Skoči na glavni sadržaj

Izvorni znanstveni članak

Studying the possibility of neural network application in the diagnostics of a small four-stroke petrol engine by wear particle content

Dragutin Lisjak orcid id orcid.org/0000-0002-9976-577X ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Ivana Lučića 5, 10000 Zagreb, Croatia
Gojko Marić ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Ivana Lučića 5, 10000 Zagreb, Croatia
Nedjeljko Štefanić ; Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Ivana Lučića 5, 10000 Zagreb, Croatia


Puni tekst: hrvatski pdf 1.087 Kb

str. 857-862

preuzimanja: 423

citiraj

Puni tekst: engleski pdf 1.087 Kb

str. 857-862

preuzimanja: 430

citiraj


Sažetak

This paper presents the application of artificial neural network (ANN) in engine diagnostics. One-layer feed-forward neural network which is trained using a back-propagation algorithm that updates the weights and biases values according to Levenberg-Marquardt algorithm has been established to predict the Wear Particle Content (WPC) using the number of working hours of the motor engine as input parameter. The generalization property of the developed ANN is very high, which is confirmed by a very good match between the predicted and the targeted values on a new data set that was not included in the training data set.

Ključne riječi

neural network; maintenance; motor engine diagnostics

Hrčak ID:

93559

URI

https://hrcak.srce.hr/93559

Datum izdavanja:

12.12.2012.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.591 *