. - inna afiliacja
Graziano A. - inna afiliacja
Szolc T.A. - IPPT PAN
140p.

Kategoria A Plus

IPPT PAN

logo ippt            ul. Pawińskiego 5B, 02-106 Warszawa
  +48 22 826 12 81 (centrala)
  +48 22 826 98 15
 

Znajdź nas

mapka
© Instytut Podstawowych Problemów Techniki Polskiej Akademii Nauk 2024