EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling

Marek Bělohoubek iD, Karel Liška iD, Zdeněk Kubín iD, Petr Polcar iD, Luboš Smolík iD, Pavel Polach iD

Sensors · 23.03.2024 · 24 (7) · 2056

DOI: 10.3390/s24072056 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.03.2024. Verfasst von Marek Bělohoubek und 5 weiteren Autor:innen. Beteiligte Einrichtung: Research and Testing Institute Plzen, Tylova 1581/46, 301 00 Plzen, Czech Republic. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Industry and Trade, Ministry of Industry and Trade of the Czech Republic.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study utilizes neural networks to detect and locate thermal anomalies in low-pressure steam turbines, some of which experienced a drop in efficiency. Standard approaches relying on expert knowledge or statistical methods struggled to identify the anomalous steam line due to difficulty in capturing nonlinear and weak relations in the presence of linear and strong ones. In this research, some inputs that linearly relate to outputs have been intentionally neglected. The remaining inputs have been used to train shallow feedforward or long short-term memory neural networks using measured data. The resulting models have been analyzed by Shapley additive explanations, which can determine the impact of individual inputs or model features on outputs. This analysis identified unexpected relations between lines that should not be connected. Subsequently, during periodic plant shutdown, a leak was discovered in the indicated line.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecondensing steam turbineheat balancelow-pressure turbinemachine learningnuclear power plant

Autor:innen und Institutionen

  • Research and Testing Institute Plzen, Tylova 1581/46, 301 00 Plzen, Czech Republic.

ORCID-Profile: Marek Bělohoubek, Karel Liška, Zdeněk Kubín, Petr Polcar, Luboš Smolík, Pavel Polach

Förderung

  • Ministry of Industry and Trade
  • Ministry of Industry and Trade of the Czech Republic

Zitieren

APA

Bělohoubek, M., Liška, K., Kubín, Z., Polcar, P., Smolík, L., & Polach, P. (2024). An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling. Sensors, 24(7), 2056. https://doi.org/10.3390/s24072056

Vancouver

Bělohoubek M, Liška K, Kubín Z, Polcar P, Smolík L, Polach P. An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling. Sensors. 2024;24(7):2056. doi:10.3390/s24072056

BibTeX
@article{Blohoubek2024,
  author = {Bělohoubek, Marek and Liška, Karel and Kubín, Zdeněk and Polcar, Petr and Smolík, Luboš and Polach, Pavel},
  title = {An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2056},
  doi = {10.3390/s24072056}
}
Kostenlos starten →