- Tytuł:
- The identification method of the coal mill motor power model with the use of machine learning techniques
- Autorzy:
-
Łabęda-Grudziak, Zofia Magdalena
Lipiński, Mariusz - Powiązania:
- https://bibliotekanauki.pl/articles/2090698.pdf
- Data publikacji:
- 2021
- Wydawca:
- Polska Akademia Nauk. Czytelnia Czasopism PAN
- Tematy:
-
coal mill motor power
nonlinear model identification
machine learning
additive regression models
process monitoring
moc silnika młyna węglowego
identyfikacja modelu nieliniowa
nauczanie maszynowe
model regresji addytywny
monitorowanie procesu - Opis:
- The article presents an identification method of the model of the ball-and-race coal mill motor power signal with the use of machine learning techniques. The stages of preparing training data for model parameters identification purposes are described, as well as these aimed at verifying the quality of the evaluated model. In order to meet the tasks of machine learning, additive regression model was applied. Identification of the additive model parameters was performed on the basis of iterative backfitting algorithm combined with nonparametric estimation techniques. The proposed models have predictive nature and are aimed at simulation of the motor power signal of a coal mill during its regular operation, startup and shutdown. A comparative analysis has been performed of the models structured differently in terms of identification quality and sensitivity to the existence of an exemplary disturbance in the form of overhangs in the coal bunker. Tests carried out on the basis of real measuring data registered in the Polish power unit with a capacity of 200 MW confirm the effectiveness of the method.
- Źródło:
-
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 1; e135842, 1--9
0239-7528 - Pojawia się w:
- Bulletin of the Polish Academy of Sciences. Technical Sciences
- Dostawca treści:
- Biblioteka Nauki
Artykuł